From 7435a46b2d1ce1a1d13b35d96eff5f0439fed553 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sun, 16 Aug 2026 06:18:58 +0000 Subject: [PATCH] chore: sync model metadata --- .changeset/sync-models.md | 9 + packages/ai-anthropic/src/model-meta.ts | 80 + packages/ai-grok/src/model-meta.ts | 49 +- packages/ai-openai/src/model-meta.ts | 111 + packages/ai-openrouter/src/model-meta.ts | 11815 +++--- packages/ai-vercel-gateway/src/model-meta.ts | 87 +- scripts/.sync-models-last-run | 2 +- scripts/openrouter.models.json | 33594 +++++++++++------ scripts/vercel-gateway.models.json | 385 +- 9 files changed, 29709 insertions(+), 16423 deletions(-) create mode 100644 .changeset/sync-models.md diff --git a/.changeset/sync-models.md b/.changeset/sync-models.md new file mode 100644 index 0000000000..2090296541 --- /dev/null +++ b/.changeset/sync-models.md @@ -0,0 +1,9 @@ +--- +'@tanstack/ai-anthropic': patch +'@tanstack/ai-grok': patch +'@tanstack/ai-openai': patch +'@tanstack/ai-openrouter': patch +'@tanstack/ai-vercel-gateway': patch +--- + +Update model metadata from OpenRouter API diff --git a/packages/ai-anthropic/src/model-meta.ts b/packages/ai-anthropic/src/model-meta.ts index 591de69a5d..b3b248d27e 100644 --- a/packages/ai-anthropic/src/model-meta.ts +++ b/packages/ai-anthropic/src/model-meta.ts @@ -502,7 +502,67 @@ const CLAUDE_SONNET_5 = { * via the `speed` parameter, not a model id) were removed after Anthropic * turned them off. */ +const CLAUDE_OPUS_5 = { + name: 'claude-opus-5', + id: 'claude-opus-5', + context_window: 1_000_000, + max_output_tokens: 128_000, + supports: { + input: ['text', 'image', 'document'], + tools: [], + }, + pricing: { + input: { + normal: 5, + cached: 0.5, + }, + output: { + normal: 25, + }, + }, +} as const satisfies ModelMeta< + AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions +> + +const CLAUDE_OPUS_5_FAST = { + name: 'claude-opus-5-fast', + id: 'claude-opus-5-fast', + context_window: 1_000_000, + max_output_tokens: 128_000, + supports: { + input: ['text', 'image', 'document'], + tools: [], + }, + pricing: { + input: { + normal: 10, + cached: 1, + }, + output: { + normal: 50, + }, + }, +} as const satisfies ModelMeta< + AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions +> + export const ANTHROPIC_MODELS = [ + CLAUDE_OPUS_5.id, + CLAUDE_OPUS_5_FAST.id, CLAUDE_OPUS_4_6.id, CLAUDE_OPUS_4_5.id, CLAUDE_SONNET_4_6.id, @@ -552,6 +612,8 @@ const ANTHROPIC_MODEL_MAX_OUTPUT_TOKENS: Record = { [CLAUDE_OPUS_4_8.id]: CLAUDE_OPUS_4_8.max_output_tokens, [CLAUDE_FABLE_5.id]: CLAUDE_FABLE_5.max_output_tokens, [CLAUDE_SONNET_5.id]: CLAUDE_SONNET_5.max_output_tokens, + [CLAUDE_OPUS_5.id]: CLAUDE_OPUS_5.max_output_tokens, + [CLAUDE_OPUS_5_FAST.id]: CLAUDE_OPUS_5_FAST.max_output_tokens, } /** @@ -728,6 +790,22 @@ export type AnthropicChatModelProviderOptionsByName = { AnthropicToolChoiceOptions & AnthropicMaxTokensOptions & AnthropicOutputConfigOptions + [CLAUDE_OPUS_5.id]: AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions + [CLAUDE_OPUS_5_FAST.id]: AnthropicContainerOptions & + AnthropicContextManagementOptions & + AnthropicMCPOptions & + AnthropicServiceTierOptions & + AnthropicStopSequencesOptions & + AnthropicThinkingOptions & + AnthropicToolChoiceOptions & + AnthropicSamplingOptions } export type AnthropicChatModelToolCapabilitiesByName = { @@ -765,4 +843,6 @@ export type AnthropicModelInputModalitiesByName = { [CLAUDE_OPUS_4_8.id]: typeof CLAUDE_OPUS_4_8.supports.input [CLAUDE_FABLE_5.id]: typeof CLAUDE_FABLE_5.supports.input [CLAUDE_SONNET_5.id]: typeof CLAUDE_SONNET_5.supports.input + [CLAUDE_OPUS_5.id]: typeof CLAUDE_OPUS_5.supports.input + [CLAUDE_OPUS_5_FAST.id]: typeof CLAUDE_OPUS_5_FAST.supports.input } diff --git a/packages/ai-grok/src/model-meta.ts b/packages/ai-grok/src/model-meta.ts index 91c0d6105d..ea476fe998 100644 --- a/packages/ai-grok/src/model-meta.ts +++ b/packages/ai-grok/src/model-meta.ts @@ -29,6 +29,46 @@ interface ModelMeta { } } +const GROK_4_5 = { + name: 'grok-4.5', + context_window: 500_000, + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + capabilities: ['reasoning', 'structured_outputs', 'tool_calling'], + tools: [], + }, + pricing: { + input: { + normal: 2, + cached: 0.3, + }, + output: { + normal: 6, + }, + }, +} as const satisfies ModelMeta + +const GROK_4_6 = { + name: 'grok-4.6', + context_window: 500_000, + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + capabilities: ['reasoning', 'structured_outputs', 'tool_calling'], + tools: [], + }, + pricing: { + input: { + normal: 2, + cached: 0.5, + }, + output: { + normal: 6, + }, + }, +} as const satisfies ModelMeta + export type GrokProviderToolKind = | 'web_search' | 'x_search' @@ -175,7 +215,12 @@ const GROK_BUILD_0_1 = { /** * Grok chat models supported by the Responses adapter. */ -export const GROK_CHAT_MODELS = [GROK_BUILD_0_1.name, GROK_4_3.name] as const +export const GROK_CHAT_MODELS = [ + GROK_4_5.name, + GROK_4_6.name, + GROK_BUILD_0_1.name, + GROK_4_3.name, +] as const /** * Grok Image Generation Models @@ -261,6 +306,8 @@ export type GrokRealtimeModel = (typeof GROK_REALTIME_MODELS)[number] export type GrokModelInputModalitiesByName = { [GROK_4_3.name]: typeof GROK_4_3.supports.input [GROK_BUILD_0_1.name]: typeof GROK_BUILD_0_1.supports.input + [GROK_4_5.name]: typeof GROK_4_5.supports.input + [GROK_4_6.name]: typeof GROK_4_6.supports.input } /** diff --git a/packages/ai-openai/src/model-meta.ts b/packages/ai-openai/src/model-meta.ts index b8d0ff5287..1d401bdeba 100644 --- a/packages/ai-openai/src/model-meta.ts +++ b/packages/ai-openai/src/model-meta.ts @@ -2362,7 +2362,97 @@ const GPT_CHAT_LATEST = { OpenAIMetadataOptions > +const GPT_5_6_LUNA_PRO = { + name: 'gpt-5.6-luna-pro', + context_window: 1_050_000, + max_output_tokens: 128_000, + supports: { + input: ['image', 'text'], + output: ['text'], + endpoints: ['chat', 'chat-completions'], + features: ['streaming', 'function_calling', 'structured_outputs'], + tools: [], + }, + pricing: { + input: { + normal: 0.1, + cached: 0.01, + }, + output: { + normal: 0.6, + }, + }, +} as const satisfies ModelMeta< + OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions +> + +const GPT_5_6_SOL_PRO = { + name: 'gpt-5.6-sol-pro', + context_window: 1_050_000, + max_output_tokens: 128_000, + supports: { + input: ['image', 'text'], + output: ['text'], + endpoints: ['chat', 'chat-completions'], + features: ['streaming', 'function_calling', 'structured_outputs'], + tools: [], + }, + pricing: { + input: { + normal: 5, + cached: 0.5, + }, + output: { + normal: 30, + }, + }, +} as const satisfies ModelMeta< + OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions +> + +const GPT_5_6_TERRA_PRO = { + name: 'gpt-5.6-terra-pro', + context_window: 1_050_000, + max_output_tokens: 128_000, + supports: { + input: ['image', 'text'], + output: ['text'], + endpoints: ['chat', 'chat-completions'], + features: ['streaming', 'function_calling', 'structured_outputs'], + tools: [], + }, + pricing: { + input: { + normal: 1, + cached: 0.1, + }, + output: { + normal: 6, + }, + }, +} as const satisfies ModelMeta< + OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions +> + export const OPENAI_CHAT_MODELS = [ + GPT_5_6_LUNA_PRO.name, + GPT_5_6_SOL_PRO.name, + GPT_5_6_TERRA_PRO.name, // Frontier models GPT5_2.name, GPT5_2_PRO.name, @@ -2780,6 +2870,24 @@ export type OpenAIChatModelProviderOptionsByName = { OpenAIToolsOptions & OpenAIStreamingOptions & OpenAIMetadataOptions + [GPT_5_6_LUNA_PRO.name]: OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions + [GPT_5_6_SOL_PRO.name]: OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions + [GPT_5_6_TERRA_PRO.name]: OpenAIBaseOptions & + OpenAIReasoningOptions & + OpenAIStructuredOutputOptions & + OpenAIToolsOptions & + OpenAIStreamingOptions & + OpenAIMetadataOptions } /** @@ -2901,4 +3009,7 @@ export type OpenAIModelInputModalitiesByName = { [GPT_5_5.name]: typeof GPT_5_5.supports.input [GPT_5_5_PRO.name]: typeof GPT_5_5_PRO.supports.input [GPT_CHAT_LATEST.name]: typeof GPT_CHAT_LATEST.supports.input + [GPT_5_6_LUNA_PRO.name]: typeof GPT_5_6_LUNA_PRO.supports.input + [GPT_5_6_SOL_PRO.name]: typeof GPT_5_6_SOL_PRO.supports.input + [GPT_5_6_TERRA_PRO.name]: typeof GPT_5_6_TERRA_PRO.supports.input } diff --git a/packages/ai-openrouter/src/model-meta.ts b/packages/ai-openrouter/src/model-meta.ts index 1f1c77ddeb..8ebdb87c2c 100644 --- a/packages/ai-openrouter/src/model-meta.ts +++ b/packages/ai-openrouter/src/model-meta.ts @@ -126,6 +126,44 @@ const _ANTHROPIC_CLAUDE_SONNET_LATEST = { image: 0, }, } as const +const _DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST = { + id: '~deepseek/deepseek-v4-flash-latest', + name: 'DeepSeek V4 Flash Latest', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'parallelToolCalls', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 384000, + pricing: { + text: { + input: { + normal: 0.06706, + cached: 0.013412, + }, + output: { + normal: 0.13412, + }, + }, + image: 0, + }, +} as const const _GOOGLE_GEMINI_FLASH_LATEST = { id: '~google/gemini-flash-latest', name: 'Google Gemini Flash Latest', @@ -148,14 +186,14 @@ const _GOOGLE_GEMINI_FLASH_LATEST = { pricing: { text: { input: { - normal: 1.5, - cached: 0.2333333333, + normal: 0.375, + cached: 0.0583333333, }, output: { - normal: 9, + normal: 1.875, }, }, - image: 0.0000015, + image: 3.75e-7, }, } as const const _GOOGLE_GEMINI_PRO_LATEST = { @@ -194,14 +232,13 @@ const _MOONSHOTAI_KIMI_LATEST = { id: '~moonshotai/kimi-latest', name: 'MoonshotAI Kimi Latest', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', - 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -213,16 +250,16 @@ const _MOONSHOTAI_KIMI_LATEST = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 1048576, + max_output_tokens: 1048576, pricing: { text: { input: { - normal: 0.66, - cached: 0.14, + normal: 2.8, + cached: 0.29, }, output: { - normal: 3.41, + normal: 14, }, }, image: 0, @@ -249,7 +286,7 @@ const _OPENAI_GPT_LATEST = { text: { input: { normal: 5, - cached: 0.5, + cached: 6.75, }, output: { normal: 30, @@ -288,6 +325,41 @@ const _OPENAI_GPT_MINI_LATEST = { image: 0, }, } as const +const _X_AI_GROK_LATEST = { + id: '~x-ai/grok-latest', + name: 'xAI: Grok Latest', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 500000, + pricing: { + text: { + input: { + normal: 2, + cached: 0.5, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const const AI21_JAMBA_LARGE_1_7 = { id: 'ai21/jamba-large-1.7', name: 'AI21: Jamba Large 1.7', @@ -608,7 +680,7 @@ const ANTHRACITE_ORG_MAGNUM_V4_72B = { ], }, context_window: 32768, - max_output_tokens: 2048, + max_output_tokens: 4096, pricing: { text: { input: { @@ -681,6 +753,35 @@ const ANTHROPIC_CLAUDE_FABLE_5 = { image: 0, }, } as const +const ANTHROPIC_CLAUDE_FABLE_5_BATCH = { + id: 'anthropic/claude-fable-5:batch', + name: 'Anthropic: Claude Fable 5 (batch)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'toolChoice', + ], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 5, + cached: 6.75, + }, + output: { + normal: 25, + }, + }, + image: 0, + }, +} as const const ANTHROPIC_CLAUDE_HAIKU_4_5 = { id: 'anthropic/claude-haiku-4.5', name: 'Anthropic: Claude Haiku 4.5', @@ -713,6 +814,37 @@ const ANTHROPIC_CLAUDE_HAIKU_4_5 = { image: 0, }, } as const +const ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH = { + id: 'anthropic/claude-haiku-4.5:batch', + name: 'Anthropic: Claude Haiku 4.5 (batch)', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 200000, + max_output_tokens: 64000, + pricing: { + text: { + input: { + normal: 0.5, + cached: 0.675, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const const ANTHROPIC_CLAUDE_OPUS_4 = { id: 'anthropic/claude-opus-4', name: 'Anthropic: Claude Opus 4', @@ -750,10 +882,8 @@ const ANTHROPIC_CLAUDE_OPUS_4_1 = { input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', - 'responseFormat', 'stop', 'temperature', 'toolChoice', @@ -775,6 +905,36 @@ const ANTHROPIC_CLAUDE_OPUS_4_1 = { image: 0, }, } as const +const ANTHROPIC_CLAUDE_OPUS_4_1_BATCH = { + id: 'anthropic/claude-opus-4.1:batch', + name: 'Anthropic: Claude Opus 4.1 (batch)', + supports: { + input: ['image', 'text', 'document'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + ], + }, + context_window: 200000, + max_output_tokens: 32000, + pricing: { + text: { + input: { + normal: 7.5, + cached: 10.125, + }, + output: { + normal: 37.5, + }, + }, + image: 0, + }, +} as const const ANTHROPIC_CLAUDE_OPUS_4_5 = { id: 'anthropic/claude-opus-4.5', name: 'Anthropic: Claude Opus 4.5', @@ -806,41 +966,39 @@ const ANTHROPIC_CLAUDE_OPUS_4_5 = { image: 0, }, } as const -const ANTHROPIC_CLAUDE_OPUS_4_6 = { - id: 'anthropic/claude-opus-4.6', - name: 'Anthropic: Claude Opus 4.6', +const ANTHROPIC_CLAUDE_OPUS_4_5_BATCH = { + id: 'anthropic/claude-opus-4.5:batch', + name: 'Anthropic: Claude Opus 4.5 (batch)', supports: { - input: ['text', 'image', 'document'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'stop', 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 128000, + context_window: 200000, + max_output_tokens: 64000, pricing: { text: { input: { - normal: 5, - cached: 6.75, + normal: 2.5, + cached: 3.375, }, output: { - normal: 25, + normal: 12.5, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_OPUS_4_7 = { - id: 'anthropic/claude-opus-4.7', - name: 'Anthropic: Claude Opus 4.7', +const ANTHROPIC_CLAUDE_OPUS_4_6 = { + id: 'anthropic/claude-opus-4.6', + name: 'Anthropic: Claude Opus 4.6', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -850,7 +1008,9 @@ const ANTHROPIC_CLAUDE_OPUS_4_7 = { 'reasoning', 'responseFormat', 'stop', + 'temperature', 'toolChoice', + 'topP', ], }, context_window: 1000000, @@ -868,9 +1028,9 @@ const ANTHROPIC_CLAUDE_OPUS_4_7 = { image: 0, }, } as const -const ANTHROPIC_CLAUDE_OPUS_4_7_FAST = { - id: 'anthropic/claude-opus-4.7-fast', - name: 'Anthropic: Claude Opus 4.7 (Fast)', +const ANTHROPIC_CLAUDE_OPUS_4_6_BATCH = { + id: 'anthropic/claude-opus-4.6:batch', + name: 'Anthropic: Claude Opus 4.6 (batch)', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -879,7 +1039,9 @@ const ANTHROPIC_CLAUDE_OPUS_4_7_FAST = { 'reasoning', 'responseFormat', 'stop', + 'temperature', 'toolChoice', + 'topP', ], }, context_window: 1000000, @@ -887,19 +1049,19 @@ const ANTHROPIC_CLAUDE_OPUS_4_7_FAST = { pricing: { text: { input: { - normal: 30, - cached: 40.5, + normal: 2.5, + cached: 3.375, }, output: { - normal: 150, + normal: 12.5, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_OPUS_4_8 = { - id: 'anthropic/claude-opus-4.8', - name: 'Anthropic: Claude Opus 4.8', +const ANTHROPIC_CLAUDE_OPUS_4_7 = { + id: 'anthropic/claude-opus-4.7', + name: 'Anthropic: Claude Opus 4.7', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -909,7 +1071,6 @@ const ANTHROPIC_CLAUDE_OPUS_4_8 = { 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', ], }, @@ -928,9 +1089,9 @@ const ANTHROPIC_CLAUDE_OPUS_4_8 = { image: 0, }, } as const -const ANTHROPIC_CLAUDE_OPUS_4_8_FAST = { - id: 'anthropic/claude-opus-4.8-fast', - name: 'Anthropic: Claude Opus 4.8 (Fast)', +const ANTHROPIC_CLAUDE_OPUS_4_7_FAST = { + id: 'anthropic/claude-opus-4.7-fast', + name: 'Anthropic: Claude Opus 4.7 (Fast)', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -947,49 +1108,48 @@ const ANTHROPIC_CLAUDE_OPUS_4_8_FAST = { pricing: { text: { input: { - normal: 10, - cached: 13.5, + normal: 30, + cached: 40.5, }, output: { - normal: 50, + normal: 150, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_SONNET_4 = { - id: 'anthropic/claude-sonnet-4', - name: 'Anthropic: Claude Sonnet 4', +const ANTHROPIC_CLAUDE_OPUS_4_7_BATCH = { + id: 'anthropic/claude-opus-4.7:batch', + name: 'Anthropic: Claude Opus 4.7 (batch)', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', 'reasoning', + 'responseFormat', 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, context_window: 1000000, - max_output_tokens: 64000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 3, - cached: 4.05, + normal: 2.5, + cached: 3.375, }, output: { - normal: 15, + normal: 12.5, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_SONNET_4_5 = { - id: 'anthropic/claude-sonnet-4.5', - name: 'Anthropic: Claude Sonnet 4.5', +const ANTHROPIC_CLAUDE_OPUS_4_8 = { + id: 'anthropic/claude-opus-4.8', + name: 'Anthropic: Claude Opus 4.8', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -1001,39 +1161,35 @@ const ANTHROPIC_CLAUDE_SONNET_4_5 = { 'stop', 'temperature', 'toolChoice', - 'topP', ], }, context_window: 1000000, - max_output_tokens: 64000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 3, - cached: 4.05, + normal: 5, + cached: 6.75, }, output: { - normal: 15, + normal: 25, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_SONNET_4_6 = { - id: 'anthropic/claude-sonnet-4.6', - name: 'Anthropic: Claude Sonnet 4.6', +const ANTHROPIC_CLAUDE_OPUS_4_8_FAST = { + id: 'anthropic/claude-opus-4.8-fast', + name: 'Anthropic: Claude Opus 4.8 (Fast)', supports: { input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, context_window: 1000000, @@ -1041,24 +1197,23 @@ const ANTHROPIC_CLAUDE_SONNET_4_6 = { pricing: { text: { input: { - normal: 3, - cached: 4.05, + normal: 10, + cached: 13.5, }, output: { - normal: 15, + normal: 50, }, }, image: 0, }, } as const -const ANTHROPIC_CLAUDE_SONNET_5 = { - id: 'anthropic/claude-sonnet-5', - name: 'Anthropic: Claude Sonnet 5', +const ANTHROPIC_CLAUDE_OPUS_4_8_BATCH = { + id: 'anthropic/claude-opus-4.8:batch', + name: 'Anthropic: Claude Opus 4.8 (batch)', supports: { input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -1071,181 +1226,174 @@ const ANTHROPIC_CLAUDE_SONNET_5 = { pricing: { text: { input: { - normal: 2, - cached: 2.7, + normal: 2.5, + cached: 3.375, }, output: { - normal: 10, + normal: 12.5, }, }, image: 0, }, } as const -const ARCEE_AI_CODER_LARGE = { - id: 'arcee-ai/coder-large', - name: 'Arcee AI: Coder Large', +const ANTHROPIC_CLAUDE_OPUS_5 = { + id: 'anthropic/claude-opus-5', + name: 'Claude Opus 5', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', 'stop', 'temperature', - 'topP', + 'toolChoice', ], }, - context_window: 32768, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.5, - cached: 0, + normal: 5, + cached: 6.75, }, output: { - normal: 0.8, + normal: 25, }, }, image: 0, }, } as const -const ARCEE_AI_TRINITY_LARGE_THINKING = { - id: 'arcee-ai/trinity-large-thinking', - name: 'Arcee AI: Trinity Large Thinking', +const ANTHROPIC_CLAUDE_OPUS_5_FAST = { + id: 'anthropic/claude-opus-5-fast', + name: 'Claude Opus 5 (Fast)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', 'reasoning', - 'temperature', + 'responseFormat', + 'stop', 'toolChoice', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 80000, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.25, - cached: 0.06, + normal: 10, + cached: 13.5, }, output: { - normal: 0.8, + normal: 50, }, }, image: 0, }, } as const -const ARCEE_AI_TRINITY_MINI = { - id: 'arcee-ai/trinity-mini', - name: 'Arcee AI: Trinity Mini', +const ANTHROPIC_CLAUDE_OPUS_5_BATCH = { + id: 'anthropic/claude-opus-5:batch', + name: 'Claude Opus 5 (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'logprobs', - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.045, - cached: 0, + normal: 2.5, + cached: 3.375, }, output: { - normal: 0.15, + normal: 12.5, }, }, image: 0, }, } as const -const ARCEE_AI_VIRTUOSO_LARGE = { - id: 'arcee-ai/virtuoso-large', - name: 'Arcee AI: Virtuoso Large', +const ANTHROPIC_CLAUDE_SONNET_4 = { + id: 'anthropic/claude-sonnet-4', + name: 'Anthropic: Claude Sonnet 4', supports: { - input: ['text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 131072, + context_window: 1000000, max_output_tokens: 64000, pricing: { text: { input: { - normal: 0.75, - cached: 0, + normal: 3, + cached: 4.05, }, output: { - normal: 1.2, + normal: 15, }, }, image: 0, }, } as const -const BAIDU_ERNIE_4_5_VL_424B_A47B = { - id: 'baidu/ernie-4.5-vl-424b-a47b', - name: 'Baidu: ERNIE 4.5 VL 424B A47B ', +const ANTHROPIC_CLAUDE_SONNET_4_5 = { + id: 'anthropic/claude-sonnet-4.5', + name: 'Anthropic: Claude Sonnet 4.5', supports: { - input: ['image', 'text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', - 'seed', + 'responseFormat', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16000, + context_window: 1000000, + max_output_tokens: 64000, pricing: { text: { input: { - normal: 0.42, - cached: 0, + normal: 3, + cached: 4.05, }, output: { - normal: 1.25, + normal: 15, }, }, image: 0, }, } as const -const BYTEDANCE_SEED_SEED_1_6 = { - id: 'bytedance-seed/seed-1.6', - name: 'ByteDance Seed: Seed 1.6', +const ANTHROPIC_CLAUDE_SONNET_4_5_BATCH = { + id: 'anthropic/claude-sonnet-4.5:batch', + name: 'Anthropic: Claude Sonnet 4.5 (batch)', supports: { - input: ['image', 'text', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -1255,29 +1403,29 @@ const BYTEDANCE_SEED_SEED_1_6 = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1000000, + max_output_tokens: 64000, pricing: { text: { input: { - normal: 0.25, - cached: 0, + normal: 1.5, + cached: 2.025, }, output: { - normal: 2, + normal: 7.5, }, }, image: 0, }, } as const -const BYTEDANCE_SEED_SEED_1_6_FLASH = { - id: 'bytedance-seed/seed-1.6-flash', - name: 'ByteDance Seed: Seed 1.6 Flash', +const ANTHROPIC_CLAUDE_SONNET_4_6 = { + id: 'anthropic/claude-sonnet-4.6', + name: 'Anthropic: Claude Sonnet 4.6', supports: { - input: ['image', 'text', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', + 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -1287,29 +1435,28 @@ const BYTEDANCE_SEED_SEED_1_6_FLASH = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.075, - cached: 0, + normal: 3, + cached: 4.05, }, output: { - normal: 0.3, + normal: 15, }, }, image: 0, }, } as const -const BYTEDANCE_SEED_SEED_2_0_LITE = { - id: 'bytedance-seed/seed-2.0-lite', - name: 'ByteDance Seed: Seed-2.0-Lite', +const ANTHROPIC_CLAUDE_SONNET_4_6_BATCH = { + id: 'anthropic/claude-sonnet-4.6:batch', + name: 'Anthropic: Claude Sonnet 4.6 (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -1319,385 +1466,378 @@ const BYTEDANCE_SEED_SEED_2_0_LITE = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 131072, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.25, - cached: 0, + normal: 1.5, + cached: 2.025, }, output: { - normal: 2, + normal: 7.5, }, }, image: 0, }, } as const -const BYTEDANCE_SEED_SEED_2_0_MINI = { - id: 'bytedance-seed/seed-2.0-mini', - name: 'ByteDance Seed: Seed-2.0-Mini', +const ANTHROPIC_CLAUDE_SONNET_5 = { + id: 'anthropic/claude-sonnet-5', + name: 'Anthropic: Claude Sonnet 5', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', + 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 131072, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.1, - cached: 0, + normal: 2, + cached: 2.7, }, output: { - normal: 0.4, + normal: 10, }, }, image: 0, }, } as const -const BYTEDANCE_UI_TARS_1_5_7B = { - id: 'bytedance/ui-tars-1.5-7b', - name: 'ByteDance: UI-TARS 7B ', +const ANTHROPIC_CLAUDE_SONNET_5_BATCH = { + id: 'anthropic/claude-sonnet-5:batch', + name: 'Anthropic: Claude Sonnet 5 (batch)', supports: { - input: ['image', 'text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', - 'seed', + 'reasoning', + 'responseFormat', 'stop', - 'temperature', - 'topLogprobs', - 'topP', + 'toolChoice', ], }, - context_window: 128000, - max_output_tokens: 2048, + context_window: 1000000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.1, - cached: 0.1, + normal: 1, + cached: 1.35, }, output: { - normal: 0.2, + normal: 5, }, }, image: 0, }, } as const -const COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE = { - id: 'cognitivecomputations/dolphin-mistral-24b-venice-edition:free', - name: 'Venice: Uncensored (free)', +const ARCEE_AI_TRINITY_LARGE_THINKING = { + id: 'arcee-ai/trinity-large-thinking', + name: 'Arcee AI: Trinity Large Thinking', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', + 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 32768, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.22, + cached: 0.06, }, output: { - normal: 0, + normal: 0.85, }, }, image: 0, }, } as const -const COHERE_COMMAND_A = { - id: 'cohere/command-a', - name: 'Cohere: Command A', +const ARCEE_AI_VIRTUOSO_LARGE = { + id: 'arcee-ai/virtuoso-large', + name: 'Arcee AI: Virtuoso Large', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', - 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 256000, - max_output_tokens: 8192, + context_window: 131072, + max_output_tokens: 64000, pricing: { text: { input: { - normal: 2.5, + normal: 0.75, cached: 0, }, output: { - normal: 10, + normal: 1.2, }, }, image: 0, }, } as const -const COHERE_COMMAND_R_08_2024 = { - id: 'cohere/command-r-08-2024', - name: 'Cohere: Command R (08-2024)', +const BAIDU_ERNIE_4_5_VL_424B_A47B = { + id: 'baidu/ernie-4.5-vl-424b-a47b', + name: 'Baidu: ERNIE 4.5 VL 424B A47B ', supports: { - input: ['text'], + input: ['image', 'text'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', + 'reasoning', 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 128000, - max_output_tokens: 4000, + context_window: 123000, + max_output_tokens: 16000, pricing: { text: { input: { - normal: 0.15, + normal: 0.42, cached: 0, }, output: { - normal: 0.6, + normal: 1.25, }, }, image: 0, }, } as const -const COHERE_COMMAND_R_PLUS_08_2024 = { - id: 'cohere/command-r-plus-08-2024', - name: 'Cohere: Command R+ (08-2024)', +const BYTEDANCE_SEED_SEED_1_6 = { + id: 'bytedance-seed/seed-1.6', + name: 'ByteDance Seed: Seed 1.6', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 128000, - max_output_tokens: 4000, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 2.5, + normal: 0.25, cached: 0, }, output: { - normal: 10, + normal: 2, }, }, image: 0, }, } as const -const COHERE_COMMAND_R7B_12_2024 = { - id: 'cohere/command-r7b-12-2024', - name: 'Cohere: Command R7B (12-2024)', +const BYTEDANCE_SEED_SEED_1_6_FLASH = { + id: 'bytedance-seed/seed-1.6-flash', + name: 'ByteDance Seed: Seed 1.6 Flash', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 128000, - max_output_tokens: 4000, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.0375, + normal: 0.075, cached: 0, }, output: { - normal: 0.15, + normal: 0.3, }, }, image: 0, }, } as const -const COHERE_NORTH_MINI_CODE_FREE = { - id: 'cohere/north-mini-code:free', - name: 'Cohere: North Mini Code (free)', +const BYTEDANCE_SEED_SEED_2_1_TURBO = { + id: 'bytedance-seed/seed-2-1-turbo', + name: 'ByteDance Seed: Seed 2.1 Turbo', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'seed', + 'responseFormat', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 256000, - max_output_tokens: 64000, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0, + normal: 0.5, cached: 0, }, output: { - normal: 0, + normal: 2.5, }, }, image: 0, }, } as const -const DEEPCOGITO_COGITO_V2_1_671B = { - id: 'deepcogito/cogito-v2.1-671b', - name: 'Deep Cogito: Cogito v2.1 671B', +const BYTEDANCE_SEED_SEED_2_0_CODE = { + id: 'bytedance-seed/seed-2.0-code', + name: 'ByteDance Seed: Seed-2.0-Code', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 128000, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 1.25, + normal: 0.5, cached: 0, }, output: { - normal: 1.25, + normal: 3, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_CHAT = { - id: 'deepseek/deepseek-chat', - name: 'DeepSeek: DeepSeek V3', +const BYTEDANCE_SEED_SEED_2_0_LITE = { + id: 'bytedance-seed/seed-2.0-lite', + name: 'ByteDance Seed: Seed-2.0-Lite', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16000, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.2002, + normal: 0.25, cached: 0, }, output: { - normal: 0.8001, + normal: 2, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_CHAT_V3_0324 = { - id: 'deepseek/deepseek-chat-v3-0324', - name: 'DeepSeek: DeepSeek V3 0324', +const BYTEDANCE_SEED_SEED_2_0_MINI = { + id: 'bytedance-seed/seed-2.0-mini', + name: 'ByteDance Seed: Seed-2.0-Mini', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 163840, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.24, - cached: 0.135, + normal: 0.1, + cached: 0, }, output: { - normal: 0.9, + normal: 0.4, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_CHAT_V3_1 = { - id: 'deepseek/deepseek-chat-v3.1', - name: 'DeepSeek: DeepSeek V3.1', +const BYTEDANCE_UI_TARS_1_5_7B = { + id: 'bytedance/ui-tars-1.5-7b', + name: 'ByteDance: UI-TARS 7B ', supports: { - input: ['text'], + input: ['image', 'text'], output: ['text'], supports: [ 'frequencyPenalty', @@ -1705,106 +1845,94 @@ const DEEPSEEK_DEEPSEEK_CHAT_V3_1 = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', - 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 163840, - max_output_tokens: 32768, + context_window: 128000, + max_output_tokens: 2048, pricing: { text: { input: { - normal: 0.21, - cached: 0.13, + normal: 0.1, + cached: 0.1, }, output: { - normal: 0.79, + normal: 0.2, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_R1 = { - id: 'deepseek/deepseek-r1', - name: 'DeepSeek: R1', +const COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION = { + id: 'cognitivecomputations/dolphin-mistral-24b-venice-edition', + name: 'Venice: Uncensored', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', - 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 163840, - max_output_tokens: 16000, + context_window: 128000, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.7, + normal: 0.2, cached: 0, }, output: { - normal: 2.5, + normal: 0.9, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_R1_0528 = { - id: 'deepseek/deepseek-r1-0528', - name: 'DeepSeek: R1 0528', +const COHERE_COMMAND_A = { + id: 'cohere/command-a', + name: 'Cohere: Command A', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 163840, - max_output_tokens: 32768, + context_window: 256000, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.5, - cached: 0.35, + normal: 2.5, + cached: 0, }, output: { - normal: 2.15, + normal: 10, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B = { - id: 'deepseek/deepseek-r1-distill-llama-70b', - name: 'DeepSeek: R1 Distill Llama 70B', +const COHERE_COMMAND_R_08_2024 = { + id: 'cohere/command-r-08-2024', + name: 'Cohere: Command R (08-2024)', supports: { input: ['text'], output: ['text'], @@ -1812,40 +1940,39 @@ const DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B = { 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, context_window: 128000, - max_output_tokens: 8192, + max_output_tokens: 4000, pricing: { text: { input: { - normal: 0.8, + normal: 0.15, cached: 0, }, output: { - normal: 0.8, + normal: 0.6, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V3_1_TERMINUS = { - id: 'deepseek/deepseek-v3.1-terminus', - name: 'DeepSeek: DeepSeek V3.1 Terminus', +const COHERE_COMMAND_R_PLUS_08_2024 = { + id: 'cohere/command-r-plus-08-2024', + name: 'Cohere: Command R+ (08-2024)', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -1854,178 +1981,163 @@ const DEEPSEEK_DEEPSEEK_V3_1_TERMINUS = { 'topP', ], }, - context_window: 163840, - max_output_tokens: 32768, + context_window: 128000, + max_output_tokens: 4000, pricing: { text: { input: { - normal: 0.27, - cached: 0.13, + normal: 2.5, + cached: 0, }, output: { - normal: 0.95, + normal: 10, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V3_2 = { - id: 'deepseek/deepseek-v3.2', - name: 'DeepSeek: DeepSeek V3.2', +const COHERE_COMMAND_R7B_12_2024 = { + id: 'cohere/command-r7b-12-2024', + name: 'Cohere: Command R7B (12-2024)', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 64000, + context_window: 128000, + max_output_tokens: 4000, pricing: { text: { input: { - normal: 0.2288, - cached: 0.02288, + normal: 0.0375, + cached: 0, }, output: { - normal: 0.3432, + normal: 0.15, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V3_2_EXP = { - id: 'deepseek/deepseek-v3.2-exp', - name: 'DeepSeek: DeepSeek V3.2 Exp', +const COHERE_NORTH_MINI_CODE_FREE = { + id: 'cohere/north-mini-code:free', + name: 'Cohere: North Mini Code (free)', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', - 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 163840, - max_output_tokens: 65536, + context_window: 256000, + max_output_tokens: 64000, pricing: { text: { input: { - normal: 0.27, + normal: 0, cached: 0, }, output: { - normal: 0.41, + normal: 0, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V4_FLASH = { - id: 'deepseek/deepseek-v4-flash', - name: 'DeepSeek: DeepSeek V4 Flash', +const DEEPCOGITO_COGITO_V2_1_671B = { + id: 'deepcogito/cogito-v2.1-671b', + name: 'Deep Cogito: Cogito v2.1 671B', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65536, + context_window: 128000, pricing: { text: { input: { - normal: 0.09, - cached: 0.018, + normal: 1.25, + cached: 0, }, output: { - normal: 0.18, + normal: 1.25, }, }, image: 0, }, } as const -const DEEPSEEK_DEEPSEEK_V4_PRO = { - id: 'deepseek/deepseek-v4-pro', - name: 'DeepSeek: DeepSeek V4 Pro', +const DEEPSEEK_DEEPSEEK_CHAT = { + id: 'deepseek/deepseek-chat', + name: 'DeepSeek: DeepSeek V3', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 384000, + context_window: 163840, + max_output_tokens: 16000, pricing: { text: { input: { - normal: 0.435, - cached: 0.003625, + normal: 0.2574, + cached: 0, }, output: { - normal: 0.87, + normal: 1.0287, }, }, image: 0, }, } as const -const GOOGLE_GEMINI_2_5_FLASH = { - id: 'google/gemini-2.5-flash', - name: 'Google: Gemini 2.5 Flash', +const DEEPSEEK_DEEPSEEK_CHAT_V3_0324 = { + id: 'deepseek/deepseek-chat-v3-0324', + name: 'DeepSeek: DeepSeek V3 0324', supports: { - input: ['document', 'image', 'text', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', 'stop', @@ -2034,59 +2146,68 @@ const GOOGLE_GEMINI_2_5_FLASH = { 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65535, + context_window: 163840, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.3, - cached: 0.1133333333, + normal: 0.27, + cached: 0.135, }, output: { - normal: 2.5, + normal: 1.12, }, }, - image: 3e-7, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_FLASH_IMAGE = { - id: 'google/gemini-2.5-flash-image', - name: 'Google: Nano Banana (Gemini 2.5 Flash Image)', +const DEEPSEEK_DEEPSEEK_CHAT_V3_1 = { + id: 'deepseek/deepseek-chat-v3.1', + name: 'DeepSeek: DeepSeek V3.1', supports: { - input: ['image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 32768, + context_window: 163840, max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.3, - cached: 0.1133333333, + normal: 0.25, + cached: 0.13, }, output: { - normal: 2.5, + normal: 0.95, }, }, - image: 3e-7, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_FLASH_LITE = { - id: 'google/gemini-2.5-flash-lite', - name: 'Google: Gemini 2.5 Flash Lite', +const DEEPSEEK_DEEPSEEK_R1 = { + id: 'deepseek/deepseek-r1', + name: 'DeepSeek: R1', supports: { - input: ['text', 'image', 'document', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', @@ -2096,93 +2217,101 @@ const GOOGLE_GEMINI_2_5_FLASH_LITE = { 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65535, + context_window: 64000, + max_output_tokens: 16000, pricing: { text: { input: { - normal: 0.1, - cached: 0.0933333333, + normal: 0.7, + cached: 0, }, output: { - normal: 0.4, + normal: 2.5, }, }, - image: 1e-7, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_09_2025 = { - id: 'google/gemini-2.5-flash-lite-preview-09-2025', - name: 'Google: Gemini 2.5 Flash Lite Preview 09-2025', +const DEEPSEEK_DEEPSEEK_R1_0528 = { + id: 'deepseek/deepseek-r1-0528', + name: 'DeepSeek: R1 0528', supports: { - input: ['text', 'image', 'document', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65535, + context_window: 163840, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.1, - cached: 0.0933333333, + normal: 0.5, + cached: 0.35, }, output: { - normal: 0.4, + normal: 2.15, }, }, - image: 1e-7, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_PRO = { - id: 'google/gemini-2.5-pro', - name: 'Google: Gemini 2.5 Pro', +const DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B = { + id: 'deepseek/deepseek-r1-distill-llama-70b', + name: 'DeepSeek: R1 Distill Llama 70B', supports: { - input: ['text', 'image', 'document', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', - 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65536, + context_window: 8192, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 1.25, - cached: 0.5, + normal: 0.8, + cached: 0, }, output: { - normal: 10, + normal: 0.8, }, }, - image: 0.00000125, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_PRO_PREVIEW = { - id: 'google/gemini-2.5-pro-preview', - name: 'Google: Gemini 2.5 Pro Preview 06-05', +const DEEPSEEK_DEEPSEEK_V3_1_TERMINUS = { + id: 'deepseek/deepseek-v3.1-terminus', + name: 'DeepSeek: DeepSeek V3.1 Terminus', supports: { - input: ['document', 'image', 'text', 'audio'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', @@ -2192,213 +2321,281 @@ const GOOGLE_GEMINI_2_5_PRO_PREVIEW = { 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65536, + context_window: 163840, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 1.25, - cached: 0.5, + normal: 0.27, + cached: 0.13, }, output: { - normal: 10, + normal: 0.95, }, }, - image: 0.00000125, + image: 0, }, } as const -const GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06 = { - id: 'google/gemini-2.5-pro-preview-05-06', - name: 'Google: Gemini 2.5 Pro Preview 05-06', +const DEEPSEEK_DEEPSEEK_V3_2 = { + id: 'deepseek/deepseek-v3.2', + name: 'DeepSeek: DeepSeek V3.2', supports: { - input: ['text', 'image', 'document', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65535, + context_window: 163840, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 1.25, - cached: 0.5, + normal: 0.269, + cached: 0.1345, }, output: { - normal: 10, + normal: 0.4, }, }, - image: 0.00000125, + image: 0, }, } as const -const GOOGLE_GEMINI_3_FLASH_PREVIEW = { - id: 'google/gemini-3-flash-preview', - name: 'Google: Gemini 3 Flash Preview', +const DEEPSEEK_DEEPSEEK_V3_2_EXP = { + id: 'deepseek/deepseek-v3.2-exp', + name: 'DeepSeek: DeepSeek V3.2 Exp', supports: { - input: ['text', 'image', 'document', 'audio', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65535, + context_window: 163840, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.5, - cached: 0.13333333330000002, + normal: 0.27, + cached: 0, }, output: { - normal: 3, + normal: 0.41, }, }, - image: 5e-7, + image: 0, }, } as const -const GOOGLE_GEMINI_3_PRO_IMAGE = { - id: 'google/gemini-3-pro-image', - name: 'Google: Nano Banana Pro (Gemini 3 Pro Image)', +const DEEPSEEK_DEEPSEEK_V4_FLASH = { + id: 'deepseek/deepseek-v4-flash', + name: 'DeepSeek: DeepSeek V4 Flash 0423', supports: { - input: ['image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 384000, pricing: { text: { input: { - normal: 2, - cached: 0.575, + normal: 0.06146, + cached: 0.012292, }, output: { - normal: 12, + normal: 0.12292, }, }, - image: 0.000002, + image: 0, }, } as const -const GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW = { - id: 'google/gemini-3-pro-image-preview', - name: 'Google: Nano Banana Pro (Gemini 3 Pro Image Preview)', +const DEEPSEEK_DEEPSEEK_V4_FLASH_0731 = { + id: 'deepseek/deepseek-v4-flash-0731', + name: 'DeepSeek: DeepSeek V4 Flash 0731', supports: { - input: ['image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'parallelToolCalls', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 393216, pricing: { text: { input: { - normal: 2, - cached: 0.575, + normal: 0.14, + cached: 0.028, }, output: { - normal: 12, + normal: 0.28, }, }, - image: 0.000002, + image: 0, }, } as const -const GOOGLE_GEMINI_3_1_FLASH_IMAGE = { - id: 'google/gemini-3.1-flash-image', - name: 'Google: Nano Banana 2 (Gemini 3.1 Flash Image)', +const DEEPSEEK_DEEPSEEK_V4_PRO = { + id: 'deepseek/deepseek-v4-pro', + name: 'DeepSeek: DeepSeek V4 Pro', supports: { - input: ['image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 393216, pricing: { text: { input: { - normal: 0.5, - cached: 0, + normal: 1.168, + cached: 0.09855, }, output: { - normal: 3, + normal: 2.336, }, }, image: 0, }, } as const -const GOOGLE_GEMINI_3_1_FLASH_IMAGE_PREVIEW = { - id: 'google/gemini-3.1-flash-image-preview', - name: 'Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)', +const DEEPSEEK_DEEPSEEK_V4_PRO_0813 = { + id: 'deepseek/deepseek-v4-pro-0813', + name: 'DeepSeek: DeepSeek V4 Pro 0813', supports: { - input: ['image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 384000, pricing: { text: { input: { - normal: 0.5, + normal: 0.435, + cached: 0.003625, + }, + output: { + normal: 0.87, + }, + }, + image: 0, + }, +} as const +const DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE = { + id: 'dots-studio/dots-3-note-preview:free', + name: 'Dots Studio: Dots3-Note Preview (free)', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 512000, + max_output_tokens: 512000, + pricing: { + text: { + input: { + normal: 0, cached: 0, }, output: { - normal: 3, + normal: 0, }, }, image: 0, }, } as const -const GOOGLE_GEMINI_3_1_FLASH_LITE = { - id: 'google/gemini-3.1-flash-lite', - name: 'Google: Gemini 3.1 Flash Lite', +const GOOGLE_GEMINI_2_5_FLASH = { + id: 'google/gemini-2.5-flash', + name: 'Google: Gemini 2.5 Flash', supports: { - input: ['text', 'image', 'video', 'document', 'audio'], + input: ['document', 'image', 'text', 'audio', 'video'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -2412,55 +2609,55 @@ const GOOGLE_GEMINI_3_1_FLASH_LITE = { ], }, context_window: 1048576, - max_output_tokens: 65536, + max_output_tokens: 65535, pricing: { text: { input: { - normal: 0.25, - cached: 0.1083333333, + normal: 0.3, + cached: 0.1133333333, }, output: { - normal: 1.5, + normal: 2.5, }, }, - image: 2.5e-7, + image: 3e-7, }, } as const -const GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE = { - id: 'google/gemini-3.1-flash-lite-image', - name: 'Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)', +const GOOGLE_GEMINI_2_5_FLASH_IMAGE = { + id: 'google/gemini-2.5-flash-image', + name: 'Google: Nano Banana (Gemini 2.5 Flash Image)', supports: { input: ['image', 'text'], output: ['image', 'text'], supports: [ 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'topP', ], }, - context_window: 65536, - max_output_tokens: 66000, + context_window: 32768, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.25, - cached: 0, + normal: 0.3, + cached: 0.1133333333, }, output: { - normal: 1.5, + normal: 2.5, }, }, - image: 0, + image: 3e-7, }, } as const -const GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW = { - id: 'google/gemini-3.1-flash-lite-preview', - name: 'Google: Gemini 3.1 Flash Lite Preview', +const GOOGLE_GEMINI_2_5_FLASH_LITE = { + id: 'google/gemini-2.5-flash-lite', + name: 'Google: Gemini 2.5 Flash Lite', supports: { - input: ['text', 'image', 'video', 'document', 'audio'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -2474,25 +2671,25 @@ const GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW = { ], }, context_window: 1048576, - max_output_tokens: 65536, + max_output_tokens: 65535, pricing: { text: { input: { - normal: 0.25, - cached: 0.1083333333, + normal: 0.1, + cached: 0.0933333333, }, output: { - normal: 1.5, + normal: 0.4, }, }, - image: 2.5e-7, + image: 1e-7, }, } as const -const GOOGLE_GEMINI_3_1_PRO_PREVIEW = { - id: 'google/gemini-3.1-pro-preview', - name: 'Google: Gemini 3.1 Pro Preview', +const GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH = { + id: 'google/gemini-2.5-flash-lite:batch', + name: 'Google: Gemini 2.5 Flash Lite (batch)', supports: { - input: ['audio', 'document', 'image', 'text', 'video'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -2506,56 +2703,57 @@ const GOOGLE_GEMINI_3_1_PRO_PREVIEW = { ], }, context_window: 1048576, - max_output_tokens: 65536, + max_output_tokens: 65535, pricing: { text: { input: { - normal: 2, - cached: 0.575, + normal: 0.05, + cached: 0.01, }, output: { - normal: 12, + normal: 0.2, }, }, - image: 0.000002, + image: 5e-8, }, } as const -const GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS = { - id: 'google/gemini-3.1-pro-preview-customtools', - name: 'Google: Gemini 3.1 Pro Preview Custom Tools', +const GOOGLE_GEMINI_2_5_FLASH_BATCH = { + id: 'google/gemini-2.5-flash:batch', + name: 'Google: Gemini 2.5 Flash (batch)', supports: { - input: ['text', 'audio', 'image', 'video', 'document'], + input: ['document', 'image', 'text', 'audio', 'video'], output: ['text'], supports: [ 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 1048756, - max_output_tokens: 65536, + context_window: 1048576, + max_output_tokens: 65535, pricing: { text: { input: { - normal: 2, - cached: 0.575, + normal: 0.15, + cached: 0.03, }, output: { - normal: 12, + normal: 1.25, }, }, - image: 0.000002, + image: 1.5e-7, }, } as const -const GOOGLE_GEMINI_3_5_FLASH = { - id: 'google/gemini-3.5-flash', - name: 'Google: Gemini 3.5 Flash', +const GOOGLE_GEMINI_2_5_PRO = { + id: 'google/gemini-2.5-pro', + name: 'Google: Gemini 2.5 Pro', supports: { - input: ['text', 'image', 'video', 'document', 'audio'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -2573,59 +2771,57 @@ const GOOGLE_GEMINI_3_5_FLASH = { pricing: { text: { input: { - normal: 1.5, - cached: 0.2333333333, + normal: 1.25, + cached: 0.5, }, output: { - normal: 9, + normal: 10, }, }, - image: 0.0000015, + image: 0.00000125, }, } as const -const GOOGLE_GEMMA_2_27B_IT = { - id: 'google/gemma-2-27b-it', - name: 'Google: Gemma 2 27B', +const GOOGLE_GEMINI_2_5_PRO_PREVIEW = { + id: 'google/gemini-2.5-pro-preview', + name: 'Google: Gemini 2.5 Pro Preview 06-05', supports: { - input: ['text'], + input: ['document', 'image', 'text', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 8192, - max_output_tokens: 2048, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.65, - cached: 0, + normal: 1.25, + cached: 0.5, }, output: { - normal: 0.65, + normal: 10, }, }, - image: 0, + image: 0.00000125, }, } as const -const GOOGLE_GEMMA_3_12B_IT = { - id: 'google/gemma-3-12b-it', - name: 'Google: Gemma 3 12B', +const GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06 = { + id: 'google/gemini-2.5-pro-preview-05-06', + name: 'Google: Gemini 2.5 Pro Preview 05-06', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -2634,273 +2830,254 @@ const GOOGLE_GEMMA_3_12B_IT = { 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1048576, + max_output_tokens: 65535, pricing: { text: { input: { - normal: 0.05, - cached: 0, + normal: 1.25, + cached: 0.5, }, output: { - normal: 0.15, + normal: 10, }, }, - image: 0, + image: 0.00000125, }, } as const -const GOOGLE_GEMMA_3_27B_IT = { - id: 'google/gemma-3-27b-it', - name: 'Google: Gemma 3 27B', +const GOOGLE_GEMINI_2_5_PRO_BATCH = { + id: 'google/gemini-2.5-pro:batch', + name: 'Google: Gemini 2.5 Pro (batch)', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.08, - cached: 0, + normal: 0.625, + cached: 0.125, }, output: { - normal: 0.16, + normal: 5, }, }, - image: 0, + image: 6.25e-7, }, } as const -const GOOGLE_GEMMA_3_4B_IT = { - id: 'google/gemma-3-4b-it', - name: 'Google: Gemma 3 4B', +const GOOGLE_GEMINI_3_FLASH_PREVIEW = { + id: 'google/gemini-3-flash-preview', + name: 'Google: Gemini 3 Flash Preview', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.05, - cached: 0, + normal: 0.5, + cached: 0.13333333330000002, }, output: { - normal: 0.1, + normal: 3, }, }, - image: 0, + image: 5e-7, }, } as const -const GOOGLE_GEMMA_3N_E4B_IT = { - id: 'google/gemma-3n-e4b-it', - name: 'Google: Gemma 3n 4B', +const GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH = { + id: 'google/gemini-3-flash-preview:batch', + name: 'Google: Gemini 3 Flash Preview (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document', 'audio', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', + 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 32768, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.06, + normal: 0.25, cached: 0, }, output: { - normal: 0.12, + normal: 1.5, }, }, - image: 0, + image: 2.5e-7, }, } as const -const GOOGLE_GEMMA_4_26B_A4B_IT = { - id: 'google/gemma-4-26b-a4b-it', - name: 'Google: Gemma 4 26B A4B ', +const GOOGLE_GEMINI_3_PRO_IMAGE = { + id: 'google/gemini-3-pro-image', + name: 'Google: Nano Banana Pro (Gemini 3 Pro Image)', supports: { - input: ['image', 'text', 'video'], - output: ['text'], + input: ['image', 'text'], + output: ['image', 'text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 131072, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.06, - cached: 0, + normal: 2, + cached: 0.575, }, output: { - normal: 0.33, + normal: 12, }, }, - image: 0, + image: 0.000002, }, } as const -const GOOGLE_GEMMA_4_26B_A4B_IT_FREE = { - id: 'google/gemma-4-26b-a4b-it:free', - name: 'Google: Gemma 4 26B A4B (free)', +const GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW = { + id: 'google/gemini-3-pro-image-preview', + name: 'Google: Nano Banana Pro (Gemini 3 Pro Image Preview)', supports: { - input: ['image', 'text', 'video'], - output: ['text'], + input: ['image', 'text'], + output: ['image', 'text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 65536, max_output_tokens: 32768, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 2, + cached: 0.575, }, output: { - normal: 0, + normal: 12, }, }, - image: 0, + image: 0.000002, }, } as const -const GOOGLE_GEMMA_4_31B_IT = { - id: 'google/gemma-4-31b-it', - name: 'Google: Gemma 4 31B', +const GOOGLE_GEMINI_3_1_FLASH_IMAGE = { + id: 'google/gemini-3.1-flash-image', + name: 'Google: Nano Banana 2 (Gemini 3.1 Flash Image)', supports: { - input: ['image', 'text', 'video'], - output: ['text'], + input: ['image', 'text'], + output: ['image', 'text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 131072, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.12, - cached: 0.09, + normal: 0.5, + cached: 0, }, output: { - normal: 0.35, + normal: 3, }, }, image: 0, }, } as const -const GOOGLE_GEMMA_4_31B_IT_FREE = { - id: 'google/gemma-4-31b-it:free', - name: 'Google: Gemma 4 31B (free)', +const GOOGLE_GEMINI_3_1_FLASH_IMAGE_PREVIEW = { + id: 'google/gemini-3.1-flash-image-preview', + name: 'Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)', supports: { - input: ['image', 'text', 'video'], - output: ['text'], + input: ['image', 'text'], + output: ['image', 'text'], supports: [ 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 262144, - max_output_tokens: 8192, + context_window: 65536, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0, + normal: 0.5, cached: 0, }, output: { - normal: 0, + normal: 3, }, }, image: 0, }, } as const -const GOOGLE_LYRIA_3_CLIP_PREVIEW = { - id: 'google/lyria-3-clip-preview', - name: 'Google: Lyria 3 Clip Preview', +const GOOGLE_GEMINI_3_1_FLASH_LITE = { + id: 'google/gemini-3.1-flash-lite', + name: 'Google: Gemini 3.1 Flash Lite', supports: { - input: ['text', 'image'], - output: ['text', 'audio'], + input: ['text', 'image', 'video', 'document', 'audio'], + output: ['text'], supports: [ 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', + 'toolChoice', 'topP', ], }, @@ -2909,260 +3086,244 @@ const GOOGLE_LYRIA_3_CLIP_PREVIEW = { pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.25, + cached: 0.1083333333, }, output: { - normal: 0, + normal: 1.5, }, }, - image: 0, + image: 2.5e-7, }, } as const -const GOOGLE_LYRIA_3_PRO_PREVIEW = { - id: 'google/lyria-3-pro-preview', - name: 'Google: Lyria 3 Pro Preview', +const GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE = { + id: 'google/gemini-3.1-flash-lite-image', + name: 'Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)', supports: { - input: ['text', 'image'], - output: ['text', 'audio'], + input: ['image', 'text'], + output: ['image', 'text'], supports: [ 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', 'temperature', 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65536, + context_window: 65536, + max_output_tokens: 66000, pricing: { text: { input: { - normal: 0, + normal: 0.25, cached: 0, }, output: { - normal: 0, + normal: 1.5, }, }, image: 0, }, } as const -const GRYPHE_MYTHOMAX_L2_13B = { - id: 'gryphe/mythomax-l2-13b', - name: 'MythoMax 13B', +const GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW = { + id: 'google/gemini-3.1-flash-lite-preview', + name: 'Google: Gemini 3.1 Flash Lite Preview', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 4096, - max_output_tokens: 4096, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.06, - cached: 0, + normal: 0.25, + cached: 0.1083333333, }, output: { - normal: 0.06, + normal: 1.5, }, }, - image: 0, + image: 2.5e-7, }, } as const -const IBM_GRANITE_GRANITE_4_0_H_MICRO = { - id: 'ibm-granite/granite-4.0-h-micro', - name: 'IBM: Granite 4.0 Micro', +const GOOGLE_GEMINI_3_1_FLASH_LITE_BATCH = { + id: 'google/gemini-3.1-flash-lite:batch', + name: 'Google: Gemini 3.1 Flash Lite (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 131000, - max_output_tokens: 131000, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.017, - cached: 0, + normal: 0.125, + cached: 0.0125, }, output: { - normal: 0.112, + normal: 0.75, }, }, - image: 0, + image: 1.25e-7, }, } as const -const IBM_GRANITE_GRANITE_4_1_8B = { - id: 'ibm-granite/granite-4.1-8b', - name: 'IBM: Granite 4.1 8B', +const GOOGLE_GEMINI_3_1_PRO_PREVIEW = { + id: 'google/gemini-3.1-pro-preview', + name: 'Google: Gemini 3.1 Pro Preview', supports: { - input: ['text'], + input: ['audio', 'document', 'image', 'text', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.05, - cached: 0.05, + normal: 2, + cached: 0.575, }, output: { - normal: 0.1, + normal: 12, }, }, - image: 0, + image: 0.000002, }, } as const -const INCEPTION_MERCURY_2 = { - id: 'inception/mercury-2', - name: 'Inception: Mercury 2', +const GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS = { + id: 'google/gemini-3.1-pro-preview-customtools', + name: 'Google: Gemini 3.1 Pro Preview Custom Tools', supports: { - input: ['text'], + input: ['text', 'audio', 'image', 'video', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', 'reasoning', 'responseFormat', - 'stop', + 'seed', 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 128000, - max_output_tokens: 50000, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.25, - cached: 0.025, + normal: 2, + cached: 0.575, }, output: { - normal: 0.75, + normal: 12, }, }, - image: 0, + image: 0.000002, }, } as const -const INCLUSIONAI_LING_2_6_1T = { - id: 'inclusionai/ling-2.6-1t', - name: 'inclusionAI: Ling-2.6-1T', +const GOOGLE_GEMINI_3_1_PRO_PREVIEW_BATCH = { + id: 'google/gemini-3.1-pro-preview:batch', + name: 'Google: Gemini 3.1 Pro Preview (batch)', supports: { - input: ['text'], + input: ['audio', 'document', 'image', 'text', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.075, - cached: 0.015, + normal: 1, + cached: 0, }, output: { - normal: 0.625, + normal: 6, }, }, - image: 0, + image: 0.000001, }, } as const -const INCLUSIONAI_LING_2_6_FLASH = { - id: 'inclusionai/ling-2.6-flash', - name: 'inclusionAI: Ling-2.6-flash', +const GOOGLE_GEMINI_3_5_FLASH = { + id: 'google/gemini-3.5-flash', + name: 'Google: Gemini 3.5 Flash', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.01, - cached: 0.002, + normal: 1.5, + cached: 0.2333333333, }, output: { - normal: 0.03, + normal: 9, }, }, - image: 0, + image: 0.0000015, }, } as const -const INCLUSIONAI_RING_2_6_1T = { - id: 'inclusionai/ring-2.6-1t', - name: 'inclusionAI: Ring-2.6-1T', +const GOOGLE_GEMINI_3_5_FLASH_LITE = { + id: 'google/gemini-3.5-flash-lite', + name: 'Google: Gemini 3.5 Flash Lite', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', @@ -3172,175 +3333,155 @@ const INCLUSIONAI_RING_2_6_1T = { 'topP', ], }, - context_window: 262144, + context_window: 1048576, max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.075, - cached: 0.015, + normal: 0.3, + cached: 0.1133333333, }, output: { - normal: 0.625, - }, - }, - image: 0, - }, -} as const -const INFLECTION_INFLECTION_3_PI = { - id: 'inflection/inflection-3-pi', - name: 'Inflection: Inflection 3 Pi', - supports: { - input: ['text'], - output: ['text'], - supports: ['maxCompletionTokens', 'stop', 'temperature', 'topP'], - }, - context_window: 8000, - max_output_tokens: 1024, - pricing: { - text: { - input: { normal: 2.5, - cached: 0, - }, - output: { - normal: 10, }, }, - image: 0, + image: 3e-7, }, } as const -const INFLECTION_INFLECTION_3_PRODUCTIVITY = { - id: 'inflection/inflection-3-productivity', - name: 'Inflection: Inflection 3 Productivity', +const GOOGLE_GEMINI_3_5_FLASH_LITE_BATCH = { + id: 'google/gemini-3.5-flash-lite:batch', + name: 'Google: Gemini 3.5 Flash Lite (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], - supports: ['maxCompletionTokens', 'stop', 'temperature', 'topP'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'toolChoice', + ], }, - context_window: 8000, - max_output_tokens: 1024, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 2.5, - cached: 0, + normal: 0.15, + cached: 0.015, }, output: { - normal: 10, + normal: 1.25, }, }, - image: 0, + image: 1.5e-7, }, } as const -const KWAIPILOT_KAT_CODER_PRO_V2 = { - id: 'kwaipilot/kat-coder-pro-v2', - name: 'Kwaipilot: KAT-Coder-Pro V2', +const GOOGLE_GEMINI_3_5_FLASH_BATCH = { + id: 'google/gemini-3.5-flash:batch', + name: 'Google: Gemini 3.5 Flash (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 256000, - max_output_tokens: 80000, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.3, - cached: 0.06, + normal: 0.75, + cached: 0.075, }, output: { - normal: 1.2, + normal: 4.5, }, }, - image: 0, + image: 7.5e-7, }, } as const -const LIQUID_LFM_2_24B_A2B = { - id: 'liquid/lfm-2-24b-a2b', - name: 'LiquidAI: LFM2-24B-A2B', +const GOOGLE_GEMINI_3_6_FLASH = { + id: 'google/gemini-3.6-flash', + name: 'Google: Gemini 3.6 Flash', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', + 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 128000, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.03, - cached: 0, + normal: 0.75, + cached: 0.1166666667, }, output: { - normal: 0.12, + normal: 3.75, }, }, - image: 0, + image: 7.5e-7, }, } as const -const LIQUID_LFM_2_5_1_2B_INSTRUCT_FREE = { - id: 'liquid/lfm-2.5-1.2b-instruct:free', - name: 'LiquidAI: LFM2.5-1.2B-Instruct (free)', +const GOOGLE_GEMINI_3_6_FLASH_BATCH = { + id: 'google/gemini-3.6-flash:batch', + name: 'Google: Gemini 3.6 Flash (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', + 'responseFormat', 'seed', 'stop', - 'temperature', - 'topP', + 'toolChoice', ], }, - context_window: 32768, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.375, + cached: 0.0791666667, }, output: { - normal: 0, + normal: 1.875, }, }, - image: 0, + image: 3.75e-7, }, } as const -const LIQUID_LFM_2_5_1_2B_THINKING_FREE = { - id: 'liquid/lfm-2.5-1.2b-thinking:free', - name: 'LiquidAI: LFM2.5-1.2B-Thinking (free)', +const GOOGLE_GEMINI_3_7_FLASH = { + id: 'google/gemini-3.7-flash', + name: 'Google: Gemini 3.7 Flash', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', @@ -3348,96 +3489,92 @@ const LIQUID_LFM_2_5_1_2B_THINKING_FREE = { 'topP', ], }, - context_window: 32768, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.375, + cached: 0.0583333333, }, output: { - normal: 0, + normal: 1.875, }, }, - image: 0, + image: 3.75e-7, }, } as const -const MANCER_WEAVER = { - id: 'mancer/weaver', - name: 'Mancer: Weaver (alpha)', +const GOOGLE_GEMINI_3_7_FLASH_BATCH = { + id: 'google/gemini-3.7-flash:batch', + name: 'Google: Gemini 3.7 Flash (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', - 'temperature', - 'topLogprobs', - 'topP', + 'toolChoice', ], }, - context_window: 8000, - max_output_tokens: 2000, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.75, - cached: 0, + normal: 0.1875, + cached: 0.039583333299999995, }, output: { - normal: 1, + normal: 0.9375, }, }, - image: 0, + image: 1.875e-7, }, } as const -const META_LLAMA_LLAMA_3_8B_INSTRUCT = { - id: 'meta-llama/llama-3-8b-instruct', - name: 'Meta: Llama 3 8B Instruct', +const GOOGLE_GEMMA_2_27B_IT = { + id: 'google/gemma-2-27b-it', + name: 'Google: Gemma 2 27B', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', + 'seed', 'stop', 'temperature', 'topP', ], }, context_window: 8192, + max_output_tokens: 2048, pricing: { text: { input: { - normal: 0.14, + normal: 0.65, cached: 0, }, output: { - normal: 0.14, + normal: 0.65, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_1_70B_INSTRUCT = { - id: 'meta-llama/llama-3.1-70b-instruct', - name: 'Meta: Llama 3.1 70B Instruct', +const GOOGLE_GEMMA_3_12B_IT = { + id: 'google/gemma-3-12b-it', + name: 'Google: Gemma 3 12B', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -3445,7 +3582,6 @@ const META_LLAMA_LLAMA_3_1_70B_INSTRUCT = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, @@ -3454,21 +3590,21 @@ const META_LLAMA_LLAMA_3_1_70B_INSTRUCT = { pricing: { text: { input: { - normal: 0.4, + normal: 0.05, cached: 0, }, output: { - normal: 0.4, + normal: 0.15, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { - id: 'meta-llama/llama-3.1-8b-instruct', - name: 'Meta: Llama 3.1 8B Instruct', +const GOOGLE_GEMMA_3_27B_IT = { + id: 'google/gemma-3-27b-it', + name: 'Google: Gemma 3 27B', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', @@ -3485,24 +3621,24 @@ const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.02, - cached: 0, + normal: 0.08, + cached: 0.04, }, output: { - normal: 0.03, + normal: 0.45, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT = { - id: 'meta-llama/llama-3.2-11b-vision-instruct', - name: 'Meta: Llama 3.2 11B Vision Instruct', +const GOOGLE_GEMMA_3_4B_IT = { + id: 'google/gemma-3-4b-it', + name: 'Google: Gemma 3 4B', supports: { input: ['text', 'image'], output: ['text'], @@ -3523,19 +3659,19 @@ const META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT = { pricing: { text: { input: { - normal: 0.345, + normal: 0.05, cached: 0, }, output: { - normal: 0.345, + normal: 0.1, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_2_1B_INSTRUCT = { - id: 'meta-llama/llama-3.2-1b-instruct', - name: 'Meta: Llama 3.2 1B Instruct', +const GOOGLE_GEMMA_3N_E4B_IT = { + id: 'google/gemma-3n-e4b-it', + name: 'Google: Gemma 3n 4B', supports: { input: ['text'], output: ['text'], @@ -3544,32 +3680,31 @@ const META_LLAMA_LLAMA_3_2_1B_INSTRUCT = { 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'seed', + 'responseFormat', 'stop', 'temperature', 'topP', ], }, - context_window: 131072, - max_output_tokens: 60000, + context_window: 32768, pricing: { text: { input: { - normal: 0.027, + normal: 0.06, cached: 0, }, output: { - normal: 0.201, + normal: 0.12, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_2_3B_INSTRUCT = { - id: 'meta-llama/llama-3.2-3b-instruct', - name: 'Meta: Llama 3.2 3B Instruct', +const GOOGLE_GEMMA_4_26B_A4B_IT = { + id: 'google/gemma-4-26b-a4b-it', + name: 'Google: Gemma 4 26B A4B ', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ 'frequencyPenalty', @@ -3577,44 +3712,54 @@ const META_LLAMA_LLAMA_3_2_3B_INSTRUCT = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.05, - cached: 0, + normal: 0.12, + cached: 0.05, }, output: { - normal: 0.33, + normal: 0.4, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = { - id: 'meta-llama/llama-3.2-3b-instruct:free', - name: 'Meta: Llama 3.2 3B Instruct (free)', +const GOOGLE_GEMMA_4_26B_A4B_IT_FREE = { + id: 'google/gemma-4-26b-a4b-it:free', + name: 'Google: Gemma 4 26B A4B (free)', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { @@ -3628,11 +3773,11 @@ const META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = { image: 0, }, } as const -const META_LLAMA_LLAMA_3_3_70B_INSTRUCT = { - id: 'meta-llama/llama-3.3-70b-instruct', - name: 'Meta: Llama 3.3 70B Instruct', +const GOOGLE_GEMMA_4_31B_IT = { + id: 'google/gemma-4-31b-it', + name: 'Google: Gemma 4 31B', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ 'frequencyPenalty', @@ -3640,6 +3785,7 @@ const META_LLAMA_LLAMA_3_3_70B_INSTRUCT = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -3649,38 +3795,39 @@ const META_LLAMA_LLAMA_3_3_70B_INSTRUCT = { 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { normal: 0.1, - cached: 0, + cached: 0.1, }, output: { - normal: 0.32, + normal: 0.34, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE = { - id: 'meta-llama/llama-3.3-70b-instruct:free', - name: 'Meta: Llama 3.3 70B Instruct (free)', +const GOOGLE_GEMMA_4_31B_IT_FREE = { + id: 'google/gemma-4-31b-it:free', + name: 'Google: Gemma 4 31B (free)', supports: { - input: ['text'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'stop', + 'reasoning', + 'responseFormat', + 'seed', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 131072, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { @@ -3694,233 +3841,237 @@ const META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE = { image: 0, }, } as const -const META_LLAMA_LLAMA_4_MAVERICK = { - id: 'meta-llama/llama-4-maverick', - name: 'Meta: Llama 4 Maverick', +const GOOGLE_LYRIA_3_CLIP_PREVIEW = { + id: 'google/lyria-3-clip-preview', + name: 'Google: Lyria 3 Clip Preview', supports: { input: ['text', 'image'], - output: ['text'], + output: ['text', 'audio'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'responseFormat', 'seed', - 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, context_window: 1048576, - max_output_tokens: 16384, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.15, + normal: 0, cached: 0, }, output: { - normal: 0.6, + normal: 0, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_4_SCOUT = { - id: 'meta-llama/llama-4-scout', - name: 'Meta: Llama 4 Scout', +const GOOGLE_LYRIA_3_PRO_PREVIEW = { + id: 'google/lyria-3-pro-preview', + name: 'Google: Lyria 3 Pro Preview', supports: { input: ['text', 'image'], - output: ['text'], + output: ['text', 'audio'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', 'responseFormat', 'seed', - 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 10000000, - max_output_tokens: 16384, + context_window: 1048576, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.1, + normal: 0, cached: 0, }, output: { - normal: 0.3, + normal: 0, }, }, image: 0, }, } as const -const META_LLAMA_LLAMA_GUARD_4_12B = { - id: 'meta-llama/llama-guard-4-12b', - name: 'Meta: Llama Guard 4 12B', +const GRYPHE_MYTHOMAX_L2_13B = { + id: 'gryphe/mythomax-l2-13b', + name: 'MythoMax 13B', supports: { - input: ['image', 'text'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'topLogprobs', 'topP', ], }, - context_window: 163840, - max_output_tokens: 16384, + context_window: 8192, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 0.18, + normal: 0.06, cached: 0, }, output: { - normal: 0.18, + normal: 0.06, }, }, image: 0, }, } as const -const MICROSOFT_PHI_4 = { - id: 'microsoft/phi-4', - name: 'Microsoft: Phi 4', +const IBM_GRANITE_GRANITE_4_0_H_MICRO = { + id: 'ibm-granite/granite-4.0-h-micro', + name: 'IBM: Granite 4.0 Micro', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'topLogprobs', 'topP', ], }, - context_window: 16384, - max_output_tokens: 16384, + context_window: 131000, + max_output_tokens: 131000, pricing: { text: { input: { - normal: 0.07, + normal: 0.017, cached: 0, }, output: { - normal: 0.14, + normal: 0.112, }, }, image: 0, }, } as const -const MICROSOFT_WIZARDLM_2_8X22B = { - id: 'microsoft/wizardlm-2-8x22b', - name: 'WizardLM-2 8x22B', +const IBM_GRANITE_GRANITE_4_1_8B = { + id: 'ibm-granite/granite-4.1-8b', + name: 'IBM: Granite 4.1 8B', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 8000, + context_window: 131072, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.62, - cached: 0, + normal: 0.05, + cached: 0.05, }, output: { - normal: 0.62, + normal: 0.1, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_01 = { - id: 'minimax/minimax-01', - name: 'MiniMax: MiniMax-01', +const INCEPTION_MERCURY_2 = { + id: 'inception/mercury-2', + name: 'Inception: Mercury 2', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], - supports: ['maxCompletionTokens', 'temperature', 'topP'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + ], }, - context_window: 1000192, - max_output_tokens: 1000192, + context_window: 128000, + max_output_tokens: 50000, pricing: { text: { input: { - normal: 0.2, - cached: 0, + normal: 0.25, + cached: 0.025, }, output: { - normal: 1.1, + normal: 0.75, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M1 = { - id: 'minimax/minimax-m1', - name: 'MiniMax: MiniMax M1', +const INCLUSIONAI_LING_2_6_1T = { + id: 'inclusionai/ling-2.6-1t', + name: 'inclusionAI: Ling-2.6-1T', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1000000, - max_output_tokens: 40000, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.4, - cached: 0, + normal: 0.075, + cached: 0.015, }, output: { - normal: 2.2, + normal: 0.625, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M2 = { - id: 'minimax/minimax-m2', - name: 'MiniMax: MiniMax M2', +const INCLUSIONAI_LING_2_6_FLASH = { + id: 'inclusionai/ling-2.6-flash', + name: 'inclusionAI: Ling-2.6-flash', supports: { input: ['text'], output: ['text'], @@ -3929,7 +4080,6 @@ const MINIMAX_MINIMAX_M2 = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -3939,47 +4089,60 @@ const MINIMAX_MINIMAX_M2 = { 'topP', ], }, - context_window: 204800, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.255, - cached: 0, + normal: 0.01, + cached: 0.002, }, output: { - normal: 1.02, + normal: 0.03, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M2_HER = { - id: 'minimax/minimax-m2-her', - name: 'MiniMax: MiniMax M2-her', +const INCLUSIONAI_LING_3_0_FLASH = { + id: 'inclusionai/ling-3.0-flash', + name: 'Ling-3.0-flash', supports: { input: ['text'], output: ['text'], - supports: ['maxCompletionTokens', 'temperature', 'topP'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], }, - context_window: 65536, - max_output_tokens: 2048, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.3, - cached: 0.03, + normal: 0.021, + cached: 0.0042, }, output: { - normal: 1.2, + normal: 0.063, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M2_1 = { - id: 'minimax/minimax-m2.1', - name: 'MiniMax: MiniMax M2.1', +const INCLUSIONAI_RING_2_6_1T = { + id: 'inclusionai/ring-2.6-1t', + name: 'inclusionAI: Ring-2.6-1T', supports: { input: ['text'], output: ['text'], @@ -3996,37 +4159,32 @@ const MINIMAX_MINIMAX_M2_1 = { 'topP', ], }, - context_window: 204800, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.3, - cached: 0.03, + normal: 0.075, + cached: 0.015, }, output: { - normal: 1.2, + normal: 0.625, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M2_5 = { - id: 'minimax/minimax-m2.5', - name: 'MiniMax: MiniMax M2.5', +const KWAIPILOT_KAT_CODER_AIR_V2_5 = { + id: 'kwaipilot/kat-coder-air-v2.5', + name: 'Kwaipilot: KAT-Coder-Air V2.5', supports: { input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', - 'parallelToolCalls', 'presencePenalty', - 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', @@ -4034,24 +4192,24 @@ const MINIMAX_MINIMAX_M2_5 = { 'topP', ], }, - context_window: 204800, - max_output_tokens: 196608, + context_window: 256000, + max_output_tokens: 80000, pricing: { text: { input: { - normal: 0.12, - cached: 0, + normal: 0.15, + cached: 0.03, }, output: { - normal: 0.48, + normal: 0.6, }, }, image: 0, }, } as const -const MINIMAX_MINIMAX_M2_7 = { - id: 'minimax/minimax-m2.7', - name: 'MiniMax: MiniMax M2.7', +const KWAIPILOT_KAT_CODER_PRO_V2 = { + id: 'kwaipilot/kat-coder-pro-v2', + name: 'Kwaipilot: KAT-Coder-Pro V2', supports: { input: ['text'], output: ['text'], @@ -4061,7 +4219,6 @@ const MINIMAX_MINIMAX_M2_7 = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -4071,13 +4228,13 @@ const MINIMAX_MINIMAX_M2_7 = { 'topP', ], }, - context_window: 204800, - max_output_tokens: 196608, + context_window: 262144, + max_output_tokens: 80000, pricing: { text: { input: { normal: 0.3, - cached: 0.435, + cached: 0.06, }, output: { normal: 1.2, @@ -4086,21 +4243,17 @@ const MINIMAX_MINIMAX_M2_7 = { image: 0, }, } as const -const MINIMAX_MINIMAX_M3 = { - id: 'minimax/minimax-m3', - name: 'MiniMax: MiniMax M3', +const KWAIPILOT_KAT_CODER_PRO_V2_5 = { + id: 'kwaipilot/kat-coder-pro-v2.5', + name: 'Kwaipilot: KAT-Coder-Pro V2.5', supports: { - input: ['text', 'image', 'video'], + input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', @@ -4108,127 +4261,136 @@ const MINIMAX_MINIMAX_M3 = { 'topP', ], }, - context_window: 1000000, - max_output_tokens: 512000, + context_window: 256000, + max_output_tokens: 80000, pricing: { text: { input: { - normal: 0.6, - cached: 0.12, + normal: 0.74, + cached: 0.15, }, output: { - normal: 2.4, + normal: 2.96, }, }, image: 0, }, } as const -const MISTRALAI_CODESTRAL_2508 = { - id: 'mistralai/codestral-2508', - name: 'Mistral: Codestral 2508', +const LIQUID_LFM_2_5_2_6B_FREE = { + id: 'liquid/lfm-2.5-2.6b:free', + name: 'LiquidAI: LFM2.5-2.6B (free)', supports: { - input: ['text', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 256000, + context_window: 128000, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.3, - cached: 0.03, + normal: 0, + cached: 0, }, output: { - normal: 0.9, + normal: 0, }, }, image: 0, }, } as const -const MISTRALAI_DEVSTRAL_2512 = { - id: 'mistralai/devstral-2512', - name: 'Mistral: Devstral 2 2512', +const MANCER_WEAVER = { + id: 'mancer/weaver', + name: 'Mancer: Weaver (alpha)', supports: { - input: ['text', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 8000, + max_output_tokens: 6000, pricing: { text: { input: { - normal: 0.4, - cached: 0.04, + normal: 0.5, + cached: 0, }, output: { - normal: 2, + normal: 0.75, }, }, image: 0, }, } as const -const MISTRALAI_MINISTRAL_14B_2512 = { - id: 'mistralai/ministral-14b-2512', - name: 'Mistral: Ministral 3 14B 2512', +const MEITUAN_LONGCAT_2_0 = { + id: 'meituan/longcat-2.0', + name: 'Meituan: LongCat 2.0', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', + 'reasoning', 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 1048756, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.2, - cached: 0.02, + normal: 0.3, + cached: 0.006, }, output: { - normal: 0.2, + normal: 1.2, }, }, image: 0, }, } as const -const MISTRALAI_MINISTRAL_3B_2512 = { - id: 'mistralai/ministral-3b-2512', - name: 'Mistral: Ministral 3 3B 2512', +const META_LLAMA_LLAMA_3_1_70B_INSTRUCT = { + id: 'meta-llama/llama-3.1-70b-instruct', + name: 'Meta: Llama 3.1 70B Instruct', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -4242,27 +4404,29 @@ const MISTRALAI_MINISTRAL_3B_2512 = { ], }, context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.1, - cached: 0.01, + normal: 0.4, + cached: 0, }, output: { - normal: 0.1, + normal: 0.4, }, }, image: 0, }, } as const -const MISTRALAI_MINISTRAL_8B_2512 = { - id: 'mistralai/ministral-8b-2512', - name: 'Mistral: Ministral 3 8B 2512', +const META_LLAMA_LLAMA_3_1_8B_INSTRUCT = { + id: 'meta-llama/llama-3.1-8b-instruct', + name: 'Meta: Llama 3.1 8B Instruct', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -4275,92 +4439,97 @@ const MISTRALAI_MINISTRAL_8B_2512 = { 'topP', ], }, - context_window: 262144, + context_window: 131072, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.15, - cached: 0.015, + normal: 0.05, + cached: 0.025, }, output: { - normal: 0.15, + normal: 0.08, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_LARGE = { - id: 'mistralai/mistral-large', - name: 'Mistral Large', +const META_LLAMA_LLAMA_3_2_1B_INSTRUCT = { + id: 'meta-llama/llama-3.2-1b-instruct', + name: 'Meta: Llama 3.2 1B Instruct', supports: { - input: ['text', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 128000, + context_window: 60000, + max_output_tokens: 60000, pricing: { text: { input: { - normal: 2, - cached: 0.2, + normal: 0.027, + cached: 0, }, output: { - normal: 6, + normal: 0.201, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_LARGE_2407 = { - id: 'mistralai/mistral-large-2407', - name: 'Mistral Large 2407', +const META_LLAMA_LLAMA_3_2_3B_INSTRUCT = { + id: 'meta-llama/llama-3.2-3b-instruct', + name: 'Meta: Llama 3.2 3B Instruct', supports: { - input: ['text', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', + 'topLogprobs', 'topP', ], }, context_window: 131072, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 2, - cached: 0.2, + normal: 0.05, + cached: 0, }, output: { - normal: 6, + normal: 0.33, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_LARGE_2512 = { - id: 'mistralai/mistral-large-2512', - name: 'Mistral: Mistral Large 3 2512', +const META_LLAMA_LLAMA_3_3_70B_INSTRUCT = { + id: 'meta-llama/llama-3.3-70b-instruct', + name: 'Meta: Llama 3.3 70B Instruct', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -4368,31 +4537,35 @@ const MISTRALAI_MISTRAL_LARGE_2512 = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.5, - cached: 0.05, + normal: 0.1, + cached: 0, }, output: { - normal: 1.5, + normal: 0.32, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_MEDIUM_3 = { - id: 'mistralai/mistral-medium-3', - name: 'Mistral: Mistral Medium 3', +const META_LLAMA_LLAMA_4_MAVERICK = { + id: 'meta-llama/llama-4-maverick', + name: 'Meta: Llama 4 Maverick', supports: { - input: ['text', 'image', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', @@ -4400,34 +4573,36 @@ const MISTRALAI_MISTRAL_MEDIUM_3 = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, + context_window: 1048576, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.4, - cached: 0.04, + normal: 0.2, + cached: 0, }, output: { - normal: 2, + normal: 0.8, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_MEDIUM_3_5 = { - id: 'mistralai/mistral-medium-3-5', - name: 'Mistral: Mistral Medium 3.5', +const META_LLAMA_LLAMA_4_SCOUT = { + id: 'meta-llama/llama-4-scout', + name: 'Meta: Llama 4 Scout', supports: { - input: ['text', 'image', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -4436,57 +4611,59 @@ const MISTRALAI_MISTRAL_MEDIUM_3_5 = { 'topP', ], }, - context_window: 262144, + context_window: 1310720, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 1.5, + normal: 0.1, cached: 0, }, output: { - normal: 7.5, + normal: 0.3, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_MEDIUM_3_1 = { - id: 'mistralai/mistral-medium-3.1', - name: 'Mistral: Mistral Medium 3.1', +const META_LLAMA_LLAMA_GUARD_4_12B = { + id: 'meta-llama/llama-guard-4-12b', + name: 'Meta: Llama Guard 4 12B', supports: { - input: ['text', 'image', 'document'], + input: ['image', 'text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 131072, + context_window: 1048576, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.4, - cached: 0.04, + normal: 0.18, + cached: 0, }, output: { - normal: 2, + normal: 0.18, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_NEMO = { - id: 'mistralai/mistral-nemo', - name: 'Mistral: Mistral Nemo', +const META_MUSE_GLIMMER_30B = { + id: 'meta/muse-glimmer-30b', + name: 'Meta: Muse Glimmer 30B', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', @@ -4494,6 +4671,7 @@ const MISTRALAI_MISTRAL_NEMO = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -4507,195 +4685,173 @@ const MISTRALAI_MISTRAL_NEMO = { pricing: { text: { input: { - normal: 0.02, - cached: 0, + normal: 0.35, + cached: 0.04, }, output: { - normal: 0.03, + normal: 1.5, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_SABA = { - id: 'mistralai/mistral-saba', - name: 'Mistral: Saba', +const META_MUSE_SPARK_1_1 = { + id: 'meta/muse-spark-1.1', + name: 'Meta: Muse Spark 1.1', supports: { - input: ['text', 'document'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 32768, + context_window: 1048576, pricing: { text: { input: { - normal: 0.2, - cached: 0.02, + normal: 1.25, + cached: 0.15, }, output: { - normal: 0.6, + normal: 4.25, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501 = { - id: 'mistralai/mistral-small-24b-instruct-2501', - name: 'Mistral: Mistral Small 3', +const META_MUSE_SPARK_1_2 = { + id: 'meta/muse-spark-1.2', + name: 'Meta: Muse Spark 1.2', supports: { - input: ['text'], + input: ['text', 'image', 'video', 'document', 'audio'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 32768, - max_output_tokens: 16384, + context_window: 1048576, pricing: { text: { input: { - normal: 0.05, - cached: 0, + normal: 1.25, + cached: 0.15, }, output: { - normal: 0.08, + normal: 4.25, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_SMALL_2603 = { - id: 'mistralai/mistral-small-2603', - name: 'Mistral: Mistral Small 4', +const MICROSOFT_PHI_4 = { + id: 'microsoft/phi-4', + name: 'Microsoft: Phi 4', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 262144, + context_window: 16384, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.15, - cached: 0.015, + normal: 0.07, + cached: 0, }, output: { - normal: 0.6, + normal: 0.14, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT = { - id: 'mistralai/mistral-small-3.1-24b-instruct', - name: 'Mistral: Mistral Small 3.1 24B', +const MICROSOFT_WIZARDLM_2_8X22B = { + id: 'microsoft/wizardlm-2-8x22b', + name: 'WizardLM-2 8x22B', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'responseFormat', 'seed', 'stop', 'temperature', - 'topLogprobs', 'topP', ], }, - context_window: 128000, - max_output_tokens: 128000, + context_window: 65535, + max_output_tokens: 8000, pricing: { text: { input: { - normal: 0.351, + normal: 0.62, cached: 0, }, output: { - normal: 0.555, + normal: 0.62, }, }, image: 0, }, } as const -const MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT = { - id: 'mistralai/mistral-small-3.2-24b-instruct', - name: 'Mistral: Mistral Small 3.2 24B', +const MINIMAX_MINIMAX_01 = { + id: 'minimax/minimax-01', + name: 'MiniMax: MiniMax-01', supports: { - input: ['image', 'text'], + input: ['text', 'image'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], + supports: ['maxCompletionTokens', 'temperature', 'topP'], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 1000192, + max_output_tokens: 1000192, pricing: { text: { input: { - normal: 0.075, + normal: 0.2, cached: 0, }, output: { - normal: 0.2, + normal: 1.1, }, }, image: 0, }, } as const -const MISTRALAI_MIXTRAL_8X22B_INSTRUCT = { - id: 'mistralai/mixtral-8x22b-instruct', - name: 'Mistral: Mixtral 8x22B Instruct', +const MINIMAX_MINIMAX_M1 = { + id: 'minimax/minimax-m1', + name: 'MiniMax: MiniMax M1', supports: { - input: ['text', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', - 'responseFormat', + 'reasoning', 'seed', 'stop', 'temperature', @@ -4703,87 +4859,83 @@ const MISTRALAI_MIXTRAL_8X22B_INSTRUCT = { 'topP', ], }, - context_window: 65536, + context_window: 1000000, + max_output_tokens: 40000, pricing: { text: { input: { - normal: 2, - cached: 0.2, + normal: 0.4, + cached: 0, }, output: { - normal: 6, + normal: 2.2, }, }, image: 0, }, } as const -const MISTRALAI_VOXTRAL_SMALL_24B_2507 = { - id: 'mistralai/voxtral-small-24b-2507', - name: 'Mistral: Voxtral Small 24B 2507', +const MINIMAX_MINIMAX_M2 = { + id: 'minimax/minimax-m2', + name: 'MiniMax: MiniMax M2', supports: { - input: ['text', 'audio', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 32000, + context_window: 204800, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.1, - cached: 0.01, + normal: 0.255, + cached: 0, }, output: { - normal: 0.3, + normal: 1.02, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2 = { - id: 'moonshotai/kimi-k2', - name: 'MoonshotAI: Kimi K2 0711', +const MINIMAX_MINIMAX_M2_HER = { + id: 'minimax/minimax-m2-her', + name: 'MiniMax: MiniMax M2-her', supports: { input: ['text'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'maxCompletionTokens', - 'presencePenalty', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topP', - ], + supports: ['maxCompletionTokens', 'temperature', 'topP'], }, - context_window: 131072, - max_output_tokens: 100352, + context_window: 65536, + max_output_tokens: 2048, pricing: { text: { input: { - normal: 0.57, - cached: 0, + normal: 0.3, + cached: 0.03, }, output: { - normal: 2.3, + normal: 1.2, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_0905 = { - id: 'moonshotai/kimi-k2-0905', - name: 'MoonshotAI: Kimi K2 0905', +const MINIMAX_MINIMAX_M2_1 = { + id: 'minimax/minimax-m2.1', + name: 'MiniMax: MiniMax M2.1', supports: { input: ['text'], output: ['text'], @@ -4791,6 +4943,7 @@ const MOONSHOTAI_KIMI_K2_0905 = { 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -4799,31 +4952,33 @@ const MOONSHOTAI_KIMI_K2_0905 = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 100352, + context_window: 204800, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.6, - cached: 0, + normal: 0.3, + cached: 0.03, }, output: { - normal: 2.5, + normal: 1.2, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_THINKING = { - id: 'moonshotai/kimi-k2-thinking', - name: 'MoonshotAI: Kimi K2 Thinking', +const MINIMAX_MINIMAX_M2_5 = { + id: 'minimax/minimax-m2.5', + name: 'MiniMax: MiniMax M2.5', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -4835,26 +4990,26 @@ const MOONSHOTAI_KIMI_K2_THINKING = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 100352, + context_window: 204800, + max_output_tokens: 196608, pricing: { text: { input: { - normal: 0.6, - cached: 0.15, + normal: 0.22, + cached: 0.05, }, output: { - normal: 2.5, + normal: 0.9, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_5 = { - id: 'moonshotai/kimi-k2.5', - name: 'MoonshotAI: Kimi K2.5', +const MINIMAX_MINIMAX_M2_7 = { + id: 'minimax/minimax-m2.7', + name: 'MiniMax: MiniMax M2.7', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', @@ -4872,32 +5027,32 @@ const MOONSHOTAI_KIMI_K2_5 = { 'topP', ], }, - context_window: 262144, + context_window: 204800, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.375, - cached: 0.203, + normal: 0.3, + cached: 0.06, }, output: { - normal: 2.025, + normal: 1.2, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_6 = { - id: 'moonshotai/kimi-k2.6', - name: 'MoonshotAI: Kimi K2.6', +const MINIMAX_MINIMAX_M3 = { + id: 'minimax/minimax-m3', + name: 'MiniMax: MiniMax M3', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', - 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -4909,136 +5064,143 @@ const MOONSHOTAI_KIMI_K2_6 = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 1048576, + max_output_tokens: 512000, pricing: { text: { input: { - normal: 0.66, - cached: 0.14, + normal: 0.3, + cached: 0.06, }, output: { - normal: 3.41, + normal: 1.2, }, }, image: 0, }, } as const -const MOONSHOTAI_KIMI_K2_7_CODE = { - id: 'moonshotai/kimi-k2.7-code', - name: 'MoonshotAI: Kimi K2.7 Code', +const MINIMAX_MINIMAX_M3_BATCH = { + id: 'minimax/minimax-m3:batch', + name: 'MiniMax: MiniMax M3 (batch)', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 16384, + context_window: 524288, pricing: { text: { input: { - normal: 0.74, - cached: 0.15, + normal: 0.15, + cached: 0.03, }, output: { - normal: 3.5, + normal: 0.6, }, }, image: 0, }, } as const -const MORPH_MORPH_V3_FAST = { - id: 'morph/morph-v3-fast', - name: 'Morph: Morph V3 Fast', +const MISTRALAI_CODESTRAL_2508 = { + id: 'mistralai/codestral-2508', + name: 'Mistral: Codestral 2508', supports: { - input: ['text'], + input: ['text', 'document'], output: ['text'], - supports: ['maxCompletionTokens', 'stop', 'temperature'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'prediction', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], }, - context_window: 81920, - max_output_tokens: 38000, + context_window: 256000, pricing: { text: { input: { - normal: 0.8, - cached: 0, + normal: 0.3, + cached: 0.03, }, output: { - normal: 1.2, + normal: 0.9, }, }, image: 0, }, } as const -const MORPH_MORPH_V3_LARGE = { - id: 'morph/morph-v3-large', - name: 'Morph: Morph V3 Large', +const MISTRALAI_MINISTRAL_14B_2512 = { + id: 'mistralai/ministral-14b-2512', + name: 'Mistral: Ministral 3 14B 2512', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ - 'logprobs', + 'frequencyPenalty', 'maxCompletionTokens', + 'presencePenalty', 'responseFormat', + 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', + 'topP', ], }, context_window: 262144, - max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.9, - cached: 0, + normal: 0.2, + cached: 0.02, }, output: { - normal: 1.9, + normal: 0.2, }, }, image: 0, }, } as const -const NEX_AGI_NEX_N2_MINI = { - id: 'nex-agi/nex-n2-mini', - name: 'Nex AGI: Nex-N2-Mini', +const MISTRALAI_MINISTRAL_3B_2512 = { + id: 'mistralai/ministral-3b-2512', + name: 'Mistral: Ministral 3 3B 2512', supports: { input: ['text', 'image'], output: ['text'], supports: [ - 'logprobs', + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 131072, pricing: { text: { input: { - normal: 0.025, - cached: 0.0025, + normal: 0.1, + cached: 0.01, }, output: { normal: 0.1, @@ -5047,83 +5209,85 @@ const NEX_AGI_NEX_N2_MINI = { image: 0, }, } as const -const NEX_AGI_NEX_N2_PRO = { - id: 'nex-agi/nex-n2-pro', - name: 'Nex AGI: Nex-N2-Pro', +const MISTRALAI_MINISTRAL_8B_2512 = { + id: 'mistralai/ministral-8b-2512', + name: 'Mistral: Ministral 3 8B 2512', supports: { input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, context_window: 262144, - max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.25, - cached: 0.025, + normal: 0.15, + cached: 0.015, }, output: { - normal: 1, + normal: 0.15, }, }, image: 0, }, } as const -const NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = { - id: 'nousresearch/hermes-3-llama-3.1-405b', - name: 'Nous: Hermes 3 405B Instruct', +const MISTRALAI_MISTRAL_LARGE = { + id: 'mistralai/mistral-large', + name: 'Mistral Large', supports: { - input: ['text'], + input: ['text', 'document'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 128000, pricing: { text: { input: { - normal: 1, - cached: 0, + normal: 2, + cached: 0.2, }, output: { - normal: 1, + normal: 6, }, }, image: 0, }, } as const -const NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE = { - id: 'nousresearch/hermes-3-llama-3.1-405b:free', - name: 'Nous: Hermes 3 405B Instruct (free)', +const MISTRALAI_MISTRAL_LARGE_2407 = { + id: 'mistralai/mistral-large-2407', + name: 'Mistral Large 2407', supports: { - input: ['text'], + input: ['text', 'document'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', + 'responseFormat', + 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, @@ -5131,62 +5295,63 @@ const NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE = { pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 2, + cached: 0.2, }, output: { - normal: 0, + normal: 6, }, }, image: 0, }, } as const -const NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = { - id: 'nousresearch/hermes-3-llama-3.1-70b', - name: 'Nous: Hermes 3 70B Instruct', +const MISTRALAI_MISTRAL_LARGE_2512 = { + id: 'mistralai/mistral-large-2512', + name: 'Mistral: Mistral Large 3 2512', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 262144, pricing: { text: { input: { - normal: 0.7, - cached: 0, + normal: 0.5, + cached: 0.05, }, output: { - normal: 0.7, + normal: 1.5, }, }, image: 0, }, } as const -const NOUSRESEARCH_HERMES_4_405B = { - id: 'nousresearch/hermes-4-405b', - name: 'Nous: Hermes 4 405B', +const MISTRALAI_MISTRAL_MEDIUM_3 = { + id: 'mistralai/mistral-medium-3', + name: 'Mistral: Mistral Medium 3', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', + 'toolChoice', 'topP', ], }, @@ -5194,21 +5359,21 @@ const NOUSRESEARCH_HERMES_4_405B = { pricing: { text: { input: { - normal: 1, - cached: 0, + normal: 0.4, + cached: 0.04, }, output: { - normal: 3, + normal: 2, }, }, image: 0, }, } as const -const NOUSRESEARCH_HERMES_4_70B = { - id: 'nousresearch/hermes-4-70b', - name: 'Nous: Hermes 4 70B', +const MISTRALAI_MISTRAL_MEDIUM_3_5 = { + id: 'mistralai/mistral-medium-3-5', + name: 'Mistral: Mistral Medium 3.5', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', @@ -5216,36 +5381,37 @@ const NOUSRESEARCH_HERMES_4_70B = { 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 131072, + context_window: 262144, pricing: { text: { input: { - normal: 0.13, + normal: 1.5, cached: 0, }, output: { - normal: 0.4, + normal: 7.5, }, }, image: 0, }, } as const -const NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5 = { - id: 'nvidia/llama-3.3-nemotron-super-49b-v1.5', - name: 'NVIDIA: Llama 3.3 Nemotron Super 49B V1.5', +const MISTRALAI_MISTRAL_MEDIUM_3_1 = { + id: 'mistralai/mistral-medium-3.1', + name: 'Mistral: Mistral Medium 3.1', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5255,23 +5421,22 @@ const NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5 = { ], }, context_window: 131072, - max_output_tokens: 16384, pricing: { text: { input: { normal: 0.4, - cached: 0, + cached: 0.04, }, output: { - normal: 0.4, + normal: 2, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { - id: 'nvidia/nemotron-3-nano-30b-a3b', - name: 'NVIDIA: Nemotron 3 Nano 30B A3B', +const MISTRALAI_MISTRAL_NEMO = { + id: 'mistralai/mistral-nemo', + name: 'Mistral: Mistral Nemo', supports: { input: ['text'], output: ['text'], @@ -5281,7 +5446,6 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5291,90 +5455,94 @@ const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 228000, + context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.05, + normal: 0.019, cached: 0, }, output: { - normal: 0.2, + normal: 0.03, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE = { - id: 'nvidia/nemotron-3-nano-30b-a3b:free', - name: 'NVIDIA: Nemotron 3 Nano 30B A3B (free)', +const MISTRALAI_MISTRAL_SABA = { + id: 'mistralai/mistral-saba', + name: 'Mistral: Saba', supports: { - input: ['text'], + input: ['text', 'document'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 256000, + context_window: 32768, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.2, + cached: 0.02, }, output: { - normal: 0, + normal: 0.6, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE = { - id: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', - name: 'NVIDIA: Nemotron 3 Nano Omni (free)', +const MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501 = { + id: 'mistralai/mistral-small-24b-instruct-2501', + name: 'Mistral: Mistral Small 3', supports: { - input: ['text', 'audio', 'image', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'responseFormat', 'seed', + 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 256000, - max_output_tokens: 65536, + context_window: 32768, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0, + normal: 0.05, cached: 0, }, output: { - normal: 0, + normal: 0.08, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { - id: 'nvidia/nemotron-3-super-120b-a12b', - name: 'NVIDIA: Nemotron 3 Super', +const MISTRALAI_MISTRAL_SMALL_2603 = { + id: 'mistralai/mistral-small-2603', + name: 'Mistral: Mistral Small 4', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -5383,221 +5551,234 @@ const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 1000000, + context_window: 262144, pricing: { text: { input: { - normal: 0.08, - cached: 0, + normal: 0.15, + cached: 0.015, }, output: { - normal: 0.45, + normal: 0.6, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE = { - id: 'nvidia/nemotron-3-super-120b-a12b:free', - name: 'NVIDIA: Nemotron 3 Super (free)', +const MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT = { + id: 'mistralai/mistral-small-3.1-24b-instruct', + name: 'Mistral: Mistral Small 3.1 24B', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'reasoning', - 'responseFormat', + 'presencePenalty', 'seed', + 'stop', 'temperature', - 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1000000, - max_output_tokens: 262144, + context_window: 128000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0, + normal: 0.351, cached: 0, }, output: { - normal: 0, + normal: 0.555, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B = { - id: 'nvidia/nemotron-3-ultra-550b-a55b', - name: 'NVIDIA: Nemotron 3 Ultra', +const MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT = { + id: 'mistralai/mistral-small-3.2-24b-instruct', + name: 'Mistral: Mistral Small 3.2 24B', supports: { - input: ['text'], + input: ['image', 'text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1000000, + context_window: 256000, max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.5, - cached: 0.1, + normal: 0.09375, + cached: 0, }, output: { - normal: 2.2, + normal: 0.25, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE = { - id: 'nvidia/nemotron-3-ultra-550b-a55b:free', - name: 'NVIDIA: Nemotron 3 Ultra (free)', +const MISTRALAI_MIXTRAL_8X22B_INSTRUCT = { + id: 'mistralai/mixtral-8x22b-instruct', + name: 'Mistral: Mixtral 8x22B Instruct', supports: { - input: ['text'], + input: ['text', 'document'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 65536, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 2, + cached: 0.2, }, output: { - normal: 0, + normal: 6, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE = { - id: 'nvidia/nemotron-3.5-content-safety:free', - name: 'NVIDIA: Nemotron 3.5 Content Safety (free)', +const MISTRALAI_VOXTRAL_SMALL_24B_2507 = { + id: 'mistralai/voxtral-small-24b-2507', + name: 'Mistral: Voxtral Small 24B 2507', supports: { - input: ['text', 'image'], + input: ['text', 'audio', 'document'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'responseFormat', 'seed', + 'stop', 'temperature', + 'toolChoice', 'topP', ], }, - context_window: 128000, - max_output_tokens: 8192, + context_window: 32000, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.1, + cached: 0.01, }, output: { - normal: 0, + normal: 0.3, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE = { - id: 'nvidia/nemotron-nano-12b-v2-vl:free', - name: 'NVIDIA: Nemotron Nano 12B 2 VL (free)', +const MOONSHOTAI_KIMI_K2 = { + id: 'moonshotai/kimi-k2', + name: 'MoonshotAI: Kimi K2 0711', supports: { - input: ['image', 'text', 'video'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 128000, - max_output_tokens: 128000, + context_window: 131072, + max_output_tokens: 100352, pricing: { text: { input: { - normal: 0, + normal: 0.57, cached: 0, }, output: { - normal: 0, + normal: 2.3, }, }, image: 0, }, } as const -const NVIDIA_NEMOTRON_NANO_9B_V2_FREE = { - id: 'nvidia/nemotron-nano-9b-v2:free', - name: 'NVIDIA: Nemotron Nano 9B V2 (free)', +const MOONSHOTAI_KIMI_K2_0905 = { + id: 'moonshotai/kimi-k2-0905', + name: 'MoonshotAI: Kimi K2 0905', supports: { input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topP', ], }, - context_window: 128000, + context_window: 262144, + max_output_tokens: 100352, pricing: { text: { input: { - normal: 0, + normal: 0.6, cached: 0, }, output: { - normal: 0, + normal: 2.5, }, }, image: 0, }, } as const -const OPENAI_GPT_3_5_TURBO = { - id: 'openai/gpt-3.5-turbo', - name: 'OpenAI: GPT-3.5 Turbo', +const MOONSHOTAI_KIMI_K2_THINKING = { + id: 'moonshotai/kimi-k2-thinking', + name: 'MoonshotAI: Kimi K2 Thinking', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5607,26 +5788,26 @@ const OPENAI_GPT_3_5_TURBO = { 'topP', ], }, - context_window: 16385, - max_output_tokens: 4096, + context_window: 262144, + max_output_tokens: 100352, pricing: { text: { input: { - normal: 0.5, - cached: 0, + normal: 0.6, + cached: 0.15, }, output: { - normal: 1.5, + normal: 2.5, }, }, image: 0, }, } as const -const OPENAI_GPT_3_5_TURBO_0613 = { - id: 'openai/gpt-3.5-turbo-0613', - name: 'OpenAI: GPT-3.5 Turbo (older v0613)', +const MOONSHOTAI_KIMI_K2_5 = { + id: 'moonshotai/kimi-k2.5', + name: 'MoonshotAI: Kimi K2.5', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', @@ -5634,6 +5815,7 @@ const OPENAI_GPT_3_5_TURBO_0613 = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5643,34 +5825,35 @@ const OPENAI_GPT_3_5_TURBO_0613 = { 'topP', ], }, - context_window: 4095, - max_output_tokens: 4096, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 1, - cached: 0, + normal: 0.57, + cached: 0.095, }, output: { - normal: 2, + normal: 2.85, }, }, image: 0, }, } as const -const OPENAI_GPT_3_5_TURBO_16K = { - id: 'openai/gpt-3.5-turbo-16k', - name: 'OpenAI: GPT-3.5 Turbo 16k', +const MOONSHOTAI_KIMI_K2_6 = { + id: 'moonshotai/kimi-k2.6', + name: 'MoonshotAI: Kimi K2.6', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5680,98 +5863,97 @@ const OPENAI_GPT_3_5_TURBO_16K = { 'topP', ], }, - context_window: 16385, - max_output_tokens: 4096, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 3, - cached: 0, + normal: 0.5415, + cached: 0.0912, }, output: { - normal: 4, + normal: 2.28, }, }, image: 0, }, } as const -const OPENAI_GPT_3_5_TURBO_INSTRUCT = { - id: 'openai/gpt-3.5-turbo-instruct', - name: 'OpenAI: GPT-3.5 Turbo Instruct', +const MOONSHOTAI_KIMI_K2_7_CODE = { + id: 'moonshotai/kimi-k2.7-code', + name: 'MoonshotAI: Kimi K2.7 Code', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', + 'parallelToolCalls', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 4095, - max_output_tokens: 4096, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 1.5, - cached: 0, + normal: 0.71, + cached: 0.15, }, output: { - normal: 2, + normal: 3.5, }, }, image: 0, }, } as const -const OPENAI_GPT_4 = { - id: 'openai/gpt-4', - name: 'OpenAI: GPT-4', +const MOONSHOTAI_KIMI_K2_7_CODE_BATCH = { + id: 'moonshotai/kimi-k2.7-code:batch', + name: 'MoonshotAI: Kimi K2.7 Code (batch)', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', - 'maxCompletionTokens', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 8191, - max_output_tokens: 4096, + context_window: 262144, pricing: { text: { input: { - normal: 30, - cached: 0, + normal: 0.475, + cached: 0.095, }, output: { - normal: 60, + normal: 2, }, }, image: 0, }, } as const -const OPENAI_GPT_4_TURBO = { - id: 'openai/gpt-4-turbo', - name: 'OpenAI: GPT-4 Turbo', +const MOONSHOTAI_KIMI_K3 = { + id: 'moonshotai/kimi-k3', + name: 'MoonshotAI: Kimi K3', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', @@ -5779,6 +5961,7 @@ const OPENAI_GPT_4_TURBO = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -5788,309 +5971,276 @@ const OPENAI_GPT_4_TURBO = { 'topP', ], }, - context_window: 128000, - max_output_tokens: 4096, + context_window: 1048576, pricing: { text: { input: { - normal: 10, - cached: 0, + normal: 3, + cached: 0.3, }, output: { - normal: 30, + normal: 15, }, }, image: 0, }, } as const -const OPENAI_GPT_4_TURBO_PREVIEW = { - id: 'openai/gpt-4-turbo-preview', - name: 'OpenAI: GPT-4 Turbo Preview', +const MORPH_MORPH_V3_FAST = { + id: 'morph/morph-v3-fast', + name: 'Morph: Morph V3 Fast', supports: { input: ['text'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], + supports: ['maxCompletionTokens', 'stop', 'temperature'], }, - context_window: 128000, - max_output_tokens: 4096, + context_window: 81920, + max_output_tokens: 38000, pricing: { text: { input: { - normal: 10, + normal: 0.8, cached: 0, }, output: { - normal: 30, + normal: 1.2, }, }, image: 0, }, } as const -const OPENAI_GPT_4_1 = { - id: 'openai/gpt-4.1', - name: 'OpenAI: GPT-4.1', +const MORPH_MORPH_V3_LARGE = { + id: 'morph/morph-v3-large', + name: 'Morph: Morph V3 Large', supports: { - input: ['image', 'text', 'document'], + input: ['text'], output: ['text'], supports: [ - 'maxCompletionTokens', + 'logprobs', 'maxCompletionTokens', 'responseFormat', - 'seed', + 'stop', 'temperature', - 'toolChoice', - 'topP', + 'topLogprobs', ], }, - context_window: 1047576, + context_window: 262144, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 2, - cached: 0.5, + normal: 0.9, + cached: 0, }, output: { - normal: 8, + normal: 1.9, }, }, image: 0, }, } as const -const OPENAI_GPT_4_1_MINI = { - id: 'openai/gpt-4.1-mini', - name: 'OpenAI: GPT-4.1 Mini', +const NEX_AGI_NEX_N2_MINI = { + id: 'nex-agi/nex-n2-mini', + name: 'Nex AGI: Nex-N2-Mini', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', + 'reasoning', 'responseFormat', - 'seed', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1047576, - max_output_tokens: 32768, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.4, - cached: 0.1, + normal: 0.025, + cached: 0.0025, }, output: { - normal: 1.6, + normal: 0.1, }, }, image: 0, }, } as const -const OPENAI_GPT_4_1_NANO = { - id: 'openai/gpt-4.1-nano', - name: 'OpenAI: GPT-4.1 Nano', +const NEX_AGI_NEX_N2_PRO = { + id: 'nex-agi/nex-n2-pro', + name: 'Nex AGI: Nex-N2-Pro', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', - 'responseFormat', - 'seed', + 'reasoning', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 1047576, - max_output_tokens: 32768, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.1, + normal: 0.25, cached: 0.025, }, output: { - normal: 0.4, + normal: 1, }, }, image: 0, }, } as const -const OPENAI_GPT_4O = { - id: 'openai/gpt-4o', - name: 'OpenAI: GPT-4o', +const NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = { + id: 'nousresearch/hermes-3-llama-3.1-405b', + name: 'Nous: Hermes 3 405B Instruct', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', - 'maxCompletionTokens', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 128000, + context_window: 131072, max_output_tokens: 16384, pricing: { text: { input: { - normal: 2.5, + normal: 1, cached: 0, }, output: { - normal: 10, + normal: 1, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_2024_05_13 = { - id: 'openai/gpt-4o-2024-05-13', - name: 'OpenAI: GPT-4o (2024-05-13)', +const NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = { + id: 'nousresearch/hermes-3-llama-3.1-70b', + name: 'Nous: Hermes 3 70B Instruct', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', - 'maxCompletionTokens', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 128000, - max_output_tokens: 4096, + context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 5, + normal: 0.7, cached: 0, }, output: { - normal: 15, + normal: 0.7, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_2024_08_06 = { - id: 'openai/gpt-4o-2024-08-06', - name: 'OpenAI: GPT-4o (2024-08-06)', +const NOUSRESEARCH_HERMES_4_405B = { + id: 'nousresearch/hermes-4-405b', + name: 'Nous: Hermes 4 405B', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 131072, pricing: { text: { input: { - normal: 2.5, - cached: 1.25, + normal: 1, + cached: 0, }, output: { - normal: 10, + normal: 3, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_2024_11_20 = { - id: 'openai/gpt-4o-2024-11-20', - name: 'OpenAI: GPT-4o (2024-11-20)', +const NOUSRESEARCH_HERMES_4_70B = { + id: 'nousresearch/hermes-4-70b', + name: 'Nous: Hermes 4 70B', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', - 'seed', - 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 131072, pricing: { text: { input: { - normal: 2.5, - cached: 1.25, + normal: 0.13, + cached: 0, }, output: { - normal: 10, + normal: 0.4, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_MINI = { - id: 'openai/gpt-4o-mini', - name: 'OpenAI: GPT-4o-mini', +const NVIDIA_NEMOTRON_3_NANO_30B_A3B = { + id: 'nvidia/nemotron-3-nano-30b-a3b', + name: 'NVIDIA: Nemotron 3 Nano 30B A3B', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -6100,895 +6250,960 @@ const OPENAI_GPT_4O_MINI = { 'topP', ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 228000, pricing: { text: { input: { - normal: 0.15, - cached: 0.075, + normal: 0.05, + cached: 0.025, }, output: { - normal: 0.6, + normal: 0.2, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_MINI_2024_07_18 = { - id: 'openai/gpt-4o-mini-2024-07-18', - name: 'OpenAI: GPT-4o-mini (2024-07-18)', +const NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE = { + id: 'nvidia/nemotron-3-nano-30b-a3b:free', + name: 'NVIDIA: Nemotron 3 Nano 30B A3B (free)', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', + 'reasoning', 'seed', - 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 256000, pricing: { text: { input: { - normal: 0.15, - cached: 0.075, + normal: 0, + cached: 0, }, output: { - normal: 0.6, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_MINI_SEARCH_PREVIEW = { - id: 'openai/gpt-4o-mini-search-preview', - name: 'OpenAI: GPT-4o-mini Search Preview', +const NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE = { + id: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', + name: 'NVIDIA: Nemotron 3 Nano Omni (free)', supports: { - input: ['text'], + input: ['text', 'audio', 'image', 'video'], output: ['text'], - supports: ['maxCompletionTokens', 'responseFormat'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'seed', + 'temperature', + 'toolChoice', + 'topP', + ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 256000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.15, + normal: 0, cached: 0, }, output: { - normal: 0.6, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_4O_SEARCH_PREVIEW = { - id: 'openai/gpt-4o-search-preview', - name: 'OpenAI: GPT-4o Search Preview', - supports: { - input: ['text'], +const NVIDIA_NEMOTRON_3_SUPER_120B_A12B = { + id: 'nvidia/nemotron-3-super-120b-a12b', + name: 'NVIDIA: Nemotron 3 Super', + supports: { + input: ['text'], output: ['text'], - supports: ['maxCompletionTokens', 'responseFormat'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], }, - context_window: 128000, + context_window: 1000000, max_output_tokens: 16384, pricing: { text: { input: { - normal: 2.5, + normal: 0.085, cached: 0, }, output: { - normal: 10, + normal: 0.4, }, }, image: 0, }, } as const -const OPENAI_GPT_5 = { - id: 'openai/gpt-5', - name: 'OpenAI: GPT-5', +const NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE = { + id: 'nvidia/nemotron-3-super-120b-a12b:free', + name: 'NVIDIA: Nemotron 3 Super (free)', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, - pricing: { - text: { - input: { - normal: 1.25, - cached: 0.125, - }, - output: { - normal: 10, - }, - }, - image: 0, - }, -} as const -const OPENAI_GPT_5_CHAT = { - id: 'openai/gpt-5-chat', - name: 'OpenAI: GPT-5 Chat', - supports: { - input: ['document', 'image', 'text'], - output: ['text'], - supports: ['maxCompletionTokens', 'responseFormat', 'seed'], - }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 1.25, - cached: 0.125, + normal: 0, + cached: 0, }, output: { - normal: 10, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_CODEX = { - id: 'openai/gpt-5-codex', - name: 'OpenAI: GPT-5 Codex', +const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B = { + id: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'NVIDIA: Nemotron 3 Ultra', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 512288, pricing: { text: { input: { - normal: 1.25, - cached: 0.125, + normal: 0.6, + cached: 0.2, }, output: { - normal: 10, + normal: 3.6, }, }, image: 0, }, } as const -const OPENAI_GPT_5_IMAGE = { - id: 'openai/gpt-5-image', - name: 'OpenAI: GPT-5 Image', +const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_BATCH = { + id: 'nvidia/nemotron-3-ultra-550b-a55b:batch', + name: 'NVIDIA: Nemotron 3 Ultra (batch)', supports: { - input: ['image', 'text', 'document'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', 'responseFormat', - 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 512288, pricing: { text: { input: { - normal: 10, - cached: 1.25, + normal: 0.3, + cached: 0.1, }, output: { - normal: 10, + normal: 1.8, }, }, image: 0, }, } as const -const OPENAI_GPT_5_IMAGE_MINI = { - id: 'openai/gpt-5-image-mini', - name: 'OpenAI: GPT-5 Image Mini', +const NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE = { + id: 'nvidia/nemotron-3-ultra-550b-a55b:free', + name: 'NVIDIA: Nemotron 3 Ultra (free)', supports: { - input: ['document', 'image', 'text'], - output: ['image', 'text'], + input: ['text'], + output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'responseFormat', 'seed', - 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 1000000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 2.5, - cached: 0.25, + normal: 0, + cached: 0, }, output: { - normal: 2, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_MINI = { - id: 'openai/gpt-5-mini', - name: 'OpenAI: GPT-5 Mini', +const NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE = { + id: 'nvidia/nemotron-3.5-content-safety:free', + name: 'NVIDIA: Nemotron 3.5 Content Safety (free)', supports: { - input: ['text', 'image', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', - 'responseFormat', 'seed', - 'toolChoice', + 'temperature', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 128000, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.25, - cached: 0.025, + normal: 0, + cached: 0, }, output: { - normal: 2, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_NANO = { - id: 'openai/gpt-5-nano', - name: 'OpenAI: GPT-5 Nano', +const NVIDIA_NEMOTRON_3_5_LIGHTNING = { + id: 'nvidia/nemotron-3.5-lightning', + name: 'NVIDIA: Nemotron 3.5 Lightning', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, + context_window: 1000000, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.05, - cached: 0.01, + normal: 0.1, + cached: 0.05, }, output: { - normal: 0.4, + normal: 0.25, }, }, image: 0, }, } as const -const OPENAI_GPT_5_PRO = { - id: 'openai/gpt-5-pro', - name: 'OpenAI: GPT-5 Pro', +const NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE = { + id: 'nvidia/nemotron-3.5-lightning:free', + name: 'NVIDIA: Nemotron 3.5 Lightning (free)', supports: { - input: ['image', 'text', 'document'], + input: ['text'], output: ['text'], supports: [ 'maxCompletionTokens', 'reasoning', - 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 1000000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 15, + normal: 0, cached: 0, }, output: { - normal: 120, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_1 = { - id: 'openai/gpt-5.1', - name: 'OpenAI: GPT-5.1', +const NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE = { + id: 'nvidia/nemotron-nano-12b-v2-vl:free', + name: 'NVIDIA: Nemotron Nano 12B 2 VL (free)', supports: { - input: ['image', 'text', 'document'], + input: ['image', 'text', 'video'], output: ['text'], supports: [ - 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', - 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, + context_window: 128000, max_output_tokens: 128000, pricing: { text: { input: { - normal: 1.25, - cached: 0.13, + normal: 0, + cached: 0, }, output: { - normal: 10, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_1_CHAT = { - id: 'openai/gpt-5.1-chat', - name: 'OpenAI: GPT-5.1 Chat', +const NVIDIA_NEMOTRON_NANO_9B_V2_FREE = { + id: 'nvidia/nemotron-nano-9b-v2:free', + name: 'NVIDIA: Nemotron Nano 9B V2 (free)', supports: { - input: ['document', 'image', 'text'], + input: ['text'], output: ['text'], supports: [ 'maxCompletionTokens', - 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, context_window: 128000, - max_output_tokens: 32000, pricing: { text: { input: { - normal: 1.25, - cached: 0.13, + normal: 0, + cached: 0, }, output: { - normal: 10, + normal: 0, }, }, image: 0, }, } as const -const OPENAI_GPT_5_1_CODEX = { - id: 'openai/gpt-5.1-codex', - name: 'OpenAI: GPT-5.1-Codex', +const OPENAI_GPT_3_5_TURBO = { + id: 'openai/gpt-3.5-turbo', + name: 'OpenAI: GPT-3.5 Turbo', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 16385, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.25, - cached: 0.13, + normal: 0.5, + cached: 0, }, output: { - normal: 10, + normal: 1.5, }, }, image: 0, }, } as const -const OPENAI_GPT_5_1_CODEX_MAX = { - id: 'openai/gpt-5.1-codex-max', - name: 'OpenAI: GPT-5.1-Codex-Max', +const OPENAI_GPT_3_5_TURBO_0613 = { + id: 'openai/gpt-3.5-turbo-0613', + name: 'OpenAI: GPT-3.5 Turbo (older v0613)', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 4095, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.25, - cached: 0.125, + normal: 1, + cached: 0, }, output: { - normal: 10, + normal: 2, }, }, image: 0, }, } as const -const OPENAI_GPT_5_1_CODEX_MINI = { - id: 'openai/gpt-5.1-codex-mini', - name: 'OpenAI: GPT-5.1-Codex-Mini', +const OPENAI_GPT_3_5_TURBO_16K = { + id: 'openai/gpt-3.5-turbo-16k', + name: 'OpenAI: GPT-3.5 Turbo 16k', supports: { - input: ['image', 'text'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 100000, + context_window: 16385, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 0.25, - cached: 0.025, + normal: 3, + cached: 0, }, output: { - normal: 2, + normal: 4, }, }, image: 0, }, } as const -const OPENAI_GPT_5_2 = { - id: 'openai/gpt-5.2', - name: 'OpenAI: GPT-5.2', +const OPENAI_GPT_3_5_TURBO_INSTRUCT = { + id: 'openai/gpt-3.5-turbo-instruct', + name: 'OpenAI: GPT-3.5 Turbo Instruct', supports: { - input: ['document', 'image', 'text'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', - 'toolChoice', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 4095, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.75, - cached: 0.175, + normal: 1.5, + cached: 0, }, output: { - normal: 14, + normal: 2, }, }, image: 0, }, } as const -const OPENAI_GPT_5_2_CHAT = { - id: 'openai/gpt-5.2-chat', - name: 'OpenAI: GPT-5.2 Chat', +const OPENAI_GPT_3_5_TURBO_BATCH = { + id: 'openai/gpt-3.5-turbo:batch', + name: 'OpenAI: GPT-3.5 Turbo (batch)', supports: { - input: ['document', 'image', 'text'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 128000, - max_output_tokens: 16384, + context_window: 16385, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.75, - cached: 0.175, + normal: 0.25, + cached: 0, }, output: { - normal: 14, + normal: 0.75, }, }, image: 0, }, } as const -const OPENAI_GPT_5_2_CODEX = { - id: 'openai/gpt-5.2-codex', - name: 'OpenAI: GPT-5.2-Codex', +const OPENAI_GPT_4 = { + id: 'openai/gpt-4', + name: 'OpenAI: GPT-4', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 8191, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.75, - cached: 0.175, + normal: 30, + cached: 0, }, output: { - normal: 14, + normal: 60, }, }, image: 0, }, } as const -const OPENAI_GPT_5_2_PRO = { - id: 'openai/gpt-5.2-pro', - name: 'OpenAI: GPT-5.2 Pro', +const OPENAI_GPT_4_TURBO = { + id: 'openai/gpt-4-turbo', + name: 'OpenAI: GPT-4 Turbo', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 128000, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 21, + normal: 10, cached: 0, }, output: { - normal: 168, + normal: 30, }, }, image: 0, }, } as const -const OPENAI_GPT_5_3_CHAT = { - id: 'openai/gpt-5.3-chat', - name: 'OpenAI: GPT-5.3 Chat', +const OPENAI_GPT_4_TURBO_PREVIEW = { + id: 'openai/gpt-4-turbo-preview', + name: 'OpenAI: GPT-4 Turbo Preview', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, context_window: 128000, - max_output_tokens: 16384, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.75, - cached: 0.175, + normal: 10, + cached: 0, }, output: { - normal: 14, + normal: 30, }, }, image: 0, }, } as const -const OPENAI_GPT_5_3_CODEX = { - id: 'openai/gpt-5.3-codex', - name: 'OpenAI: GPT-5.3-Codex', +const OPENAI_GPT_4_TURBO_BATCH = { + id: 'openai/gpt-4-turbo:batch', + name: 'OpenAI: GPT-4 Turbo (batch)', supports: { - input: ['text', 'image', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 128000, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 1.75, - cached: 0.175, + normal: 5, + cached: 0, }, output: { - normal: 14, + normal: 15, }, }, image: 0, }, } as const -const OPENAI_GPT_5_4 = { - id: 'openai/gpt-5.4', - name: 'OpenAI: GPT-5.4', +const OPENAI_GPT_4_1 = { + id: 'openai/gpt-4.1', + name: 'OpenAI: GPT-4.1', supports: { - input: ['text', 'image', 'document'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 1050000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 2.5, - cached: 0.25, + normal: 2, + cached: 0.5, }, output: { - normal: 15, + normal: 8, }, }, image: 0, }, } as const -const OPENAI_GPT_5_4_IMAGE_2 = { - id: 'openai/gpt-5.4-image-2', - name: 'OpenAI: GPT-5.4 Image 2', +const OPENAI_GPT_4_1_MINI = { + id: 'openai/gpt-4.1-mini', + name: 'OpenAI: GPT-4.1 Mini', supports: { input: ['image', 'text', 'document'], - output: ['image', 'text'], + output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', + 'maxCompletionTokens', 'responseFormat', 'seed', - 'stop', - 'topLogprobs', + 'temperature', + 'toolChoice', + 'topP', ], }, - context_window: 272000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 8, - cached: 2, + normal: 0.4, + cached: 0.1, }, output: { - normal: 15, + normal: 1.6, }, }, image: 0, }, } as const -const OPENAI_GPT_5_4_MINI = { - id: 'openai/gpt-5.4-mini', - name: 'OpenAI: GPT-5.4 Mini', +const OPENAI_GPT_4_1_MINI_BATCH = { + id: 'openai/gpt-4.1-mini:batch', + name: 'OpenAI: GPT-4.1 Mini (batch)', supports: { - input: ['document', 'image', 'text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.75, - cached: 0.075, + normal: 0.2, + cached: 0.05, }, output: { - normal: 4.5, + normal: 0.8, }, }, image: 0, }, } as const -const OPENAI_GPT_5_4_NANO = { - id: 'openai/gpt-5.4-nano', - name: 'OpenAI: GPT-5.4 Nano', +const OPENAI_GPT_4_1_NANO = { + id: 'openai/gpt-4.1-nano', + name: 'OpenAI: GPT-4.1 Nano', supports: { - input: ['document', 'image', 'text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.2, - cached: 0.02, + normal: 0.1, + cached: 0.025, }, output: { - normal: 1.25, + normal: 0.4, }, }, image: 0, }, } as const -const OPENAI_GPT_5_4_PRO = { - id: 'openai/gpt-5.4-pro', - name: 'OpenAI: GPT-5.4 Pro', +const OPENAI_GPT_4_1_NANO_BATCH = { + id: 'openai/gpt-4.1-nano:batch', + name: 'OpenAI: GPT-4.1 Nano (batch)', supports: { - input: ['text', 'image', 'document'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 1050000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 30, - cached: 0, + normal: 0.05, + cached: 0.0125, }, output: { - normal: 180, + normal: 0.2, }, }, image: 0, }, } as const -const OPENAI_GPT_5_5 = { - id: 'openai/gpt-5.5', - name: 'OpenAI: GPT-5.5', +const OPENAI_GPT_4_1_BATCH = { + id: 'openai/gpt-4.1:batch', + name: 'OpenAI: GPT-4.1 (batch)', supports: { - input: ['document', 'image', 'text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', - 'maxCompletionTokens', - 'reasoning', 'responseFormat', 'seed', + 'temperature', 'toolChoice', + 'topP', ], }, - context_window: 1050000, - max_output_tokens: 128000, + context_window: 1047576, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 5, - cached: 0.5, + normal: 1, + cached: 0.25, }, output: { - normal: 30, + normal: 4, }, }, image: 0, }, } as const -const OPENAI_GPT_5_5_PRO = { - id: 'openai/gpt-5.5-pro', - name: 'OpenAI: GPT-5.5 Pro', +const OPENAI_GPT_4O = { + id: 'openai/gpt-4o', + name: 'OpenAI: GPT-4o', supports: { - input: ['document', 'image', 'text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'maxCompletionTokens', + 'prediction', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', + 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 1050000, - max_output_tokens: 128000, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 30, - cached: 0, + normal: 2.5, + cached: 1.25, }, output: { - normal: 180, + normal: 10, }, }, image: 0, }, } as const -const OPENAI_GPT_AUDIO = { - id: 'openai/gpt-audio', - name: 'OpenAI: GPT Audio', +const OPENAI_GPT_4O_2024_05_13 = { + id: 'openai/gpt-4o-2024-05-13', + name: 'OpenAI: GPT-4o (2024-05-13)', supports: { - input: ['text', 'audio'], - output: ['text', 'audio'], + input: ['text', 'image', 'document'], + output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'prediction', 'presencePenalty', 'responseFormat', 'seed', @@ -7000,31 +7215,33 @@ const OPENAI_GPT_AUDIO = { ], }, context_window: 128000, - max_output_tokens: 16384, + max_output_tokens: 4096, pricing: { text: { input: { - normal: 2.5, + normal: 5, cached: 0, }, output: { - normal: 10, + normal: 15, }, }, image: 0, }, } as const -const OPENAI_GPT_AUDIO_MINI = { - id: 'openai/gpt-audio-mini', - name: 'OpenAI: GPT Audio Mini', +const OPENAI_GPT_4O_2024_08_06 = { + id: 'openai/gpt-4o-2024-08-06', + name: 'OpenAI: GPT-4o (2024-08-06)', supports: { - input: ['text', 'audio'], - output: ['text', 'audio'], + input: ['text', 'image', 'document'], + output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'prediction', 'presencePenalty', 'responseFormat', 'seed', @@ -7040,19 +7257,19 @@ const OPENAI_GPT_AUDIO_MINI = { pricing: { text: { input: { - normal: 0.6, - cached: 0, + normal: 2.5, + cached: 1.25, }, output: { - normal: 2.4, + normal: 10, }, }, image: 0, }, } as const -const OPENAI_GPT_CHAT_LATEST = { - id: 'openai/gpt-chat-latest', - name: 'OpenAI: GPT Chat Latest', +const OPENAI_GPT_4O_2024_11_20 = { + id: 'openai/gpt-4o-2024-11-20', + name: 'OpenAI: GPT-4o (2024-11-20)', supports: { input: ['text', 'image', 'document'], output: ['text'], @@ -7061,42 +7278,46 @@ const OPENAI_GPT_CHAT_LATEST = { 'logitBias', 'logprobs', 'maxCompletionTokens', + 'prediction', 'presencePenalty', 'responseFormat', 'seed', 'stop', + 'temperature', 'toolChoice', 'topLogprobs', + 'topP', ], }, - context_window: 400000, - max_output_tokens: 128000, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 5, - cached: 0.5, + normal: 2.5, + cached: 1.25, }, output: { - normal: 30, + normal: 10, }, }, image: 0, }, } as const -const OPENAI_GPT_OSS_120B = { - id: 'openai/gpt-oss-120b', - name: 'OpenAI: gpt-oss-120b', +const OPENAI_GPT_4O_MINI = { + id: 'openai/gpt-4o-mini', + name: 'OpenAI: GPT-4o-mini', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', + 'maxCompletionTokens', + 'prediction', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -7106,65 +7327,71 @@ const OPENAI_GPT_OSS_120B = { 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.03, - cached: 0, + normal: 0.15, + cached: 0.075, }, output: { - normal: 0.15, + normal: 0.6, }, }, image: 0, }, } as const -const OPENAI_GPT_OSS_120B_FREE = { - id: 'openai/gpt-oss-120b:free', - name: 'OpenAI: gpt-oss-120b (free)', +const OPENAI_GPT_4O_MINI_2024_07_18 = { + id: 'openai/gpt-4o-mini-2024-07-18', + name: 'OpenAI: GPT-4o-mini (2024-07-18)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'prediction', + 'presencePenalty', + 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.15, + cached: 0.075, }, output: { - normal: 0, + normal: 0.6, }, }, image: 0, }, } as const -const OPENAI_GPT_OSS_20B = { - id: 'openai/gpt-oss-20b', - name: 'OpenAI: gpt-oss-20b', +const OPENAI_GPT_4O_MINI_BATCH = { + id: 'openai/gpt-4o-mini:batch', + name: 'OpenAI: GPT-4o-mini (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', + 'prediction', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -7174,32 +7401,34 @@ const OPENAI_GPT_OSS_20B = { 'topP', ], }, - context_window: 131072, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.029, - cached: 0, + normal: 0.075, + cached: 0.0375, }, output: { - normal: 0.14, + normal: 0.3, }, }, image: 0, }, } as const -const OPENAI_GPT_OSS_20B_FREE = { - id: 'openai/gpt-oss-20b:free', - name: 'OpenAI: gpt-oss-20b (free)', +const OPENAI_GPT_4O_BATCH = { + id: 'openai/gpt-4o:batch', + name: 'OpenAI: GPT-4o (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', + 'prediction', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -7209,58 +7438,56 @@ const OPENAI_GPT_OSS_20B_FREE = { 'topP', ], }, - context_window: 131072, - max_output_tokens: 32768, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 1.25, + cached: 0.625, }, output: { - normal: 0, + normal: 5, }, }, image: 0, }, } as const -const OPENAI_GPT_OSS_SAFEGUARD_20B = { - id: 'openai/gpt-oss-safeguard-20b', - name: 'OpenAI: gpt-oss-safeguard-20b', +const OPENAI_GPT_5 = { + id: 'openai/gpt-5', + name: 'OpenAI: GPT-5', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ + 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 65536, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.075, - cached: 0.0375, + normal: 1.25, + cached: 0.125, }, output: { - normal: 0.3, + normal: 10, }, }, image: 0, }, } as const -const OPENAI_O1 = { - id: 'openai/o1', - name: 'OpenAI: o1', +const OPENAI_GPT_5_CODEX_BATCH = { + id: 'openai/gpt-5-codex:batch', + name: 'OpenAI: GPT-5 Codex (batch)', supports: { - input: ['text', 'image', 'document'], + input: ['text', 'image'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -7270,79 +7497,63 @@ const OPENAI_O1 = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, - pricing: { - text: { - input: { - normal: 15, - cached: 7.5, - }, - output: { - normal: 60, - }, - }, - image: 0, - }, -} as const -const OPENAI_O1_PRO = { - id: 'openai/o1-pro', - name: 'OpenAI: o1-pro', - supports: { - input: ['text', 'image', 'document'], - output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'responseFormat', 'seed'], - }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 150, - cached: 0, + normal: 0.625, + cached: 0.0625, }, output: { - normal: 600, + normal: 5, }, }, image: 0, }, } as const -const OPENAI_O3 = { - id: 'openai/o3', - name: 'OpenAI: o3', +const OPENAI_GPT_5_IMAGE = { + id: 'openai/gpt-5-image', + name: 'OpenAI: GPT-5 Image', supports: { input: ['image', 'text', 'document'], - output: ['text'], + output: ['image', 'text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'toolChoice', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 2, - cached: 0.5, + normal: 10, + cached: 1.25, }, output: { - normal: 8, + normal: 10, }, }, image: 0, }, } as const -const OPENAI_O3_DEEP_RESEARCH = { - id: 'openai/o3-deep-research', - name: 'OpenAI: o3 Deep Research', +const OPENAI_GPT_5_IMAGE_MINI = { + id: 'openai/gpt-5-image-mini', + name: 'OpenAI: GPT-5 Image Mini', supports: { - input: ['image', 'text', 'document'], - output: ['text'], + input: ['document', 'image', 'text'], + output: ['image', 'text'], supports: [ 'frequencyPenalty', 'logitBias', @@ -7354,33 +7565,33 @@ const OPENAI_O3_DEEP_RESEARCH = { 'seed', 'stop', 'temperature', - 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 10, - cached: 2.5, + normal: 2.5, + cached: 0.25, }, output: { - normal: 40, + normal: 2, }, }, image: 0, }, } as const -const OPENAI_O3_MINI = { - id: 'openai/o3-mini', - name: 'OpenAI: o3 Mini', +const OPENAI_GPT_5_MINI = { + id: 'openai/gpt-5-mini', + name: 'OpenAI: GPT-5 Mini', supports: { - input: ['text', 'document'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ + 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -7388,26 +7599,26 @@ const OPENAI_O3_MINI = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1.1, - cached: 0.55, + normal: 0.25, + cached: 0.025, }, output: { - normal: 4.4, + normal: 2, }, }, image: 0, }, } as const -const OPENAI_O3_MINI_HIGH = { - id: 'openai/o3-mini-high', - name: 'OpenAI: o3 Mini High', +const OPENAI_GPT_5_MINI_BATCH = { + id: 'openai/gpt-5-mini:batch', + name: 'OpenAI: GPT-5 Mini (batch)', supports: { - input: ['text', 'document'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -7417,28 +7628,29 @@ const OPENAI_O3_MINI_HIGH = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1.1, - cached: 0.55, + normal: 0.125, + cached: 0.0125, }, output: { - normal: 4.4, + normal: 1, }, }, image: 0, }, } as const -const OPENAI_O3_PRO = { - id: 'openai/o3-pro', - name: 'OpenAI: o3 Pro', +const OPENAI_GPT_5_NANO = { + id: 'openai/gpt-5-nano', + name: 'OpenAI: GPT-5 Nano', supports: { - input: ['text', 'document', 'image'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ + 'maxCompletionTokens', 'maxCompletionTokens', 'reasoning', 'responseFormat', @@ -7446,26 +7658,26 @@ const OPENAI_O3_PRO = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 20, - cached: 0, + normal: 0.05, + cached: 0.005, }, output: { - normal: 80, + normal: 0.4, }, }, image: 0, }, } as const -const OPENAI_O4_MINI = { - id: 'openai/o4-mini', - name: 'OpenAI: o4 Mini', +const OPENAI_GPT_5_NANO_BATCH = { + id: 'openai/gpt-5-nano:batch', + name: 'OpenAI: GPT-5 Nano (batch)', supports: { - input: ['image', 'text', 'document'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', @@ -7475,61 +7687,53 @@ const OPENAI_O4_MINI = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1.1, - cached: 0.275, + normal: 0.025, + cached: 0.0025, }, output: { - normal: 4.4, + normal: 0.2, }, }, image: 0, }, } as const -const OPENAI_O4_MINI_DEEP_RESEARCH = { - id: 'openai/o4-mini-deep-research', - name: 'OpenAI: o4 Mini Deep Research', +const OPENAI_GPT_5_PRO = { + id: 'openai/gpt-5-pro', + name: 'OpenAI: GPT-5 Pro', supports: { - input: ['document', 'image', 'text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 2, - cached: 0.5, + normal: 15, + cached: 0, }, output: { - normal: 8, + normal: 120, }, }, image: 0, }, } as const -const OPENAI_O4_MINI_HIGH = { - id: 'openai/o4-mini-high', - name: 'OpenAI: o4 Mini High', +const OPENAI_GPT_5_PRO_BATCH = { + id: 'openai/gpt-5-pro:batch', + name: 'OpenAI: GPT-5 Pro (batch)', supports: { input: ['image', 'text', 'document'], output: ['text'], @@ -7541,1234 +7745,1148 @@ const OPENAI_O4_MINI_HIGH = { 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 100000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1.1, - cached: 0.275, + normal: 7.5, + cached: 0, }, output: { - normal: 4.4, + normal: 60, }, }, image: 0, }, } as const -const PERCEPTRON_PERCEPTRON_MK1 = { - id: 'perceptron/perceptron-mk1', - name: 'Perceptron: Perceptron Mk1', +const OPENAI_GPT_5_BATCH = { + id: 'openai/gpt-5:batch', + name: 'OpenAI: GPT-5 (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'temperature', - 'topP', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 32768, - max_output_tokens: 8192, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.15, - cached: 0, + normal: 0.625, + cached: 0.0625, }, output: { - normal: 1.5, + normal: 5, }, }, image: 0, }, } as const -const PERPLEXITY_SONAR = { - id: 'perplexity/sonar', - name: 'Perplexity: Sonar', +const OPENAI_GPT_5_1 = { + id: 'openai/gpt-5.1', + name: 'OpenAI: GPT-5.1', supports: { - input: ['text', 'image'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'temperature', - 'topP', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 127072, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 1, - cached: 0, + normal: 1.25, + cached: 0.125, }, output: { - normal: 1, + normal: 10, }, }, image: 0, }, } as const -const PERPLEXITY_SONAR_DEEP_RESEARCH = { - id: 'perplexity/sonar-deep-research', - name: 'Perplexity: Sonar Deep Research', +const OPENAI_GPT_5_1_CODEX = { + id: 'openai/gpt-5.1-codex', + name: 'OpenAI: GPT-5.1-Codex', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'temperature', - 'topP', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 128000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 2, - cached: 0, + normal: 1.25, + cached: 0.13, }, output: { - normal: 8, + normal: 10, }, }, image: 0, }, } as const -const PERPLEXITY_SONAR_PRO = { - id: 'perplexity/sonar-pro', - name: 'Perplexity: Sonar Pro', +const OPENAI_GPT_5_1_CODEX_MAX = { + id: 'openai/gpt-5.1-codex-max', + name: 'OpenAI: GPT-5.1-Codex-Max', supports: { input: ['text', 'image'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'temperature', - 'topP', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 8000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 3, - cached: 0, + normal: 1.25, + cached: 0.125, }, output: { - normal: 15, + normal: 10, }, }, image: 0, }, } as const -const PERPLEXITY_SONAR_PRO_SEARCH = { - id: 'perplexity/sonar-pro-search', - name: 'Perplexity: Sonar Pro Search', +const OPENAI_GPT_5_1_CODEX_MINI = { + id: 'openai/gpt-5.1-codex-mini', + name: 'OpenAI: GPT-5.1-Codex-Mini', supports: { - input: ['text', 'image'], + input: ['image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'temperature', - 'topP', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 200000, - max_output_tokens: 8000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 3, - cached: 0, + normal: 0.25, + cached: 0.03, }, output: { - normal: 15, + normal: 2, }, }, image: 0, }, } as const -const PERPLEXITY_SONAR_REASONING_PRO = { - id: 'perplexity/sonar-reasoning-pro', - name: 'Perplexity: Sonar Reasoning Pro', +const OPENAI_GPT_5_1_BATCH = { + id: 'openai/gpt-5.1:batch', + name: 'OpenAI: GPT-5.1 (batch)', supports: { - input: ['text', 'image'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', - 'temperature', - 'topP', + 'responseFormat', + 'seed', + 'toolChoice', ], }, - context_window: 128000, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 2, - cached: 0, + normal: 0.625, + cached: 0.0625, }, output: { - normal: 8, + normal: 5, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_M_1 = { - id: 'poolside/laguna-m.1', - name: 'Poolside: Laguna M.1', +const OPENAI_GPT_5_2 = { + id: 'openai/gpt-5.2', + name: 'OpenAI: GPT-5.2', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'maxCompletionTokens', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.2, - cached: 0.1, + normal: 1.75, + cached: 0.175, }, output: { - normal: 0.4, + normal: 14, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_M_1_FREE = { - id: 'poolside/laguna-m.1:free', - name: 'Poolside: Laguna M.1 (free)', +const OPENAI_GPT_5_2_CHAT = { + id: 'openai/gpt-5.2-chat', + name: 'OpenAI: GPT-5.2 Chat', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: ['maxCompletionTokens', 'responseFormat', 'seed', 'toolChoice'], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 128000, + max_output_tokens: 32000, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 1.75, + cached: 0.175, }, output: { - normal: 0, + normal: 14, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_XS_2_1 = { - id: 'poolside/laguna-xs-2.1', - name: 'Poolside: Laguna XS 2.1', +const OPENAI_GPT_5_2_CODEX = { + id: 'openai/gpt-5.2-codex', + name: 'OpenAI: GPT-5.2-Codex', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.06, - cached: 0.03, + normal: 1.75, + cached: 0.175, }, output: { - normal: 0.12, + normal: 14, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_XS_2_1_FREE = { - id: 'poolside/laguna-xs-2.1:free', - name: 'Poolside: Laguna XS 2.1 (free)', +const OPENAI_GPT_5_2_PRO = { + id: 'openai/gpt-5.2-pro', + name: 'OpenAI: GPT-5.2 Pro', supports: { - input: ['text'], + input: ['image', 'text', 'document'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0, + normal: 21, cached: 0, }, output: { - normal: 0, + normal: 168, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_XS_2 = { - id: 'poolside/laguna-xs.2', - name: 'Poolside: Laguna XS.2', +const OPENAI_GPT_5_2_PRO_BATCH = { + id: 'openai/gpt-5.2-pro:batch', + name: 'OpenAI: GPT-5.2 Pro (batch)', supports: { - input: ['text'], + input: ['image', 'text', 'document'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.1, - cached: 0.05, + normal: 10.5, + cached: 0, }, output: { - normal: 0.2, + normal: 84, }, }, image: 0, }, } as const -const POOLSIDE_LAGUNA_XS_2_FREE = { - id: 'poolside/laguna-xs.2:free', - name: 'Poolside: Laguna XS.2 (free)', +const OPENAI_GPT_5_2_BATCH = { + id: 'openai/gpt-5.2:batch', + name: 'OpenAI: GPT-5.2 (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], - supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'toolChoice', + ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 0.875, + cached: 0.0875, }, output: { - normal: 0, + normal: 7, }, }, image: 0, }, } as const -const QWEN_QWEN_2_5_72B_INSTRUCT = { - id: 'qwen/qwen-2.5-72b-instruct', - name: 'Qwen2.5 72B Instruct', +const OPENAI_GPT_5_3_CODEX = { + id: 'openai/gpt-5.3-codex', + name: 'OpenAI: GPT-5.3-Codex', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.36, - cached: 0, + normal: 1.75, + cached: 0.175, }, output: { - normal: 0.4, + normal: 14, }, }, image: 0, }, } as const -const QWEN_QWEN_2_5_7B_INSTRUCT = { - id: 'qwen/qwen-2.5-7b-instruct', - name: 'Qwen: Qwen2.5 7B Instruct', +const OPENAI_GPT_5_4 = { + id: 'openai/gpt-5.4', + name: 'OpenAI: GPT-5.4', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 32768, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.04, - cached: 0, + normal: 2.5, + cached: 0.25, }, output: { - normal: 0.1, + normal: 15, }, }, image: 0, }, } as const -const QWEN_QWEN_2_5_CODER_32B_INSTRUCT = { - id: 'qwen/qwen-2.5-coder-32b-instruct', - name: 'Qwen2.5 Coder 32B Instruct', +const OPENAI_GPT_5_4_IMAGE_2 = { + id: 'openai/gpt-5.4-image-2', + name: 'OpenAI: GPT-5.4 Image 2', supports: { - input: ['text'], - output: ['text'], + input: ['image', 'text', 'document'], + output: ['image', 'text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', + 'responseFormat', 'seed', 'stop', - 'temperature', - 'topP', + 'topLogprobs', ], }, - context_window: 128000, - max_output_tokens: 32768, + context_window: 272000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.66, - cached: 0, + normal: 8, + cached: 2, }, output: { - normal: 1, + normal: 15, }, }, image: 0, }, } as const -const QWEN_QWEN_PLUS = { - id: 'qwen/qwen-plus', - name: 'Qwen: Qwen-Plus', +const OPENAI_GPT_5_4_MINI = { + id: 'openai/gpt-5.4-mini', + name: 'OpenAI: GPT-5.4 Mini', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.26, - cached: 0.377, + normal: 0.75, + cached: 0.075, }, output: { - normal: 0.78, + normal: 4.5, }, }, image: 0, }, } as const -const QWEN_QWEN_PLUS_2025_07_28 = { - id: 'qwen/qwen-plus-2025-07-28', - name: 'Qwen: Qwen Plus 0728', +const OPENAI_GPT_5_4_MINI_BATCH = { + id: 'openai/gpt-5.4-mini:batch', + name: 'OpenAI: GPT-5.4 Mini (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.26, - cached: 0, + normal: 0.375, + cached: 0.0375, }, output: { - normal: 0.78, + normal: 2.25, }, }, image: 0, }, } as const -const QWEN_QWEN_PLUS_2025_07_28_THINKING = { - id: 'qwen/qwen-plus-2025-07-28:thinking', - name: 'Qwen: Qwen Plus 0728 (thinking)', +const OPENAI_GPT_5_4_NANO = { + id: 'openai/gpt-5.4-nano', + name: 'OpenAI: GPT-5.4 Nano', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 32768, + context_window: 400000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.26, - cached: 0.325, + normal: 0.2, + cached: 0.02, }, output: { - normal: 0.78, + normal: 1.25, }, }, image: 0, }, } as const -const QWEN_QWEN2_5_VL_72B_INSTRUCT = { - id: 'qwen/qwen2.5-vl-72b-instruct', - name: 'Qwen: Qwen2.5 VL 72B Instruct', +const OPENAI_GPT_5_4_NANO_BATCH = { + id: 'openai/gpt-5.4-nano:batch', + name: 'OpenAI: GPT-5.4 Nano (batch)', supports: { - input: ['text', 'image'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', - 'topLogprobs', - 'topP', + 'toolChoice', ], }, - context_window: 131072, + context_window: 400000, max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.8, - cached: 0.4, + normal: 0.1, + cached: 0.01, }, output: { - normal: 1, + normal: 0.625, }, }, image: 0, }, } as const -const QWEN_QWEN3_14B = { - id: 'qwen/qwen3-14b', - name: 'Qwen: Qwen3 14B', +const OPENAI_GPT_5_4_PRO = { + id: 'openai/gpt-5.4-pro', + name: 'OpenAI: GPT-5.4 Pro', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131702, - max_output_tokens: 40960, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.1, + normal: 30, cached: 0, }, output: { - normal: 0.24, + normal: 180, }, }, image: 0, }, } as const -const QWEN_QWEN3_235B_A22B = { - id: 'qwen/qwen3-235b-a22b', - name: 'Qwen: Qwen3 235B A22B', +const OPENAI_GPT_5_4_PRO_BATCH = { + id: 'openai/gpt-5.4-pro:batch', + name: 'OpenAI: GPT-5.4 Pro (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 8192, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.455, + normal: 15, cached: 0, }, output: { - normal: 1.82, + normal: 90, }, }, image: 0, }, } as const -const QWEN_QWEN3_235B_A22B_2507 = { - id: 'qwen/qwen3-235b-a22b-2507', - name: 'Qwen: Qwen3 235B A22B Instruct 2507', +const OPENAI_GPT_5_4_BATCH = { + id: 'openai/gpt-5.4:batch', + name: 'OpenAI: GPT-5.4 (batch)', supports: { - input: ['text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 16384, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.09, - cached: 0, + normal: 1.25, + cached: 0.125, }, output: { - normal: 0.1, + normal: 7.5, }, }, image: 0, }, } as const -const QWEN_QWEN3_235B_A22B_THINKING_2507 = { - id: 'qwen/qwen3-235b-a22b-thinking-2507', - name: 'Qwen: Qwen3 235B A22B Thinking 2507', +const OPENAI_GPT_5_5 = { + id: 'openai/gpt-5.5', + name: 'OpenAI: GPT-5.5', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.1495, - cached: 0, + normal: 5, + cached: 0.5, }, output: { - normal: 1.495, + normal: 30, }, }, image: 0, }, } as const -const QWEN_QWEN3_30B_A3B = { - id: 'qwen/qwen3-30b-a3b', - name: 'Qwen: Qwen3 30B A3B', +const OPENAI_GPT_5_5_PRO = { + id: 'openai/gpt-5.5-pro', + name: 'OpenAI: GPT-5.5 Pro', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.12, + normal: 30, cached: 0, }, output: { - normal: 0.5, + normal: 180, }, }, image: 0, }, } as const -const QWEN_QWEN3_30B_A3B_INSTRUCT_2507 = { - id: 'qwen/qwen3-30b-a3b-instruct-2507', - name: 'Qwen: Qwen3 30B A3B Instruct 2507', +const OPENAI_GPT_5_5_PRO_BATCH = { + id: 'openai/gpt-5.5-pro:batch', + name: 'OpenAI: GPT-5.5 Pro (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 32000, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.04815, + normal: 15, cached: 0, }, output: { - normal: 0.19305, + normal: 90, }, }, image: 0, }, } as const -const QWEN_QWEN3_30B_A3B_THINKING_2507 = { - id: 'qwen/qwen3-30b-a3b-thinking-2507', - name: 'Qwen: Qwen3 30B A3B Thinking 2507', +const OPENAI_GPT_5_5_BATCH = { + id: 'openai/gpt-5.5:batch', + name: 'OpenAI: GPT-5.5 (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 32768, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.13, - cached: 0, + normal: 2.5, + cached: 0.25, }, output: { - normal: 1.56, + normal: 15, }, }, image: 0, }, } as const -const QWEN_QWEN3_32B = { - id: 'qwen/qwen3-32b', - name: 'Qwen: Qwen3 32B', +const OPENAI_GPT_5_6_LUNA = { + id: 'openai/gpt-5.6-luna', + name: 'OpenAI: GPT-5.6 Luna', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.08, - cached: 0, + normal: 0.1, + cached: 0.135, }, output: { - normal: 0.28, + normal: 0.6, }, }, image: 0, }, } as const -const QWEN_QWEN3_8B = { - id: 'qwen/qwen3-8b', - name: 'Qwen: Qwen3 8B', +const OPENAI_GPT_5_6_LUNA_PRO = { + id: 'openai/gpt-5.6-luna-pro', + name: 'OpenAI: GPT-5.6 Luna Pro', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 131072, - max_output_tokens: 8192, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.117, - cached: 0, + normal: 0.1, + cached: 0.135, }, output: { - normal: 0.455, + normal: 0.6, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER = { - id: 'qwen/qwen3-coder', - name: 'Qwen: Qwen3 Coder 480B A35B', +const OPENAI_GPT_5_6_LUNA_PRO_BATCH = { + id: 'openai/gpt-5.6-luna-pro:batch', + name: 'OpenAI: GPT-5.6 Luna Pro (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1048576, - max_output_tokens: 65536, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.22, - cached: 0, + normal: 0.1, + cached: 0.01, }, output: { - normal: 1.8, + normal: 0.6, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER_30B_A3B_INSTRUCT = { - id: 'qwen/qwen3-coder-30b-a3b-instruct', - name: 'Qwen: Qwen3 Coder 30B A3B Instruct', +const OPENAI_GPT_5_6_LUNA_BATCH = { + id: 'openai/gpt-5.6-luna:batch', + name: 'OpenAI: GPT-5.6 Luna (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 160000, - max_output_tokens: 32768, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.07, - cached: 0, + normal: 0.1, + cached: 0.01, }, output: { - normal: 0.27, + normal: 0.6, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER_FLASH = { - id: 'qwen/qwen3-coder-flash', - name: 'Qwen: Qwen3 Coder Flash', +const OPENAI_GPT_5_6_SOL = { + id: 'openai/gpt-5.6-sol', + name: 'OpenAI: GPT-5.6 Sol', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.195, - cached: 0.28275, + normal: 5, + cached: 6.75, }, output: { - normal: 0.975, + normal: 30, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER_NEXT = { - id: 'qwen/qwen3-coder-next', - name: 'Qwen: Qwen3 Coder Next', +const OPENAI_GPT_5_6_SOL_PRO = { + id: 'openai/gpt-5.6-sol-pro', + name: 'OpenAI: GPT-5.6 Sol Pro', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.11, - cached: 0.07, + normal: 5, + cached: 6.75, }, output: { - normal: 0.8, + normal: 30, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER_PLUS = { - id: 'qwen/qwen3-coder-plus', - name: 'Qwen: Qwen3 Coder Plus', +const OPENAI_GPT_5_6_SOL_PRO_BATCH = { + id: 'openai/gpt-5.6-sol-pro:batch', + name: 'OpenAI: GPT-5.6 Sol Pro (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.65, - cached: 0.9425, + normal: 2.5, + cached: 0.25, }, output: { - normal: 3.25, + normal: 15, }, }, image: 0, }, } as const -const QWEN_QWEN3_CODER_FREE = { - id: 'qwen/qwen3-coder:free', - name: 'Qwen: Qwen3 Coder 480B A35B (free)', +const OPENAI_GPT_5_6_SOL_BATCH = { + id: 'openai/gpt-5.6-sol:batch', + name: 'OpenAI: GPT-5.6 Sol (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', - 'stop', - 'temperature', + 'reasoning', + 'responseFormat', + 'seed', 'toolChoice', - 'topP', ], }, - context_window: 1048576, - max_output_tokens: 262000, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 2.5, + cached: 0.25, }, output: { - normal: 0, + normal: 15, }, }, image: 0, }, } as const -const QWEN_QWEN3_MAX = { - id: 'qwen/qwen3-max', - name: 'Qwen: Qwen3 Max', +const OPENAI_GPT_5_6_TERRA = { + id: 'openai/gpt-5.6-terra', + name: 'OpenAI: GPT-5.6 Terra', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', + 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.78, - cached: 1.131, + normal: 1, + cached: 1.35, }, output: { - normal: 3.9, + normal: 6, }, }, image: 0, }, } as const -const QWEN_QWEN3_MAX_THINKING = { - id: 'qwen/qwen3-max-thinking', - name: 'Qwen: Qwen3 Max Thinking', +const OPENAI_GPT_5_6_TERRA_PRO = { + id: 'openai/gpt-5.6-terra-pro', + name: 'OpenAI: GPT-5.6 Terra Pro', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'maxCompletionTokens', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.78, - cached: 0, + normal: 1, + cached: 1.35, }, output: { - normal: 3.9, + normal: 6, }, }, image: 0, }, } as const -const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = { - id: 'qwen/qwen3-next-80b-a3b-instruct', - name: 'Qwen: Qwen3 Next 80B A3B Instruct', +const OPENAI_GPT_5_6_TERRA_PRO_BATCH = { + id: 'openai/gpt-5.6-terra-pro:batch', + name: 'OpenAI: GPT-5.6 Terra Pro (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 16384, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0.09, - cached: 0, + normal: 1, + cached: 0.1, }, output: { - normal: 1.1, + normal: 6, }, }, image: 0, }, } as const -const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT_FREE = { - id: 'qwen/qwen3-next-80b-a3b-instruct:free', - name: 'Qwen: Qwen3 Next 80B A3B Instruct (free)', +const OPENAI_GPT_5_6_TERRA_BATCH = { + id: 'openai/gpt-5.6-terra:batch', + name: 'OpenAI: GPT-5.6 Terra (batch)', supports: { - input: ['text'], + input: ['document', 'image', 'text'], output: ['text'], supports: [ - 'frequencyPenalty', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', - 'stop', - 'temperature', + 'seed', 'toolChoice', - 'topP', ], }, - context_window: 262144, + context_window: 1050000, + max_output_tokens: 128000, pricing: { text: { input: { - normal: 0, - cached: 0, + normal: 1, + cached: 0.1, }, output: { - normal: 0, + normal: 6, }, }, image: 0, }, } as const -const QWEN_QWEN3_NEXT_80B_A3B_THINKING = { - id: 'qwen/qwen3-next-80b-a3b-thinking', - name: 'Qwen: Qwen3 Next 80B A3B Thinking', +const OPENAI_GPT_AUDIO = { + id: 'openai/gpt-audio', + name: 'OpenAI: GPT Audio', supports: { - input: ['text'], - output: ['text'], + input: ['text', 'audio'], + output: ['text', 'audio'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -8778,27 +8896,27 @@ const QWEN_QWEN3_NEXT_80B_A3B_THINKING = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 128000, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.0975, + normal: 2.5, cached: 0, }, output: { - normal: 0.78, + normal: 10, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_235B_A22B_INSTRUCT = { - id: 'qwen/qwen3-vl-235b-a22b-instruct', - name: 'Qwen: Qwen3 VL 235B A22B Instruct', +const OPENAI_GPT_AUDIO_MINI = { + id: 'openai/gpt-audio-mini', + name: 'OpenAI: GPT Audio Mini', supports: { - input: ['text', 'image'], - output: ['text'], + input: ['text', 'audio'], + output: ['text', 'audio'], supports: [ 'frequencyPenalty', 'logitBias', @@ -8814,29 +8932,53 @@ const QWEN_QWEN3_VL_235B_A22B_INSTRUCT = { 'topP', ], }, - context_window: 262144, + context_window: 128000, max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.2, - cached: 0.11, + normal: 0.6, + cached: 0, }, output: { - normal: 0.88, + normal: 2.4, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_235B_A22B_THINKING = { - id: 'qwen/qwen3-vl-235b-a22b-thinking', - name: 'Qwen: Qwen3 VL 235B A22B Thinking', +const OPENAI_GPT_CHAT_LATEST = { + id: 'openai/gpt-chat-latest', + name: 'OpenAI: GPT Chat Latest', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'document'], + output: ['text'], + supports: ['maxCompletionTokens', 'responseFormat', 'seed', 'toolChoice'], + }, + context_window: 400000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 5, + cached: 0.5, + }, + output: { + normal: 30, + }, + }, + image: 0, + }, +} as const +const OPENAI_GPT_OSS_120B = { + id: 'openai/gpt-oss-120b', + name: 'OpenAI: gpt-oss-120b', + supports: { + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -8851,25 +8993,25 @@ const QWEN_QWEN3_VL_235B_A22B_THINKING = { ], }, context_window: 131072, - max_output_tokens: 32768, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.26, - cached: 0, + normal: 0.03, + cached: 0.03, }, output: { - normal: 2.6, + normal: 0.17, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_30B_A3B_INSTRUCT = { - id: 'qwen/qwen3-vl-30b-a3b-instruct', - name: 'Qwen: Qwen3 VL 30B A3B Instruct', +const OPENAI_GPT_OSS_20B = { + id: 'openai/gpt-oss-20b', + name: 'OpenAI: gpt-oss-20b', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', @@ -8877,6 +9019,7 @@ const QWEN_QWEN3_VL_30B_A3B_INSTRUCT = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', @@ -8886,26 +9029,26 @@ const QWEN_QWEN3_VL_30B_A3B_INSTRUCT = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 131072, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.13, - cached: 0, + normal: 0.03, + cached: 0.03, }, output: { - normal: 0.52, + normal: 0.13, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_30B_A3B_THINKING = { - id: 'qwen/qwen3-vl-30b-a3b-thinking', - name: 'Qwen: Qwen3 VL 30B A3B Thinking', +const OPENAI_GPT_OSS_20B_FREE = { + id: 'openai/gpt-oss-20b:free', + name: 'OpenAI: gpt-oss-20b (free)', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', @@ -8915,6 +9058,7 @@ const QWEN_QWEN3_VL_30B_A3B_THINKING = { 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topLogprobs', @@ -8926,859 +9070,770 @@ const QWEN_QWEN3_VL_30B_A3B_THINKING = { pricing: { text: { input: { - normal: 0.13, + normal: 0, cached: 0, }, output: { - normal: 1.56, + normal: 0, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_32B_INSTRUCT = { - id: 'qwen/qwen3-vl-32b-instruct', - name: 'Qwen: Qwen3 VL 32B Instruct', +const OPENAI_GPT_OSS_SAFEGUARD_20B = { + id: 'openai/gpt-oss-safeguard-20b', + name: 'OpenAI: gpt-oss-safeguard-20b', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 32768, + context_window: 131072, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.104, - cached: 0, + normal: 0.075, + cached: 0.0375, }, output: { - normal: 0.416, + normal: 0.3, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_8B_INSTRUCT = { - id: 'qwen/qwen3-vl-8b-instruct', - name: 'Qwen: Qwen3 VL 8B Instruct', +const OPENAI_O1 = { + id: 'openai/o1', + name: 'OpenAI: o1', supports: { - input: ['image', 'text'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 256000, - max_output_tokens: 32768, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.117, - cached: 0, + normal: 15, + cached: 7.5, }, output: { - normal: 0.455, + normal: 60, }, }, image: 0, }, } as const -const QWEN_QWEN3_VL_8B_THINKING = { - id: 'qwen/qwen3-vl-8b-thinking', - name: 'Qwen: Qwen3 VL 8B Thinking', +const OPENAI_O1_PRO = { + id: 'openai/o1-pro', + name: 'OpenAI: o1-pro', supports: { - input: ['image', 'text'], + input: ['text', 'image', 'document'], output: ['text'], - supports: [ - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], + supports: ['maxCompletionTokens', 'reasoning', 'responseFormat', 'seed'], }, - context_window: 256000, - max_output_tokens: 32768, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.117, + normal: 150, cached: 0, }, output: { - normal: 1.365, + normal: 600, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_122B_A10B = { - id: 'qwen/qwen3.5-122b-a10b', - name: 'Qwen: Qwen3.5-122B-A10B', +const OPENAI_O1_PRO_BATCH = { + id: 'openai/o1-pro:batch', + name: 'OpenAI: o1-pro (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'image', 'document'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', - 'maxCompletionTokens', - 'presencePenalty', - 'reasoning', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'toolChoice', - 'topLogprobs', - 'topP', - ], + supports: ['maxCompletionTokens', 'reasoning', 'responseFormat', 'seed'], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.26, + normal: 75, cached: 0, }, output: { - normal: 2.08, + normal: 300, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_27B = { - id: 'qwen/qwen3.5-27b', - name: 'Qwen: Qwen3.5-27B', +const OPENAI_O1_BATCH = { + id: 'openai/o1:batch', + name: 'OpenAI: o1 (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'image', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.195, - cached: 0, + normal: 7.5, + cached: 3.75, }, output: { - normal: 1.56, + normal: 30, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_35B_A3B = { - id: 'qwen/qwen3.5-35b-a3b', - name: 'Qwen: Qwen3.5-35B-A3B', +const OPENAI_O3 = { + id: 'openai/o3', + name: 'OpenAI: o3', supports: { - input: ['text', 'image', 'video'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 81920, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.14, - cached: 0.05, + normal: 2, + cached: 0.5, }, output: { - normal: 1, + normal: 8, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_397B_A17B = { - id: 'qwen/qwen3.5-397b-a17b', - name: 'Qwen: Qwen3.5 397B A17B', +const OPENAI_O3_MINI = { + id: 'openai/o3-mini', + name: 'OpenAI: o3 Mini', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 256000, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.385, - cached: 0.111, + normal: 1.1, + cached: 0.55, }, output: { - normal: 2.45, + normal: 4.4, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_9B = { - id: 'qwen/qwen3.5-9b', - name: 'Qwen: Qwen3.5-9B', +const OPENAI_O3_MINI_HIGH = { + id: 'openai/o3-mini-high', + name: 'OpenAI: o3 Mini High', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.1, - cached: 0, + normal: 1.1, + cached: 0.55, }, output: { - normal: 0.15, + normal: 4.4, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_FLASH_02_23 = { - id: 'qwen/qwen3.5-flash-02-23', - name: 'Qwen: Qwen3.5-Flash', +const OPENAI_O3_MINI_HIGH_BATCH = { + id: 'openai/o3-mini-high:batch', + name: 'OpenAI: o3 Mini High (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document'], output: ['text'], supports: [ 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.065, - cached: 0, + normal: 0.55, + cached: 0.275, }, output: { - normal: 0.26, + normal: 2.2, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_PLUS_02_15 = { - id: 'qwen/qwen3.5-plus-02-15', - name: 'Qwen: Qwen3.5 Plus 2026-02-15', +const OPENAI_O3_MINI_BATCH = { + id: 'openai/o3-mini:batch', + name: 'OpenAI: o3 Mini (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.26, - cached: 0, + normal: 0.55, + cached: 0.275, }, output: { - normal: 1.56, + normal: 2.2, }, }, image: 0, }, } as const -const QWEN_QWEN3_5_PLUS_20260420 = { - id: 'qwen/qwen3.5-plus-20260420', - name: 'Qwen: Qwen3.5 Plus 2026-04-20', +const OPENAI_O3_PRO = { + id: 'openai/o3-pro', + name: 'OpenAI: o3 Pro', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document', 'image'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.3, - cached: 0.375, + normal: 20, + cached: 0, }, output: { - normal: 1.8, + normal: 80, }, }, image: 0, }, } as const -const QWEN_QWEN3_6_27B = { - id: 'qwen/qwen3.6-27b', - name: 'Qwen: Qwen3.6 27B', +const OPENAI_O3_PRO_BATCH = { + id: 'openai/o3-pro:batch', + name: 'OpenAI: o3 Pro (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['text', 'document', 'image'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 262140, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.285, - cached: 0.15, + normal: 10, + cached: 0, }, output: { - normal: 2.4, + normal: 40, }, }, image: 0, }, } as const -const QWEN_QWEN3_6_35B_A3B = { - id: 'qwen/qwen3.6-35b-a3b', - name: 'Qwen: Qwen3.6 35B A3B', +const OPENAI_O3_BATCH = { + id: 'openai/o3:batch', + name: 'OpenAI: o3 (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'stop', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.14, - cached: 0, + normal: 1, + cached: 0.25, }, output: { - normal: 1, + normal: 4, }, }, image: 0, }, } as const -const QWEN_QWEN3_6_FLASH = { - id: 'qwen/qwen3.6-flash', - name: 'Qwen: Qwen3.6 Flash', +const OPENAI_O4_MINI = { + id: 'openai/o4-mini', + name: 'OpenAI: o4 Mini', supports: { - input: ['text', 'image', 'video'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.1875, - cached: 0.234375, + normal: 1.1, + cached: 0.275, }, output: { - normal: 1.125, + normal: 4.4, }, }, image: 0, }, } as const -const QWEN_QWEN3_6_MAX_PREVIEW = { - id: 'qwen/qwen3.6-max-preview', - name: 'Qwen: Qwen3.6 Max Preview', +const OPENAI_O4_MINI_HIGH = { + id: 'openai/o4-mini-high', + name: 'OpenAI: o4 Mini High', supports: { - input: ['text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 262144, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 1.04, - cached: 1.3, + normal: 1.1, + cached: 0.275, }, output: { - normal: 6.24, + normal: 4.4, }, }, image: 0, }, } as const -const QWEN_QWEN3_6_PLUS = { - id: 'qwen/qwen3.6-plus', - name: 'Qwen: Qwen3.6 Plus', +const OPENAI_O4_MINI_HIGH_BATCH = { + id: 'openai/o4-mini-high:batch', + name: 'OpenAI: o4 Mini High (batch)', supports: { - input: ['text', 'image', 'video'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 0.325, - cached: 0.40625, + normal: 0.55, + cached: 0.1375, }, output: { - normal: 1.95, + normal: 2.2, }, }, image: 0, }, } as const -const QWEN_QWEN3_7_MAX = { - id: 'qwen/qwen3.7-max', - name: 'Qwen: Qwen3.7 Max', +const OPENAI_O4_MINI_BATCH = { + id: 'openai/o4-mini:batch', + name: 'OpenAI: o4 Mini (batch)', supports: { - input: ['text'], + input: ['image', 'text', 'document'], output: ['text'], supports: [ - 'logprobs', 'maxCompletionTokens', - 'presencePenalty', 'reasoning', 'responseFormat', 'seed', - 'temperature', 'toolChoice', - 'topLogprobs', - 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 200000, + max_output_tokens: 100000, pricing: { text: { input: { - normal: 1.25, - cached: 1.8125, + normal: 0.55, + cached: 0.1375, }, output: { - normal: 3.75, + normal: 2.2, }, }, image: 0, }, } as const -const QWEN_QWEN3_7_PLUS = { - id: 'qwen/qwen3.7-plus', - name: 'Qwen: Qwen3.7 Plus', +const PERCEPTRON_PERCEPTRON_MK1 = { + id: 'perceptron/perceptron-mk1', + name: 'Perceptron: Perceptron Mk1', supports: { - input: ['text', 'image'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ - 'logprobs', + 'frequencyPenalty', 'maxCompletionTokens', 'presencePenalty', 'reasoning', - 'responseFormat', - 'seed', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 1000000, - max_output_tokens: 65536, + context_window: 32768, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.32, - cached: 0.464, + normal: 0.15, + cached: 0, }, output: { - normal: 1.28, + normal: 1.5, }, }, image: 0, }, } as const -const REKAAI_REKA_EDGE = { - id: 'rekaai/reka-edge', - name: 'Reka Edge', +const PERPLEXITY_SONAR = { + id: 'perplexity/sonar', + name: 'Perplexity: Sonar', supports: { - input: ['image', 'text', 'video'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'seed', - 'stop', 'temperature', - 'toolChoice', - 'topLogprobs', 'topP', ], }, - context_window: 16384, - max_output_tokens: 16384, + context_window: 127072, pricing: { text: { input: { - normal: 0.1, + normal: 1, cached: 0, }, output: { - normal: 0.1, + normal: 1, }, }, image: 0, }, } as const -const REKAAI_REKA_FLASH_3 = { - id: 'rekaai/reka-flash-3', - name: 'Reka Flash 3', +const PERPLEXITY_SONAR_DEEP_RESEARCH = { + id: 'perplexity/sonar-deep-research', + name: 'Perplexity: Sonar Deep Research', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', - 'seed', - 'stop', 'temperature', - 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 65536, + context_window: 128000, pricing: { text: { input: { - normal: 0.1, + normal: 2, cached: 0, }, output: { - normal: 0.2, + normal: 8, }, }, image: 0, }, } as const -const RELACE_RELACE_APPLY_3 = { - id: 'relace/relace-apply-3', - name: 'Relace: Relace Apply 3', +const PERPLEXITY_SONAR_PRO = { + id: 'perplexity/sonar-pro', + name: 'Perplexity: Sonar Pro', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], - supports: ['maxCompletionTokens', 'seed', 'stop'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'temperature', + 'topP', + ], }, - context_window: 256000, - max_output_tokens: 128000, + context_window: 200000, + max_output_tokens: 8000, pricing: { text: { input: { - normal: 0.85, + normal: 3, cached: 0, }, output: { - normal: 1.25, + normal: 15, }, }, image: 0, }, } as const -const RELACE_RELACE_SEARCH = { - id: 'relace/relace-search', - name: 'Relace: Relace Search', +const PERPLEXITY_SONAR_PRO_SEARCH = { + id: 'perplexity/sonar-pro-search', + name: 'Perplexity: Sonar Pro Search', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ + 'frequencyPenalty', 'maxCompletionTokens', - 'responseFormat', - 'seed', - 'stop', + 'presencePenalty', + 'reasoning', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 256000, - max_output_tokens: 128000, + context_window: 200000, + max_output_tokens: 8000, pricing: { text: { input: { - normal: 1, + normal: 3, cached: 0, }, output: { - normal: 3, + normal: 15, }, }, image: 0, }, } as const -const SAKANA_FUGU_ULTRA = { - id: 'sakana/fugu-ultra', - name: 'Sakana: Fugu Ultra', +const PERPLEXITY_SONAR_REASONING_PRO = { + id: 'perplexity/sonar-reasoning-pro', + name: 'Perplexity: Sonar Reasoning Pro', supports: { input: ['text', 'image'], output: ['text'], - supports: ['reasoning', 'toolChoice'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'temperature', + 'topP', + ], }, - context_window: 1000000, - max_output_tokens: 128000, + context_window: 128000, pricing: { text: { input: { - normal: 5, - cached: 0.5, + normal: 2, + cached: 0, }, output: { - normal: 30, + normal: 8, }, }, image: 0, }, } as const -const SAO10K_L3_LUNARIS_8B = { - id: 'sao10k/l3-lunaris-8b', - name: 'Sao10K: Llama 3 8B Lunaris', +const POOLSIDE_LAGUNA_S_2_1 = { + id: 'poolside/laguna-s-2.1', + name: 'Poolside: Laguna S 2.1', supports: { input: ['text'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'responseFormat', - 'seed', - 'stop', - 'temperature', - 'topP', - ], + supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], }, - context_window: 8192, - max_output_tokens: 16384, + context_window: 1048576, + max_output_tokens: 131072, pricing: { text: { input: { - normal: 0.04, + normal: 0.09, + cached: 0.009, + }, + output: { + normal: 0.18, + }, + }, + image: 0, + }, +} as const +const POOLSIDE_LAGUNA_S_2_1_FREE = { + id: 'poolside/laguna-s-2.1:free', + name: 'Poolside: Laguna S 2.1 (free)', + supports: { + input: ['text'], + output: ['text'], + supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + }, + context_window: 262144, + max_output_tokens: 32768, + pricing: { + text: { + input: { + normal: 0, cached: 0, }, output: { - normal: 0.05, + normal: 0, }, }, image: 0, }, } as const -const SAO10K_L3_1_70B_HANAMI_X1 = { - id: 'sao10k/l3.1-70b-hanami-x1', - name: 'Sao10K: Llama 3.1 70B Hanami x1', +const POOLSIDE_LAGUNA_XS_2_1 = { + id: 'poolside/laguna-xs-2.1', + name: 'Poolside: Laguna XS 2.1', supports: { input: ['text'], output: ['text'], - supports: [ - 'frequencyPenalty', - 'logitBias', - 'maxCompletionTokens', - 'presencePenalty', - 'seed', - 'stop', - 'temperature', - 'topP', - ], + supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], }, - context_window: 16000, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 3, + normal: 0.06, + cached: 0.03, + }, + output: { + normal: 0.12, + }, + }, + image: 0, + }, +} as const +const POOLSIDE_LAGUNA_XS_2_1_FREE = { + id: 'poolside/laguna-xs-2.1:free', + name: 'Poolside: Laguna XS 2.1 (free)', + supports: { + input: ['text'], + output: ['text'], + supports: ['maxCompletionTokens', 'reasoning', 'temperature', 'toolChoice'], + }, + context_window: 262144, + max_output_tokens: 32768, + pricing: { + text: { + input: { + normal: 0, cached: 0, }, output: { - normal: 3, + normal: 0, }, }, image: 0, }, } as const -const SAO10K_L3_1_EURYALE_70B = { - id: 'sao10k/l3.1-euryale-70b', - name: 'Sao10K: Llama 3.1 Euryale 70B v2.2', +const QWEN_QWEN_2_5_72B_INSTRUCT = { + id: 'qwen/qwen-2.5-72b-instruct', + name: 'Qwen2.5 72B Instruct', supports: { input: ['text'], output: ['text'], @@ -9795,98 +9850,98 @@ const SAO10K_L3_1_EURYALE_70B = { 'topP', ], }, - context_window: 131072, + context_window: 32768, max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.85, + normal: 0.36, cached: 0, }, output: { - normal: 0.85, + normal: 0.4, }, }, image: 0, }, } as const -const SAO10K_L3_3_EURYALE_70B = { - id: 'sao10k/l3.3-euryale-70b', - name: 'Sao10K: Llama 3.3 Euryale 70B', +const QWEN_QWEN_2_5_7B_INSTRUCT = { + id: 'qwen/qwen-2.5-7b-instruct', + name: 'Qwen: Qwen2.5 7B Instruct', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logprobs', + 'logitBias', 'maxCompletionTokens', 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 131072, - max_output_tokens: 16384, + context_window: 32768, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.65, + normal: 0.1, cached: 0, }, output: { - normal: 0.75, + normal: 0.2, }, }, image: 0, }, } as const -const STEPFUN_STEP_3_5_FLASH = { - id: 'stepfun/step-3.5-flash', - name: 'StepFun: Step 3.5 Flash', +const QWEN_QWEN_2_5_CODER_32B_INSTRUCT = { + id: 'qwen/qwen-2.5-coder-32b-instruct', + name: 'Qwen2.5 Coder 32B Instruct', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', + 'seed', + 'stop', 'temperature', - 'toolChoice', 'topP', ], }, - context_window: 262144, - max_output_tokens: 65536, + context_window: 32768, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.1, + normal: 0.66, cached: 0, }, output: { - normal: 0.3, + normal: 1, }, }, image: 0, }, } as const -const STEPFUN_STEP_3_7_FLASH = { - id: 'stepfun/step-3.7-flash', - name: 'StepFun: Step 3.7 Flash', +const QWEN_QWEN_PLUS = { + id: 'qwen/qwen-plus', + name: 'Qwen: Qwen-Plus', supports: { - input: ['text', 'image', 'video'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -9896,150 +9951,166 @@ const STEPFUN_STEP_3_7_FLASH = { 'topP', ], }, - context_window: 256000, - max_output_tokens: 256000, + context_window: 1000000, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.2, - cached: 0.04, + normal: 0.26, + cached: 0.377, }, output: { - normal: 1.15, + normal: 0.78, }, }, image: 0, }, } as const -const SWITCHPOINT_ROUTER = { - id: 'switchpoint/router', - name: 'Switchpoint Router', +const QWEN_QWEN_PLUS_2025_07_28 = { + id: 'qwen/qwen-plus-2025-07-28', + name: 'Qwen: Qwen Plus 0728', supports: { input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, + context_window: 1000000, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.85, + normal: 0.26, cached: 0, }, output: { - normal: 3.4, + normal: 0.78, }, }, image: 0, }, } as const -const TENCENT_HUNYUAN_A13B_INSTRUCT = { - id: 'tencent/hunyuan-a13b-instruct', - name: 'Tencent: Hunyuan A13B Instruct', +const QWEN_QWEN_PLUS_2025_07_28_THINKING = { + id: 'qwen/qwen-plus-2025-07-28:thinking', + name: 'Qwen: Qwen Plus 0728 (thinking)', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', + 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 1000000, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.14, + normal: 0.26, cached: 0, }, output: { - normal: 0.57, + normal: 0.78, }, }, image: 0, }, } as const -const TENCENT_HY3 = { - id: 'tencent/hy3', - name: 'Tencent: Hy3', +const QWEN_QWEN2_5_VL_72B_INSTRUCT = { + id: 'qwen/qwen2.5-vl-72b-instruct', + name: 'Qwen: Qwen2.5 VL 72B Instruct', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', - 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 262144, - max_output_tokens: 131072, + context_window: 128000, pricing: { text: { input: { - normal: 0.2, - cached: 0.5, + normal: 0.25, + cached: 0, }, output: { - normal: 0.8, + normal: 0.75, }, }, image: 0, }, } as const -const TENCENT_HY3_PREVIEW = { - id: 'tencent/hy3-preview', - name: 'Tencent: Hy3 preview', +const QWEN_QWEN3_14B = { + id: 'qwen/qwen3-14b', + name: 'Qwen: Qwen3 14B', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 262144, + context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.063, - cached: 0.021, + normal: 0.12, + cached: 0, }, output: { - normal: 0.21, + normal: 0.24, }, }, image: 0, }, } as const -const TENCENT_HY3_FREE = { - id: 'tencent/hy3:free', - name: 'Tencent: Hy3 (free)', +const QWEN_QWEN3_235B_A22B = { + id: 'qwen/qwen3-235b-a22b', + name: 'Qwen: Qwen3 235B A22B', supports: { input: ['text'], output: ['text'], @@ -10048,6 +10119,7 @@ const TENCENT_HY3_FREE = { 'maxCompletionTokens', 'presencePenalty', 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', @@ -10055,24 +10127,24 @@ const TENCENT_HY3_FREE = { 'topP', ], }, - context_window: 262144, - max_output_tokens: 262144, + context_window: 131072, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0, + normal: 0.455, cached: 0, }, output: { - normal: 0, + normal: 1.82, }, }, image: 0, }, } as const -const THEDRUMMER_CYDONIA_24B_V4_1 = { - id: 'thedrummer/cydonia-24b-v4.1', - name: 'TheDrummer: Cydonia 24B V4.1', +const QWEN_QWEN3_235B_A22B_2507 = { + id: 'qwen/qwen3-235b-a22b-2507', + name: 'Qwen: Qwen3 235B A22B Instruct 2507', supports: { input: ['text'], output: ['text'], @@ -10086,28 +10158,29 @@ const THEDRUMMER_CYDONIA_24B_V4_1 = { 'seed', 'stop', 'temperature', + 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.3, - cached: 0.15, + normal: 0.09, + cached: 0, }, output: { - normal: 0.5, + normal: 0.55, }, }, image: 0, }, } as const -const THEDRUMMER_ROCINANTE_12B = { - id: 'thedrummer/rocinante-12b', - name: 'TheDrummer: Rocinante 12B', +const QWEN_QWEN3_235B_A22B_THINKING_2507 = { + id: 'qwen/qwen3-235b-a22b-thinking-2507', + name: 'Qwen: Qwen3 235B A22B Thinking 2507', supports: { input: ['text'], output: ['text'], @@ -10117,72 +10190,74 @@ const THEDRUMMER_ROCINANTE_12B = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', + 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 65536, + context_window: 262144, pricing: { text: { input: { - normal: 0.25, + normal: 0.23, cached: 0, }, output: { - normal: 0.5, + normal: 2.3, }, }, image: 0, }, } as const -const THEDRUMMER_SKYFALL_36B_V2 = { - id: 'thedrummer/skyfall-36b-v2', - name: 'TheDrummer: Skyfall 36B V2', +const QWEN_QWEN3_30B_A3B = { + id: 'qwen/qwen3-30b-a3b', + name: 'Qwen: Qwen3 30B A3B', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 32768, - max_output_tokens: 32768, + context_window: 131072, + max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.55, - cached: 0.25, + normal: 0.13, + cached: 0, }, output: { - normal: 0.8, + normal: 0.52, }, }, image: 0, }, } as const -const THEDRUMMER_UNSLOPNEMO_12B = { - id: 'thedrummer/unslopnemo-12b', - name: 'TheDrummer: UnslopNemo 12B', +const QWEN_QWEN3_30B_A3B_INSTRUCT_2507 = { + id: 'qwen/qwen3-30b-a3b-instruct-2507', + name: 'Qwen: Qwen3 30B A3B Instruct 2507', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -10195,182 +10270,208 @@ const THEDRUMMER_UNSLOPNEMO_12B = { 'topP', ], }, - context_window: 32768, - max_output_tokens: 32768, + context_window: 262144, + max_output_tokens: 32000, pricing: { text: { input: { - normal: 0.4, + normal: 0.04815, cached: 0, }, output: { - normal: 0.4, + normal: 0.19305, }, }, image: 0, }, } as const -const UNDI95_REMM_SLERP_L2_13B = { - id: 'undi95/remm-slerp-l2-13b', - name: 'ReMM SLERP 13B', +const QWEN_QWEN3_30B_A3B_THINKING_2507 = { + id: 'qwen/qwen3-30b-a3b-thinking-2507', + name: 'Qwen: Qwen3 30B A3B Thinking 2507', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', - 'logprobs', 'maxCompletionTokens', 'presencePenalty', + 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', - 'topLogprobs', + 'toolChoice', 'topP', ], }, - context_window: 6144, - max_output_tokens: 4096, + context_window: 81920, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.45, + normal: 0.2, cached: 0, }, output: { - normal: 0.65, + normal: 2.4, }, }, image: 0, }, } as const -const UPSTAGE_SOLAR_PRO_3 = { - id: 'upstage/solar-pro-3', - name: 'Upstage: Solar Pro 3', +const QWEN_QWEN3_32B = { + id: 'qwen/qwen3-32b', + name: 'Qwen: Qwen3 32B', supports: { input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', + 'topLogprobs', + 'topP', ], }, - context_window: 128000, + context_window: 131072, + max_output_tokens: 16384, pricing: { text: { input: { - normal: 0.15, - cached: 0.015, + normal: 0.08, + cached: 0, }, output: { - normal: 0.6, + normal: 0.28, }, }, image: 0, }, } as const -const WRITER_PALMYRA_X5 = { - id: 'writer/palmyra-x5', - name: 'Writer: Palmyra X5', +const QWEN_QWEN3_8B = { + id: 'qwen/qwen3-8b', + name: 'Qwen: Qwen3 8B', supports: { input: ['text'], output: ['text'], - supports: ['maxCompletionTokens', 'stop', 'temperature', 'topP'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], }, - context_window: 1040000, + context_window: 131072, max_output_tokens: 8192, pricing: { text: { input: { - normal: 0.6, + normal: 0.117, cached: 0, }, output: { - normal: 6, + normal: 0.455, }, }, image: 0, }, } as const -const X_AI_GROK_4_20 = { - id: 'x-ai/grok-4.20', - name: 'xAI: Grok 4.20', +const QWEN_QWEN3_CODER = { + id: 'qwen/qwen3-coder', + name: 'Qwen: Qwen3 Coder 480B A35B', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', 'temperature', 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 2000000, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 1.25, - cached: 0.2, + normal: 0.3, + cached: 0.1, }, output: { - normal: 2.5, + normal: 1, }, }, image: 0, }, } as const -const X_AI_GROK_4_20_MULTI_AGENT = { - id: 'x-ai/grok-4.20-multi-agent', - name: 'xAI: Grok 4.20 Multi-Agent', +const QWEN_QWEN3_CODER_30B_A3B_INSTRUCT = { + id: 'qwen/qwen3-coder-30b-a3b-instruct', + name: 'Qwen: Qwen3 Coder 30B A3B Instruct', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', 'logprobs', 'maxCompletionTokens', - 'reasoning', + 'presencePenalty', 'responseFormat', 'seed', + 'stop', 'temperature', + 'toolChoice', 'topLogprobs', 'topP', ], }, - context_window: 2000000, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 1.25, - cached: 0.2, + normal: 0.07, + cached: 0, }, output: { - normal: 2.5, + normal: 0.28, }, }, image: 0, }, } as const -const X_AI_GROK_4_3 = { - id: 'x-ai/grok-4.3', - name: 'xAI: Grok 4.3', +const QWEN_QWEN3_CODER_FLASH = { + id: 'qwen/qwen3-coder-flash', + name: 'Qwen: Qwen3 Coder Flash', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10381,31 +10482,32 @@ const X_AI_GROK_4_3 = { ], }, context_window: 1000000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 1.25, - cached: 0.2, + normal: 0.195, + cached: 0.28275, }, output: { - normal: 2.5, + normal: 0.975, }, }, image: 0, }, } as const -const X_AI_GROK_BUILD_0_1 = { - id: 'x-ai/grok-build-0.1', - name: 'xAI: Grok Build 0.1', +const QWEN_QWEN3_CODER_NEXT = { + id: 'qwen/qwen3-coder-next', + name: 'Qwen: Qwen3 Coder Next', supports: { - input: ['text', 'image', 'document'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10415,33 +10517,32 @@ const X_AI_GROK_BUILD_0_1 = { 'topP', ], }, - context_window: 256000, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 1, - cached: 0.2, + normal: 0.12, + cached: 0.07, }, output: { - normal: 2, + normal: 0.8, }, }, image: 0, }, } as const -const XIAOMI_MIMO_V2_5 = { - id: 'xiaomi/mimo-v2.5', - name: 'Xiaomi: MiMo-V2.5', +const QWEN_QWEN3_CODER_PLUS = { + id: 'qwen/qwen3-coder-plus', + name: 'Qwen: Qwen3 Coder Plus', supports: { - input: ['text', 'audio', 'image', 'video'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10451,33 +10552,32 @@ const XIAOMI_MIMO_V2_5 = { 'topP', ], }, - context_window: 1048576, + context_window: 1000000, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.105, - cached: 0.028, + normal: 0.65, + cached: 0.9425, }, output: { - normal: 0.28, + normal: 3.25, }, }, image: 0, }, } as const -const XIAOMI_MIMO_V2_5_PRO = { - id: 'xiaomi/mimo-v2.5-pro', - name: 'Xiaomi: MiMo-V2.5-Pro', +const QWEN_QWEN3_MAX = { + id: 'qwen/qwen3-max', + name: 'Qwen: Qwen3 Max', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10487,92 +10587,103 @@ const XIAOMI_MIMO_V2_5_PRO = { 'topP', ], }, - context_window: 1048576, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.435, - cached: 0.0036, + normal: 0.78, + cached: 1.131, }, output: { - normal: 0.87, + normal: 3.9, }, }, image: 0, }, } as const -const Z_AI_GLM_4_5 = { - id: 'z-ai/glm-4.5', - name: 'Z.ai: GLM 4.5', +const QWEN_QWEN3_MAX_THINKING = { + id: 'qwen/qwen3-max-thinking', + name: 'Qwen: Qwen3 Max Thinking', supports: { input: ['text'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 98304, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.6, - cached: 0.11, + normal: 0.78, + cached: 0, }, output: { - normal: 2.2, + normal: 3.9, }, }, image: 0, }, } as const -const Z_AI_GLM_4_5_AIR = { - id: 'z-ai/glm-4.5-air', - name: 'Z.ai: GLM 4.5 Air', +const QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT = { + id: 'qwen/qwen3-next-80b-a3b-instruct', + name: 'Qwen: Qwen3 Next 80B A3B Instruct', supports: { input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', + 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 131072, - max_output_tokens: 98304, + context_window: 262144, + max_output_tokens: 262144, pricing: { text: { input: { - normal: 0.13, - cached: 0.025, + normal: 0.1, + cached: 0.07, }, output: { - normal: 0.85, + normal: 1.1, }, }, image: 0, }, } as const -const Z_AI_GLM_4_5V = { - id: 'z-ai/glm-4.5v', - name: 'Z.ai: GLM 4.5V', +const QWEN_QWEN3_NEXT_80B_A3B_THINKING = { + id: 'qwen/qwen3-next-80b-a3b-thinking', + name: 'Qwen: Qwen3 Next 80B A3B Thinking', supports: { - input: ['text', 'image'], + input: ['text'], output: ['text'], supports: [ 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -10581,67 +10692,70 @@ const Z_AI_GLM_4_5V = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 65536, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.6, - cached: 0.11, + normal: 0.15, + cached: 0, }, output: { - normal: 1.8, + normal: 1.2, }, }, image: 0, }, } as const -const Z_AI_GLM_4_6 = { - id: 'z-ai/glm-4.6', - name: 'Z.ai: GLM 4.6', +const QWEN_QWEN3_VL_235B_A22B_INSTRUCT = { + id: 'qwen/qwen3-vl-235b-a22b-instruct', + name: 'Qwen: Qwen3 VL 235B A22B Instruct', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 202752, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.43, - cached: 0.08, + normal: 0.26, + cached: 0, }, output: { - normal: 1.74, + normal: 1.04, }, }, image: 0, }, } as const -const Z_AI_GLM_4_6V = { - id: 'z-ai/glm-4.6v', - name: 'Z.ai: GLM 4.6V', +const QWEN_QWEN3_VL_235B_A22B_THINKING = { + id: 'qwen/qwen3-vl-235b-a22b-thinking', + name: 'Qwen: Qwen3 VL 235B A22B Thinking', supports: { - input: ['image', 'text', 'video'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', 'reasoning', @@ -10650,6 +10764,7 @@ const Z_AI_GLM_4_6V = { 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, @@ -10658,21 +10773,21 @@ const Z_AI_GLM_4_6V = { pricing: { text: { input: { - normal: 0.3, - cached: 0.055, + normal: 0.4, + cached: 0, }, output: { - normal: 0.9, + normal: 4, }, }, image: 0, }, } as const -const Z_AI_GLM_4_7 = { - id: 'z-ai/glm-4.7', - name: 'Z.ai: GLM 4.7', +const QWEN_QWEN3_VL_30B_A3B_INSTRUCT = { + id: 'qwen/qwen3-vl-30b-a3b-instruct', + name: 'Qwen: Qwen3 VL 30B A3B Instruct', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', @@ -10680,7 +10795,6 @@ const Z_AI_GLM_4_7 = { 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10690,30 +10804,29 @@ const Z_AI_GLM_4_7 = { 'topP', ], }, - context_window: 202752, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.4, - cached: 0.08, + normal: 0.13, + cached: 0, }, output: { - normal: 1.75, + normal: 0.52, }, }, image: 0, }, } as const -const Z_AI_GLM_4_7_FLASH = { - id: 'z-ai/glm-4.7-flash', - name: 'Z.ai: GLM 4.7 Flash', +const QWEN_QWEN3_VL_30B_A3B_THINKING = { + id: 'qwen/qwen3-vl-30b-a3b-thinking', + name: 'Qwen: Qwen3 VL 30B A3B Thinking', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', @@ -10727,34 +10840,32 @@ const Z_AI_GLM_4_7_FLASH = { 'topP', ], }, - context_window: 202752, - max_output_tokens: 16384, + context_window: 262144, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.06, - cached: 0.01, + normal: 0.2, + cached: 0, }, output: { - normal: 0.4, + normal: 2.4, }, }, image: 0, }, } as const -const Z_AI_GLM_5 = { - id: 'z-ai/glm-5', - name: 'Z.ai: GLM 5', +const QWEN_QWEN3_VL_32B_INSTRUCT = { + id: 'qwen/qwen3-vl-32b-instruct', + name: 'Qwen: Qwen3 VL 32B Instruct', supports: { - input: ['text'], + input: ['text', 'image'], output: ['text'], supports: [ 'frequencyPenalty', - 'logitBias', 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', @@ -10764,60 +10875,98 @@ const Z_AI_GLM_5 = { 'topP', ], }, - context_window: 202752, + context_window: 131072, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 0.6, - cached: 0.12, + normal: 0.104, + cached: 0, }, output: { - normal: 1.92, + normal: 0.416, }, }, image: 0, }, } as const -const Z_AI_GLM_5_TURBO = { - id: 'z-ai/glm-5-turbo', - name: 'Z.ai: GLM 5 Turbo', +const QWEN_QWEN3_VL_8B_INSTRUCT = { + id: 'qwen/qwen3-vl-8b-instruct', + name: 'Qwen: Qwen3 VL 8B Instruct', supports: { - input: ['text'], + input: ['image', 'text'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', + 'logprobs', 'maxCompletionTokens', 'presencePenalty', - 'reasoning', 'responseFormat', 'seed', 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, context_window: 262144, - max_output_tokens: 131072, + max_output_tokens: 32768, pricing: { text: { input: { - normal: 1.2, - cached: 0.24, + normal: 0.117, + cached: 0, }, output: { - normal: 4, + normal: 0.455, }, }, image: 0, }, } as const -const Z_AI_GLM_5_1 = { - id: 'z-ai/glm-5.1', - name: 'Z.ai: GLM 5.1', +const QWEN_QWEN3_VL_8B_THINKING = { + id: 'qwen/qwen3-vl-8b-thinking', + name: 'Qwen: Qwen3 VL 8B Thinking', supports: { - input: ['text'], + input: ['image', 'text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 32768, + pricing: { + text: { + input: { + normal: 0.18, + cached: 0, + }, + output: { + normal: 2.1, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_5_122B_A10B = { + id: 'qwen/qwen3.5-122b-a10b', + name: 'Qwen: Qwen3.5-122B-A10B', + supports: { + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', @@ -10835,33 +10984,32 @@ const Z_AI_GLM_5_1 = { 'topP', ], }, - context_window: 202752, - max_output_tokens: 128000, + context_window: 262144, + max_output_tokens: 81920, pricing: { text: { input: { - normal: 0.966, - cached: 0.1794, + normal: 0.29, + cached: 0, }, output: { - normal: 3.036, + normal: 2.4, }, }, image: 0, }, } as const -const Z_AI_GLM_5_2 = { - id: 'z-ai/glm-5.2', - name: 'Z.ai: GLM 5.2', +const QWEN_QWEN3_5_27B = { + id: 'qwen/qwen3.5-27b', + name: 'Qwen: Qwen3.5-27B', supports: { - input: ['text'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ 'frequencyPenalty', 'logitBias', 'logprobs', 'maxCompletionTokens', - 'parallelToolCalls', 'presencePenalty', 'reasoning', 'responseFormat', @@ -10873,64 +11021,2615 @@ const Z_AI_GLM_5_2 = { 'topP', ], }, - context_window: 1048576, - max_output_tokens: 32768, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 0.93, - cached: 0.18, + normal: 0.195, + cached: 0, }, output: { - normal: 3, + normal: 1.56, }, }, image: 0, }, } as const -const Z_AI_GLM_5V_TURBO = { - id: 'z-ai/glm-5v-turbo', - name: 'Z.ai: GLM 5V Turbo', +const QWEN_QWEN3_5_35B_A3B = { + id: 'qwen/qwen3.5-35b-a3b', + name: 'Qwen: Qwen3.5-35B-A3B', supports: { - input: ['image', 'text', 'video'], + input: ['text', 'image', 'video'], output: ['text'], supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', 'maxCompletionTokens', + 'presencePenalty', 'reasoning', 'responseFormat', + 'seed', + 'stop', 'temperature', 'toolChoice', + 'topLogprobs', 'topP', ], }, - context_window: 202752, - max_output_tokens: 131072, + context_window: 262144, + max_output_tokens: 65536, pricing: { text: { input: { - normal: 1.2, - cached: 0.24, + normal: 0.225, + cached: 0.225, }, output: { - normal: 4, + normal: 1.8, }, }, image: 0, }, } as const - -export type OpenRouterModelOptionsByName = { - [_ANTHROPIC_CLAUDE_FABLE_LATEST.id]: OpenRouterCommonOptions & +const QWEN_QWEN3_5_397B_A17B = { + id: 'qwen/qwen3.5-397b-a17b', + name: 'Qwen: Qwen3.5 397B A17B', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.39, + cached: 0, + }, + output: { + normal: 2.34, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_5_9B = { + id: 'qwen/qwen3.5-9b', + name: 'Qwen: Qwen3.5-9B', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 262144, + pricing: { + text: { + input: { + normal: 0.1, + cached: 0, + }, + output: { + normal: 0.15, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_5_FLASH_02_23 = { + id: 'qwen/qwen3.5-flash-02-23', + name: 'Qwen: Qwen3.5-Flash', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.065, + cached: 0, + }, + output: { + normal: 0.26, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_5_PLUS_02_15 = { + id: 'qwen/qwen3.5-plus-02-15', + name: 'Qwen: Qwen3.5 Plus 2026-02-15', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.26, + cached: 0, + }, + output: { + normal: 1.56, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_5_PLUS_20260420 = { + id: 'qwen/qwen3.5-plus-20260420', + name: 'Qwen: Qwen3.5 Plus 2026-04-20', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.3, + cached: 0.375, + }, + output: { + normal: 1.8, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_6_27B = { + id: 'qwen/qwen3.6-27b', + name: 'Qwen: Qwen3.6 27B', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.3, + cached: 0.03, + }, + output: { + normal: 2, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_6_35B_A3B = { + id: 'qwen/qwen3.6-35b-a3b', + name: 'Qwen: Qwen3.6 35B A3B', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 262144, + pricing: { + text: { + input: { + normal: 0.15, + cached: 0.05, + }, + output: { + normal: 1, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_6_FLASH = { + id: 'qwen/qwen3.6-flash', + name: 'Qwen: Qwen3.6 Flash', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.1875, + cached: 0.234375, + }, + output: { + normal: 1.125, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_6_MAX_PREVIEW = { + id: 'qwen/qwen3.6-max-preview', + name: 'Qwen: Qwen3.6 Max Preview', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 1.027, + cached: 1.28375, + }, + output: { + normal: 6.162, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_6_PLUS = { + id: 'qwen/qwen3.6-plus', + name: 'Qwen: Qwen3.6 Plus', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.325, + cached: 0.40625, + }, + output: { + normal: 1.95, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_7_FLASH = { + id: 'qwen/qwen3.7-flash', + name: 'Qwen: Qwen3.7 Flash', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.03, + cached: 0.044, + }, + output: { + normal: 0.13, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_7_MAX = { + id: 'qwen/qwen3.7-max', + name: 'Qwen: Qwen3.7 Max', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 1.475, + cached: 2.13875, + }, + output: { + normal: 4.425, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_7_PLUS = { + id: 'qwen/qwen3.7-plus', + name: 'Qwen: Qwen3.7 Plus', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.32, + cached: 0.464, + }, + output: { + normal: 1.28, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_8_2_4T_A95B = { + id: 'qwen/qwen3.8-2.4t-a95b', + name: 'Qwen: Qwen3.8 2.4T A95B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 262144, + pricing: { + text: { + input: { + normal: 2, + cached: 0.25, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_8_27B = { + id: 'qwen/qwen3.8-27b', + name: 'Qwen: Qwen3.8 27B', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.45, + cached: 0, + }, + output: { + normal: 3.2, + }, + }, + image: 0, + }, +} as const +const QWEN_QWEN3_8_MAX = { + id: 'qwen/qwen3.8-max', + name: 'Qwen: Qwen3.8 Max', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 2, + cached: 2.75, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const +const REKAAI_REKA_EDGE = { + id: 'rekaai/reka-edge', + name: 'Reka Edge', + supports: { + input: ['image', 'text', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 16384, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.1, + cached: 0, + }, + output: { + normal: 0.1, + }, + }, + image: 0, + }, +} as const +const REKAAI_REKA_FLASH_3 = { + id: 'rekaai/reka-flash-3', + name: 'Reka Flash 3', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 65536, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.1, + cached: 0, + }, + output: { + normal: 0.2, + }, + }, + image: 0, + }, +} as const +const RELACE_RELACE_APPLY_3 = { + id: 'relace/relace-apply-3', + name: 'Relace: Relace Apply 3', + supports: { + input: ['text'], + output: ['text'], + supports: ['maxCompletionTokens', 'seed', 'stop'], + }, + context_window: 256000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.85, + cached: 0, + }, + output: { + normal: 1.25, + }, + }, + image: 0, + }, +} as const +const RELACE_RELACE_SEARCH = { + id: 'relace/relace-search', + name: 'Relace: Relace Search', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 256000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 1, + cached: 0, + }, + output: { + normal: 3, + }, + }, + image: 0, + }, +} as const +const SAKANA_FUGU_ULTRA = { + id: 'sakana/fugu-ultra', + name: 'Sakana: Fugu Ultra', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: ['reasoning', 'toolChoice'], + }, + context_window: 1000000, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 5, + cached: 0.5, + }, + output: { + normal: 30, + }, + }, + image: 0, + }, +} as const +const SAKANA_SAKANA_NAMAZU = { + id: 'sakana/sakana-namazu', + name: 'Sakana: Sakana Namazu', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: ['reasoning', 'toolChoice'], + }, + context_window: 262144, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.95, + cached: 0.15, + }, + output: { + normal: 4, + }, + }, + image: 0, + }, +} as const +const SAO10K_L3_LUNARIS_8B = { + id: 'sao10k/l3-lunaris-8b', + name: 'Sao10K: Llama 3 8B Lunaris', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 8192, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.04, + cached: 0, + }, + output: { + normal: 0.05, + }, + }, + image: 0, + }, +} as const +const SAO10K_L3_1_EURYALE_70B = { + id: 'sao10k/l3.1-euryale-70b', + name: 'Sao10K: Llama 3.1 Euryale 70B v2.2', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.85, + cached: 0, + }, + output: { + normal: 0.85, + }, + }, + image: 0, + }, +} as const +const SAO10K_L3_3_EURYALE_70B = { + id: 'sao10k/l3.3-euryale-70b', + name: 'Sao10K: Llama 3.3 Euryale 70B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.65, + cached: 0, + }, + output: { + normal: 0.75, + }, + }, + image: 0, + }, +} as const +const STEPFUN_STEP_3_5_FLASH = { + id: 'stepfun/step-3.5-flash', + name: 'StepFun: Step 3.5 Flash', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'reasoning', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.1, + cached: 0, + }, + output: { + normal: 0.3, + }, + }, + image: 0, + }, +} as const +const STEPFUN_STEP_3_7_FLASH = { + id: 'stepfun/step-3.7-flash', + name: 'StepFun: Step 3.7 Flash', + supports: { + input: ['text', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 256000, + pricing: { + text: { + input: { + normal: 0.2, + cached: 0.04, + }, + output: { + normal: 1.15, + }, + }, + image: 0, + }, +} as const +const TENCENT_HUNYUAN_A13B_INSTRUCT = { + id: 'tencent/hunyuan-a13b-instruct', + name: 'Tencent: Hunyuan A13B Instruct', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.14, + cached: 0, + }, + output: { + normal: 0.57, + }, + }, + image: 0, + }, +} as const +const TENCENT_HY3 = { + id: 'tencent/hy3', + name: 'Tencent: Hy3', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 262144, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.132, + cached: 0.033, + }, + output: { + normal: 0.528, + }, + }, + image: 0, + }, +} as const +const TENCENT_HY3_PREVIEW = { + id: 'tencent/hy3-preview', + name: 'Tencent: Hy3 preview', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'seed', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 262144, + pricing: { + text: { + input: { + normal: 0.18, + cached: 0.06, + }, + output: { + normal: 0.6, + }, + }, + image: 0, + }, +} as const +const THEDRUMMER_CYDONIA_24B_V4_1 = { + id: 'thedrummer/cydonia-24b-v4.1', + name: 'TheDrummer: Cydonia 24B V4.1', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.3, + cached: 0.15, + }, + output: { + normal: 0.5, + }, + }, + image: 0, + }, +} as const +const THEDRUMMER_ROCINANTE_12B = { + id: 'thedrummer/rocinante-12b', + name: 'TheDrummer: Rocinante 12B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 65536, + max_output_tokens: 65536, + pricing: { + text: { + input: { + normal: 0.25, + cached: 0, + }, + output: { + normal: 0.5, + }, + }, + image: 0, + }, +} as const +const THEDRUMMER_SKYFALL_36B_V2 = { + id: 'thedrummer/skyfall-36b-v2', + name: 'TheDrummer: Skyfall 36B V2', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 32768, + max_output_tokens: 32768, + pricing: { + text: { + input: { + normal: 0.55, + cached: 0.25, + }, + output: { + normal: 0.8, + }, + }, + image: 0, + }, +} as const +const THEDRUMMER_UNSLOPNEMO_12B = { + id: 'thedrummer/unslopnemo-12b', + name: 'TheDrummer: UnslopNemo 12B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1024000, + max_output_tokens: 1024000, + pricing: { + text: { + input: { + normal: 0.4, + cached: 0, + }, + output: { + normal: 0.4, + }, + }, + image: 0, + }, +} as const +const THINKINGMACHINES_INKLING = { + id: 'thinkingmachines/inkling', + name: 'Thinking Machines: Inkling', + supports: { + input: ['text', 'image', 'audio'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 262144, + pricing: { + text: { + input: { + normal: 0.95, + cached: 0.16, + }, + output: { + normal: 4.05, + }, + }, + image: 0, + }, +} as const +const THINKINGMACHINES_INKLING_SMALL = { + id: 'thinkingmachines/inkling-small', + name: 'Thinking Machines: Inkling Small', + supports: { + input: ['text', 'image', 'audio'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 524288, + max_output_tokens: 262144, + pricing: { + text: { + input: { + normal: 0.45, + cached: 0.1, + }, + output: { + normal: 1.2, + }, + }, + image: 0, + }, +} as const +const THINKINGMACHINES_INKLING_BATCH = { + id: 'thinkingmachines/inkling:batch', + name: 'Thinking Machines: Inkling (batch)', + supports: { + input: ['text', 'image', 'audio'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 524288, + pricing: { + text: { + input: { + normal: 0.5, + cached: 0.085, + }, + output: { + normal: 2.025, + }, + }, + image: 0, + }, +} as const +const UNDI95_REMM_SLERP_L2_13B = { + id: 'undi95/remm-slerp-l2-13b', + name: 'ReMM SLERP 13B', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 6144, + max_output_tokens: 6144, + pricing: { + text: { + input: { + normal: 0.45, + cached: 0, + }, + output: { + normal: 0.65, + }, + }, + image: 0, + }, +} as const +const UPSTAGE_SOLAR_PRO_3 = { + id: 'upstage/solar-pro-3', + name: 'Upstage: Solar Pro 3', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.15, + cached: 0.015, + }, + output: { + normal: 0.6, + }, + }, + image: 0, + }, +} as const +const UPSTAGE_SOLAR_PRO4 = { + id: 'upstage/solar-pro4', + name: 'Upstage: Solar Pro 4', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 524288, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.03, + cached: 0.006, + }, + output: { + normal: 0.12, + }, + }, + image: 0, + }, +} as const +const WRITER_PALMYRA_X5 = { + id: 'writer/palmyra-x5', + name: 'Writer: Palmyra X5', + supports: { + input: ['text'], + output: ['text'], + supports: ['maxCompletionTokens', 'stop', 'temperature', 'topP'], + }, + context_window: 1040000, + max_output_tokens: 8192, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_4_20 = { + id: 'x-ai/grok-4.20', + name: 'SpaceXAI: Grok 4.20', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 2000000, + pricing: { + text: { + input: { + normal: 1.25, + cached: 0.2, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_4_20_MULTI_AGENT = { + id: 'x-ai/grok-4.20-multi-agent', + name: 'SpaceXAI: Grok 4.20 Multi-Agent', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'logprobs', + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'seed', + 'temperature', + 'topLogprobs', + 'topP', + ], + }, + context_window: 2000000, + pricing: { + text: { + input: { + normal: 1.25, + cached: 0.2, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_4_3 = { + id: 'x-ai/grok-4.3', + name: 'SpaceXAI: Grok 4.3', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1000000, + pricing: { + text: { + input: { + normal: 1.25, + cached: 0.2, + }, + output: { + normal: 2.5, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_4_5 = { + id: 'x-ai/grok-4.5', + name: 'SpaceXAI: Grok 4.5', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 500000, + pricing: { + text: { + input: { + normal: 2, + cached: 0.3, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_4_6 = { + id: 'x-ai/grok-4.6', + name: 'SpaceXAI: Grok 4.6', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 500000, + pricing: { + text: { + input: { + normal: 2, + cached: 0.5, + }, + output: { + normal: 6, + }, + }, + image: 0, + }, +} as const +const X_AI_GROK_BUILD_0_1 = { + id: 'x-ai/grok-build-0.1', + name: 'SpaceXAI: Grok Build 0.1', + supports: { + input: ['text', 'image', 'document'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 256000, + pricing: { + text: { + input: { + normal: 1, + cached: 0.2, + }, + output: { + normal: 2, + }, + }, + image: 0, + }, +} as const +const XIAOMI_MIMO_V2_5 = { + id: 'xiaomi/mimo-v2.5', + name: 'Xiaomi: MiMo-V2.5', + supports: { + input: ['text', 'audio', 'image', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1050000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.14, + cached: 0.0028, + }, + output: { + normal: 0.28, + }, + }, + image: 0, + }, +} as const +const XIAOMI_MIMO_V2_5_PRO = { + id: 'xiaomi/mimo-v2.5-pro', + name: 'Xiaomi: MiMo-V2.5-Pro', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1050000, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.435, + cached: 0.0036, + }, + output: { + normal: 0.87, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_5 = { + id: 'z-ai/glm-4.5', + name: 'Z.ai: GLM 4.5', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 98304, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0.11, + }, + output: { + normal: 2.2, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_5_AIR = { + id: 'z-ai/glm-4.5-air', + name: 'Z.ai: GLM 4.5 Air', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 98304, + pricing: { + text: { + input: { + normal: 0.13, + cached: 0.025, + }, + output: { + normal: 0.85, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_5V = { + id: 'z-ai/glm-4.5v', + name: 'Z.ai: GLM 4.5V', + supports: { + input: ['text', 'image'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 65536, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0.11, + }, + output: { + normal: 1.8, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_6 = { + id: 'z-ai/glm-4.6', + name: 'Z.ai: GLM 4.6', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 204800, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.55, + cached: 0.11, + }, + output: { + normal: 2.2, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_6V = { + id: 'z-ai/glm-4.6v', + name: 'Z.ai: GLM 4.6V', + supports: { + input: ['image', 'text', 'video'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 131072, + max_output_tokens: 32768, + pricing: { + text: { + input: { + normal: 0.3, + cached: 0.055, + }, + output: { + normal: 0.9, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_7 = { + id: 'z-ai/glm-4.7', + name: 'Z.ai: GLM 4.7', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 204800, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 0.4, + cached: 0.08, + }, + output: { + normal: 1.75, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_4_7_FLASH = { + id: 'z-ai/glm-4.7-flash', + name: 'Z.ai: GLM 4.7 Flash', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 202752, + max_output_tokens: 16384, + pricing: { + text: { + input: { + normal: 0.06, + cached: 0.01, + }, + output: { + normal: 0.4, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5 = { + id: 'z-ai/glm-5', + name: 'Z.ai: GLM 5', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 204800, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.6, + cached: 0.12, + }, + output: { + normal: 1.92, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5_TURBO = { + id: 'z-ai/glm-5-turbo', + name: 'Z.ai: GLM 5 Turbo', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 202752, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 1.2, + cached: 0.24, + }, + output: { + normal: 4, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5_1 = { + id: 'z-ai/glm-5.1', + name: 'Z.ai: GLM 5.1', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 204800, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.966, + cached: 0.1794, + }, + output: { + normal: 3.036, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5_2 = { + id: 'z-ai/glm-5.2', + name: 'Z.ai: GLM 5.2', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'logprobs', + 'maxCompletionTokens', + 'parallelToolCalls', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'seed', + 'stop', + 'temperature', + 'toolChoice', + 'topLogprobs', + 'topP', + ], + }, + context_window: 1048576, + max_output_tokens: 128000, + pricing: { + text: { + input: { + normal: 0.308, + cached: 0.0572, + }, + output: { + normal: 0.968, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5_2_BATCH = { + id: 'z-ai/glm-5.2:batch', + name: 'Z.ai: GLM 5.2 (batch)', + supports: { + input: ['text'], + output: ['text'], + supports: [ + 'frequencyPenalty', + 'logitBias', + 'maxCompletionTokens', + 'presencePenalty', + 'reasoning', + 'responseFormat', + 'stop', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 512000, + pricing: { + text: { + input: { + normal: 0.7, + cached: 0.13, + }, + output: { + normal: 2.2, + }, + }, + image: 0, + }, +} as const +const Z_AI_GLM_5V_TURBO = { + id: 'z-ai/glm-5v-turbo', + name: 'Z.ai: GLM 5V Turbo', + supports: { + input: ['image', 'text', 'video'], + output: ['text'], + supports: [ + 'maxCompletionTokens', + 'reasoning', + 'responseFormat', + 'temperature', + 'toolChoice', + 'topP', + ], + }, + context_window: 202752, + max_output_tokens: 131072, + pricing: { + text: { + input: { + normal: 1.2, + cached: 0.24, + }, + output: { + normal: 4, + }, + }, + image: 0, + }, +} as const + +export type OpenRouterModelOptionsByName = { + [_ANTHROPIC_CLAUDE_FABLE_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [_ANTHROPIC_CLAUDE_HAIKU_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [_ANTHROPIC_CLAUDE_OPUS_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [_ANTHROPIC_CLAUDE_SONNET_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [_DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'parallelToolCalls' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [_GOOGLE_GEMINI_FLASH_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [_GOOGLE_GEMINI_PRO_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [_MOONSHOTAI_KIMI_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [_OPENAI_GPT_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [_OPENAI_GPT_MINI_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [_X_AI_GROK_LATEST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [AI21_JAMBA_LARGE_1_7.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [AION_LABS_AION_2_0.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [AION_LABS_AION_3_0.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [AION_LABS_AION_3_0_MINI.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [AION_LABS_AION_RP_LLAMA_3_1_8B.id]: OpenRouterCommonOptions & + Pick + [ALLENAI_OLMO_3_32B_THINK.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'topP' + > + [AMAZON_NOVA_2_LITE_V1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [AMAZON_NOVA_LITE_V1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + > + [AMAZON_NOVA_MICRO_V1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + > + [AMAZON_NOVA_PREMIER_V1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + > + [AMAZON_NOVA_PRO_V1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + > + [ANTHRACITE_ORG_MAGNUM_V4_72B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'topLogprobs' + | 'topP' + > + [ANTHROPIC_CLAUDE_3_HAIKU.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'stop' | 'temperature' | 'toolChoice' | 'topP' + > + [ANTHROPIC_CLAUDE_FABLE_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_FABLE_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_HAIKU_4_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_OPUS_4.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_OPUS_4_1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_6.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_OPUS_4_6_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [ANTHROPIC_CLAUDE_OPUS_4_7.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_7_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_8.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_4_8_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_5_FAST.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_OPUS_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ANTHROPIC_CLAUDE_SONNET_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' - | 'responseFormat' | 'stop' + | 'temperature' | 'toolChoice' + | 'topP' > - [_ANTHROPIC_CLAUDE_HAIKU_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_4_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -10942,18 +13641,18 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [_ANTHROPIC_CLAUDE_OPUS_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'stop' | 'temperature' | 'toolChoice' + | 'topP' > - [_ANTHROPIC_CLAUDE_SONNET_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_4_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -10961,40 +13660,47 @@ export type OpenRouterModelOptionsByName = { | 'reasoning' | 'responseFormat' | 'stop' + | 'temperature' | 'toolChoice' + | 'topP' > - [_GOOGLE_GEMINI_FLASH_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_4_6_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [_GOOGLE_GEMINI_PRO_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' - | 'temperature' | 'toolChoice' - | 'topP' > - [_MOONSHOTAI_KIMI_LATEST.id]: OpenRouterCommonOptions & + [ANTHROPIC_CLAUDE_SONNET_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'toolChoice' + > + [ARCEE_AI_TRINITY_LARGE_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'parallelToolCalls' | 'presencePenalty' | 'reasoning' | 'responseFormat' @@ -11005,496 +13711,632 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [_OPENAI_GPT_LATEST.id]: OpenRouterCommonOptions & + [ARCEE_AI_VIRTUOSO_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'maxCompletionTokens' - | 'reasoning' - | 'responseFormat' - | 'seed' + | 'presencePenalty' + | 'stop' + | 'temperature' | 'toolChoice' + | 'topP' > - [_OPENAI_GPT_MINI_LATEST.id]: OpenRouterCommonOptions & + [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' - | 'responseFormat' | 'seed' - | 'toolChoice' + | 'stop' + | 'temperature' + | 'topP' > - [AI21_JAMBA_LARGE_1_7.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_1_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [AION_LABS_AION_2_0.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [AION_LABS_AION_3_0.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_2_1_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [AION_LABS_AION_3_0_MINI.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_2_0_CODE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [AION_LABS_AION_RP_LLAMA_3_1_8B.id]: OpenRouterCommonOptions & - Pick - [ALLENAI_OLMO_3_32B_THINK.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_2_0_LITE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [AMAZON_NOVA_2_LITE_V1.id]: OpenRouterCommonOptions & + [BYTEDANCE_SEED_SEED_2_0_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' + | 'responseFormat' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [AMAZON_NOVA_LITE_V1.id]: OpenRouterCommonOptions & + [BYTEDANCE_UI_TARS_1_5_7B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'seed' + | 'stop' + | 'temperature' + | 'topLogprobs' + | 'topP' > - [AMAZON_NOVA_MICRO_V1.id]: OpenRouterCommonOptions & + [COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'topP' > - [AMAZON_NOVA_PREMIER_V1.id]: OpenRouterCommonOptions & + [COHERE_COMMAND_A.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'topP' > - [AMAZON_NOVA_PRO_V1.id]: OpenRouterCommonOptions & + [COHERE_COMMAND_R_08_2024.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' > - [ANTHRACITE_ORG_MAGNUM_V4_72B.id]: OpenRouterCommonOptions & + [COHERE_COMMAND_R_PLUS_08_2024.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [ANTHROPIC_CLAUDE_3_HAIKU.id]: OpenRouterCommonOptions & + [COHERE_COMMAND_R7B_12_2024.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'toolChoice' | 'topP' + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'topP' > - [ANTHROPIC_CLAUDE_FABLE_5.id]: OpenRouterCommonOptions & + [COHERE_NORTH_MINI_CODE_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [DEEPCOGITO_COGITO_V2_1_671B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'stop' - | 'toolChoice' + | 'temperature' + | 'topP' > - [ANTHROPIC_CLAUDE_HAIKU_4_5.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_CHAT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [DEEPSEEK_DEEPSEEK_CHAT_V3_0324.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_CHAT_V3_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_1.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_R1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_5.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_R1_0528.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_6.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'seed' + | 'stop' + | 'temperature' + | 'topP' + > + [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_7.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V3_2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' + | 'temperature' | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V3_2_EXP.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' + | 'temperature' | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_8.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_FLASH_0731.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' + | 'temperature' | 'toolChoice' + | 'topLogprobs' + | 'topP' > - [ANTHROPIC_CLAUDE_SONNET_4.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [ANTHROPIC_CLAUDE_SONNET_4_5.id]: OpenRouterCommonOptions & + [DEEPSEEK_DEEPSEEK_V4_PRO_0813.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [ANTHROPIC_CLAUDE_SONNET_4_6.id]: OpenRouterCommonOptions & + [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [ANTHROPIC_CLAUDE_SONNET_5.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' + | 'temperature' | 'toolChoice' + | 'topP' > - [ARCEE_AI_CODER_LARGE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'topP' > - [ARCEE_AI_TRINITY_LARGE_THINKING.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [ARCEE_AI_TRINITY_MINI.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'logprobs' - | 'maxCompletionTokens' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [ARCEE_AI_VIRTUOSO_LARGE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [BYTEDANCE_SEED_SEED_1_6.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [BYTEDANCE_SEED_SEED_2_0_LITE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [BYTEDANCE_SEED_SEED_2_0_MINI.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [BYTEDANCE_UI_TARS_1_5_7B.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_PRO_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [COHERE_COMMAND_A.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'topP' > - [COHERE_COMMAND_R_08_2024.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [COHERE_COMMAND_R_PLUS_08_2024.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_IMAGE_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [COHERE_COMMAND_R7B_12_2024.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_LITE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [COHERE_NORTH_MINI_CODE_FREE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' - | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [DEEPCOGITO_COGITO_V2_1_671B.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'stop' + | 'seed' | 'temperature' + | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_CHAT.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_FLASH_LITE_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -11502,13 +14344,11 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_CHAT_V3_0324.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_PRO_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -11516,30 +14356,21 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_CHAT_V3_1.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_R1.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_1_PRO_PREVIEW_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' @@ -11548,119 +14379,87 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_R1_0528.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_5_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_5_FLASH_LITE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [DEEPSEEK_DEEPSEEK_V3_1_TERMINUS.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_5_FLASH_LITE_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' - | 'temperature' | 'toolChoice' - | 'topP' > - [DEEPSEEK_DEEPSEEK_V3_2.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_5_FLASH_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_V3_2_EXP.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_6_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [DEEPSEEK_DEEPSEEK_V4_FLASH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_6_FLASH_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [DEEPSEEK_DEEPSEEK_V4_PRO.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_7_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH.id]: OpenRouterCommonOptions & + [GOOGLE_GEMINI_3_7_FLASH_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -11668,25 +14467,27 @@ export type OpenRouterModelOptionsByName = { | 'responseFormat' | 'seed' | 'stop' - | 'temperature' | 'toolChoice' - | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_IMAGE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_2_27B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_3_12B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' @@ -11694,170 +14495,225 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_09_2025.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_3_27B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_3_4B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO_PREVIEW.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_3N_E4B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_4_26B_A4B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_4_26B_A4B_IT_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_PRO_IMAGE.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_4_31B_IT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW.id]: OpenRouterCommonOptions & + [GOOGLE_GEMMA_4_31B_IT_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [GOOGLE_GEMINI_3_1_FLASH_IMAGE.id]: OpenRouterCommonOptions & + [GOOGLE_LYRIA_3_CLIP_PREVIEW.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' | 'topP' + > + [GOOGLE_LYRIA_3_PRO_PREVIEW.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' | 'topP' + > + [GRYPHE_MYTHOMAX_L2_13B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_1_FLASH_IMAGE_PREVIEW.id]: OpenRouterCommonOptions & + [IBM_GRANITE_GRANITE_4_0_H_MICRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_1_FLASH_LITE.id]: OpenRouterCommonOptions & + [IBM_GRANITE_GRANITE_4_1_8B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE.id]: OpenRouterCommonOptions & + [INCEPTION_MERCURY_2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' - | 'seed' + | 'stop' | 'temperature' - | 'topP' + | 'toolChoice' > - [GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_2_6_1T.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_1_PRO_PREVIEW.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_2_6_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS.id]: OpenRouterCommonOptions & + [INCLUSIONAI_LING_3_0_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' - | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMINI_3_5_FLASH.id]: OpenRouterCommonOptions & + [INCLUSIONAI_RING_2_6_1T.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' @@ -11866,23 +14722,25 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [GOOGLE_GEMMA_2_27B_IT.id]: OpenRouterCommonOptions & + [KWAIPILOT_KAT_CODER_AIR_V2_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_3_12B_IT.id]: OpenRouterCommonOptions & + [KWAIPILOT_KAT_CODER_PRO_V2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -11890,74 +14748,76 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_3_27B_IT.id]: OpenRouterCommonOptions & + [KWAIPILOT_KAT_CODER_PRO_V2_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_3_4B_IT.id]: OpenRouterCommonOptions & + [LIQUID_LFM_2_5_2_6B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_3N_E4B_IT.id]: OpenRouterCommonOptions & + [MANCER_WEAVER.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' + | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_4_26B_A4B_IT.id]: OpenRouterCommonOptions & + [MEITUAN_LONGCAT_2_0.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_4_26B_A4B_IT_FREE.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -11966,7 +14826,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_4_31B_IT.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -11974,7 +14834,6 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -11983,29 +14842,19 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [GOOGLE_GEMMA_4_31B_IT_FREE.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_3_2_1B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' - | 'responseFormat' + | 'presencePenalty' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [GOOGLE_LYRIA_3_CLIP_PREVIEW.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' | 'topP' - > - [GOOGLE_LYRIA_3_PRO_PREVIEW.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' | 'topP' - > - [GRYPHE_MYTHOMAX_L2_13B.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_3_2_3B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12013,14 +14862,13 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'topLogprobs' | 'topP' > - [IBM_GRANITE_GRANITE_4_0_H_MICRO.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_3_3_70B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12032,13 +14880,15 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topLogprobs' | 'topP' > - [IBM_GRANITE_GRANITE_4_1_8B.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_4_MAVERICK.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -12050,38 +14900,42 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [INCEPTION_MERCURY_2.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_4_SCOUT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topP' > - [INCLUSIONAI_LING_2_6_1T.id]: OpenRouterCommonOptions & + [META_LLAMA_LLAMA_GUARD_4_12B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topLogprobs' | 'topP' > - [INCLUSIONAI_LING_2_6_FLASH.id]: OpenRouterCommonOptions & + [META_MUSE_GLIMMER_30B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12090,110 +14944,117 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [INCLUSIONAI_RING_2_6_1T.id]: OpenRouterCommonOptions & + [META_MUSE_SPARK_1_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [INFLECTION_INFLECTION_3_PI.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' - > - [INFLECTION_INFLECTION_3_PRODUCTIVITY.id]: OpenRouterCommonOptions & + [META_MUSE_SPARK_1_2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'stop' | 'temperature' | 'topP' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' > - [KWAIPILOT_KAT_CODER_PRO_V2.id]: OpenRouterCommonOptions & + [MICROSOFT_PHI_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topLogprobs' | 'topP' > - [LIQUID_LFM_2_24B_A2B.id]: OpenRouterCommonOptions & + [MICROSOFT_WIZARDLM_2_8X22B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'topP' > - [LIQUID_LFM_2_5_1_2B_INSTRUCT_FREE.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_01.id]: OpenRouterCommonOptions & + Pick + [MINIMAX_MINIMAX_M1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [LIQUID_LFM_2_5_1_2B_THINKING_FREE.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MANCER_WEAVER.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M2_HER.id]: OpenRouterCommonOptions & + Pick + [MINIMAX_MINIMAX_M2_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_3_8B_INSTRUCT.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M2_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' + | 'reasoning' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M2_7.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12201,6 +15062,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12209,7 +15071,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12217,6 +15079,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12225,61 +15088,77 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT.id]: OpenRouterCommonOptions & + [MINIMAX_MINIMAX_M3_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [MISTRALAI_CODESTRAL_2508.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'prediction' + | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_3_2_1B_INSTRUCT.id]: OpenRouterCommonOptions & + [MISTRALAI_MINISTRAL_14B_2512.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_3_2_3B_INSTRUCT.id]: OpenRouterCommonOptions & + [MISTRALAI_MINISTRAL_3B_2512.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topLogprobs' + | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE.id]: OpenRouterCommonOptions & + [MISTRALAI_MINISTRAL_8B_2512.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_3_3_70B_INSTRUCT.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -12287,26 +15166,25 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_LARGE_2407.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_4_MAVERICK.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_LARGE_2512.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -12314,14 +15192,12 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [META_LLAMA_LLAMA_4_SCOUT.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_MEDIUM_3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -12331,78 +15207,76 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [META_LLAMA_LLAMA_GUARD_4_12B.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_MEDIUM_3_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [MICROSOFT_PHI_4.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_MEDIUM_3_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [MICROSOFT_WIZARDLM_2_8X22B.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_NEMO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MINIMAX_MINIMAX_01.id]: OpenRouterCommonOptions & - Pick - [MINIMAX_MINIMAX_M1.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_SABA.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MINIMAX_MINIMAX_M2.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MINIMAX_MINIMAX_M2_HER.id]: OpenRouterCommonOptions & - Pick - [MINIMAX_MINIMAX_M2_1.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_SMALL_2603.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12416,25 +15290,21 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MINIMAX_MINIMAX_M2_5.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'parallelToolCalls' | 'presencePenalty' - | 'reasoning' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topLogprobs' | 'topP' > - [MINIMAX_MINIMAX_M2_7.id]: OpenRouterCommonOptions & + [MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12442,7 +15312,6 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12451,24 +15320,20 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [MINIMAX_MINIMAX_M3.id]: OpenRouterCommonOptions & + [MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MISTRALAI_CODESTRAL_2508.id]: OpenRouterCommonOptions & + [MISTRALAI_VOXTRAL_SMALL_24B_2507.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12481,24 +15346,22 @@ export type OpenRouterModelOptionsByName = { | 'toolChoice' | 'topP' > - [MISTRALAI_DEVSTRAL_2512.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' - | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MISTRALAI_MINISTRAL_14B_2512.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_0905.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -12506,16 +15369,16 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MISTRALAI_MINISTRAL_3B_2512.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12524,13 +15387,15 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [MISTRALAI_MINISTRAL_8B_2512.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12539,115 +15404,123 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_LARGE.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_6.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_LARGE_2407.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_7_CODE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' + | 'parallelToolCalls' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_LARGE_2512.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K2_7_CODE_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_MEDIUM_3.id]: OpenRouterCommonOptions & + [MOONSHOTAI_KIMI_K3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_MEDIUM_3_5.id]: OpenRouterCommonOptions & + [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & + Pick + [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' - | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' - | 'toolChoice' - | 'topP' + | 'topLogprobs' > - [MISTRALAI_MISTRAL_MEDIUM_3_1.id]: OpenRouterCommonOptions & + [NEX_AGI_NEX_N2_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_NEMO.id]: OpenRouterCommonOptions & + [NEX_AGI_NEX_N2_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' + | 'reasoning' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_SABA.id]: OpenRouterCommonOptions & + [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501.id]: OpenRouterCommonOptions & + [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12660,7 +15533,7 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [MISTRALAI_MISTRAL_SMALL_2603.id]: OpenRouterCommonOptions & + [NOUSRESEARCH_HERMES_4_405B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12668,27 +15541,21 @@ export type OpenRouterModelOptionsByName = { | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' - | 'toolChoice' | 'topP' > - [MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT.id]: OpenRouterCommonOptions & + [NOUSRESEARCH_HERMES_4_70B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'seed' - | 'stop' + | 'reasoning' + | 'responseFormat' | 'temperature' - | 'topLogprobs' | 'topP' > - [MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12696,6 +15563,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12704,62 +15572,59 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [MISTRALAI_MIXTRAL_8X22B_INSTRUCT.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' + | 'reasoning' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MISTRALAI_VOXTRAL_SMALL_24B_2507.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' + | 'reasoning' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MOONSHOTAI_KIMI_K2.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [MOONSHOTAI_KIMI_K2_0905.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [MOONSHOTAI_KIMI_K2_THINKING.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' @@ -12768,52 +15633,44 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MOONSHOTAI_KIMI_K2_5.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'seed' | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MOONSHOTAI_KIMI_K2_6.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'parallelToolCalls' - | 'presencePenalty' | 'reasoning' - | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [MOONSHOTAI_KIMI_K2_7_CODE.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'reasoning' | 'seed' | 'temperature' | 'topP' + > + [NVIDIA_NEMOTRON_3_5_LIGHTNING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'parallelToolCalls' | 'presencePenalty' | 'reasoning' | 'responseFormat' @@ -12824,124 +15681,126 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [MORPH_MORPH_V3_FAST.id]: OpenRouterCommonOptions & - Pick - [MORPH_MORPH_V3_LARGE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'logprobs' - | 'maxCompletionTokens' - | 'responseFormat' - | 'stop' - | 'temperature' - | 'topLogprobs' - > - [NEX_AGI_NEX_N2_MINI.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'logprobs' | 'maxCompletionTokens' | 'reasoning' - | 'responseFormat' + | 'seed' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [NEX_AGI_NEX_N2_PRO.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logprobs' | 'maxCompletionTokens' | 'reasoning' + | 'seed' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: OpenRouterCommonOptions & + [NVIDIA_NEMOTRON_NANO_9B_V2_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' + | 'toolChoice' | 'topP' > - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_0613.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NOUSRESEARCH_HERMES_4_405B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_16K.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' + | 'seed' + | 'stop' | 'temperature' + | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NOUSRESEARCH_HERMES_4_70B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' + | 'seed' + | 'stop' | 'temperature' + | 'topLogprobs' | 'topP' > - [NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5.id]: OpenRouterCommonOptions & + [OPENAI_GPT_3_5_TURBO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12950,27 +15809,39 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' + | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_TURBO_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'reasoning' + | 'presencePenalty' + | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_TURBO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -12978,7 +15849,6 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -12987,75 +15857,78 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'reasoning' + | 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > - [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' - | 'reasoning' + | 'maxCompletionTokens' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'reasoning' + | 'responseFormat' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > - [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1_NANO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - 'maxCompletionTokens' | 'reasoning' | 'seed' | 'temperature' | 'topP' + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'responseFormat' + | 'seed' + | 'temperature' + | 'toolChoice' + | 'topP' > - [NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1_NANO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'reasoning' + | 'responseFormat' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > - [NVIDIA_NEMOTRON_NANO_9B_V2_FREE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4_1_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'reasoning' | 'responseFormat' | 'seed' | 'temperature' | 'toolChoice' | 'topP' > - [OPENAI_GPT_3_5_TURBO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13065,13 +15938,15 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_0613.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_2024_05_13.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13081,7 +15956,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_16K.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_2024_08_06.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -13089,6 +15964,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13098,22 +15974,24 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_2024_11_20.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -13121,6 +15999,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13130,13 +16009,14 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_TURBO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_MINI_2024_07_18.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13146,13 +16026,14 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_TURBO_PREVIEW.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' + | 'prediction' | 'presencePenalty' | 'responseFormat' | 'seed' @@ -13162,144 +16043,237 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_1.id]: OpenRouterCommonOptions & + [OPENAI_GPT_4O_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'prediction' + | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4_1_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'seed' - | 'temperature' | 'toolChoice' - | 'topP' > - [OPENAI_GPT_4_1_NANO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_CODEX_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'seed' - | 'temperature' | 'toolChoice' - | 'topP' > - [OPENAI_GPT_4O.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_IMAGE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4O_2024_05_13.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_IMAGE_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' | 'logprobs' | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' | 'topLogprobs' | 'topP' > - [OPENAI_GPT_4O_2024_08_06.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [OPENAI_GPT_4O_2024_11_20.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [OPENAI_GPT_4O_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_NANO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [OPENAI_GPT_4O_MINI_2024_07_18.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_NANO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > - [OPENAI_GPT_4O_MINI_SEARCH_PREVIEW.id]: OpenRouterCommonOptions & - Pick - [OPENAI_GPT_4O_SEARCH_PREVIEW.id]: OpenRouterCommonOptions & - Pick - [OPENAI_GPT_5.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_PRO.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_PRO_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_1.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_1_CODEX.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_1_CODEX_MAX.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_1_CODEX_MINI.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_1_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_2.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_2_CHAT.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' + > + [OPENAI_GPT_5_2_CODEX.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_2_PRO.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_2_PRO_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_2_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_3_CODEX.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13309,21 +16283,17 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_CHAT.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'responseFormat' | 'seed' - > - [OPENAI_GPT_5_CODEX.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_IMAGE.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_IMAGE_2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -13335,37 +16305,28 @@ export type OpenRouterModelOptionsByName = { | 'responseFormat' | 'seed' | 'stop' - | 'temperature' | 'topLogprobs' - | 'topP' > - [OPENAI_GPT_5_IMAGE_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' + | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' - | 'topLogprobs' - | 'topP' + | 'toolChoice' > - [OPENAI_GPT_5_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_MINI_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_NANO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_NANO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13375,7 +16336,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_PRO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_NANO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13384,7 +16345,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_1.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13394,26 +16355,25 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_1_CHAT.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_1_CODEX.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_4_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_1_CODEX_MAX.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_5.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13423,36 +16383,44 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_1_CODEX_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_5_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_2.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_5_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_GPT_5_5_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_2_CHAT.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_LUNA.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_2_CODEX.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_LUNA_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13462,7 +16430,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_2_PRO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_LUNA_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13471,16 +16439,16 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_3_CHAT.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_LUNA_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' + | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_3_CODEX.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_SOL.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13490,7 +16458,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_4.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_SOL_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13500,31 +16468,25 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_4_IMAGE_2.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_SOL_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'topLogprobs' + | 'toolChoice' > - [OPENAI_GPT_5_4_MINI.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_SOL_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_4_NANO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_TERRA.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13534,7 +16496,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_4_PRO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_TERRA_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13544,17 +16506,16 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_5.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_TERRA_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' - | 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' | 'toolChoice' > - [OPENAI_GPT_5_5_PRO.id]: OpenRouterCommonOptions & + [OPENAI_GPT_5_6_TERRA_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13598,16 +16559,7 @@ export type OpenRouterModelOptionsByName = { [OPENAI_GPT_CHAT_LATEST.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'responseFormat' - | 'seed' - | 'stop' - | 'toolChoice' - | 'topLogprobs' + 'maxCompletionTokens' | 'responseFormat' | 'seed' | 'toolChoice' > [OPENAI_GPT_OSS_120B.id]: OpenRouterCommonOptions & Pick< @@ -13626,17 +16578,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [OPENAI_GPT_OSS_120B_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'maxCompletionTokens' - | 'reasoning' - | 'seed' - | 'stop' - | 'temperature' - | 'toolChoice' - | 'topP' - > [OPENAI_GPT_OSS_20B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -13696,7 +16637,12 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' > - [OPENAI_O3.id]: OpenRouterCommonOptions & + [OPENAI_O1_PRO_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + 'maxCompletionTokens' | 'reasoning' | 'responseFormat' | 'seed' + > + [OPENAI_O1_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13705,22 +16651,14 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_O3_DEEP_RESEARCH.id]: OpenRouterCommonOptions & + [OPENAI_O3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > [OPENAI_O3_MINI.id]: OpenRouterCommonOptions & Pick< @@ -13740,6 +16678,24 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > + [OPENAI_O3_MINI_HIGH_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_O3_MINI_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > [OPENAI_O3_PRO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -13749,7 +16705,7 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_O4_MINI.id]: OpenRouterCommonOptions & + [OPENAI_O3_PRO_BATCH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'maxCompletionTokens' @@ -13758,22 +16714,23 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > - [OPENAI_O4_MINI_DEEP_RESEARCH.id]: OpenRouterCommonOptions & + [OPENAI_O3_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_O4_MINI.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' - | 'temperature' | 'toolChoice' - | 'topLogprobs' - | 'topP' > [OPENAI_O4_MINI_HIGH.id]: OpenRouterCommonOptions & Pick< @@ -13784,6 +16741,24 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'toolChoice' > + [OPENAI_O4_MINI_HIGH_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > + [OPENAI_O4_MINI_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'maxCompletionTokens' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'toolChoice' + > [PERCEPTRON_PERCEPTRON_MK1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -13842,12 +16817,12 @@ export type OpenRouterModelOptionsByName = { | 'temperature' | 'topP' > - [POOLSIDE_LAGUNA_M_1.id]: OpenRouterCommonOptions & + [POOLSIDE_LAGUNA_S_2_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'reasoning' | 'temperature' | 'toolChoice' > - [POOLSIDE_LAGUNA_M_1_FREE.id]: OpenRouterCommonOptions & + [POOLSIDE_LAGUNA_S_2_1_FREE.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, 'maxCompletionTokens' | 'reasoning' | 'temperature' | 'toolChoice' @@ -13862,16 +16837,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, 'maxCompletionTokens' | 'reasoning' | 'temperature' | 'toolChoice' > - [POOLSIDE_LAGUNA_XS_2.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'reasoning' | 'temperature' | 'toolChoice' - > - [POOLSIDE_LAGUNA_XS_2_FREE.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - 'maxCompletionTokens' | 'reasoning' | 'temperature' | 'toolChoice' - > [QWEN_QWEN_2_5_72B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -13891,7 +16856,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' @@ -13899,7 +16863,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: OpenRouterCommonOptions & @@ -13917,11 +16880,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -13930,11 +16895,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN_PLUS_2025_07_28.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -13943,13 +16910,17 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN_PLUS_2025_07_28_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > [QWEN_QWEN2_5_VL_72B_INSTRUCT.id]: OpenRouterCommonOptions & @@ -13987,11 +16958,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN3_235B_A22B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -14034,7 +17007,6 @@ export type OpenRouterModelOptionsByName = { OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' @@ -14043,7 +17015,6 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > [QWEN_QWEN3_30B_A3B_INSTRUCT_2507.id]: OpenRouterCommonOptions & @@ -14065,11 +17036,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN3_30B_A3B_THINKING_2507.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -14094,11 +17067,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN3_8B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -14137,11 +17112,13 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN3_CODER_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -14166,55 +17143,66 @@ export type OpenRouterModelOptionsByName = { [QWEN_QWEN3_CODER_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_CODER_FREE.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_MAX.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_MAX.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_MAX_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_MAX_THINKING.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14222,6 +17210,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -14230,19 +17219,23 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT_FREE.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' + | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14258,7 +17251,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14274,7 +17267,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14290,7 +17283,22 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_30B_A3B_INSTRUCT.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_32B_INSTRUCT.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [QWEN_QWEN3_VL_8B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14306,7 +17314,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_30B_A3B_THINKING.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_VL_8B_THINKING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14316,25 +17324,47 @@ export type OpenRouterModelOptionsByName = { | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_32B_INSTRUCT.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_122B_A10B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_8B_INSTRUCT.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_27B.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [QWEN_QWEN3_5_35B_A3B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14342,6 +17372,7 @@ export type OpenRouterModelOptionsByName = { | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' @@ -14350,21 +17381,24 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_VL_8B_THINKING.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_397B_A17B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_122B_A10B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_9B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14381,12 +17415,10 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_27B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_FLASH_02_23.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' - | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' @@ -14395,14 +17427,12 @@ export type OpenRouterModelOptionsByName = { | 'stop' | 'temperature' | 'toolChoice' - | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_35B_A3B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_PLUS_02_15.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -14415,11 +17445,10 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_397B_A17B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_5_PLUS_20260420.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -14432,7 +17461,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_9B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_27B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14449,51 +17478,59 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_FLASH_02_23.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_35B_A3B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' + | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_PLUS_02_15.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_5_PLUS_20260420.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_MAX_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_27B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_6_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' @@ -14506,88 +17543,96 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_35B_A3B.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_FLASH.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_FLASH.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_MAX.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_MAX_PREVIEW.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_7_PLUS.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_6_PLUS.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_8_2_4T_A95B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_7_MAX.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_8_27B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' | 'topP' > - [QWEN_QWEN3_7_PLUS.id]: OpenRouterCommonOptions & + [QWEN_QWEN3_8_MAX.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'seed' + | 'stop' | 'temperature' | 'toolChoice' | 'topLogprobs' @@ -14636,29 +17681,21 @@ export type OpenRouterModelOptionsByName = { > [SAKANA_FUGU_ULTRA.id]: OpenRouterCommonOptions & Pick + [SAKANA_SAKANA_NAMAZU.id]: OpenRouterCommonOptions & + Pick [SAO10K_L3_LUNARIS_8B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'topP' - > - [SAO10K_L3_1_70B_HANAMI_X1.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' - | 'maxCompletionTokens' - | 'presencePenalty' - | 'seed' - | 'stop' - | 'temperature' + | 'topLogprobs' | 'topP' > [SAO10K_L3_1_EURYALE_70B.id]: OpenRouterCommonOptions & @@ -14716,17 +17753,6 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [SWITCHPOINT_ROUTER.id]: OpenRouterCommonOptions & - Pick< - OpenRouterBaseOptions, - | 'maxCompletionTokens' - | 'reasoning' - | 'responseFormat' - | 'seed' - | 'stop' - | 'temperature' - | 'topP' - > [TENCENT_HUNYUAN_A13B_INSTRUCT.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -14743,8 +17769,10 @@ export type OpenRouterModelOptionsByName = { | 'frequencyPenalty' | 'logitBias' | 'maxCompletionTokens' + | 'maxCompletionTokens' | 'presencePenalty' | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' @@ -14754,30 +17782,29 @@ export type OpenRouterModelOptionsByName = { [TENCENT_HY3_PREVIEW.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' > - [TENCENT_HY3_FREE.id]: OpenRouterCommonOptions & + [THEDRUMMER_CYDONIA_24B_V4_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' | 'maxCompletionTokens' | 'presencePenalty' - | 'reasoning' + | 'responseFormat' | 'seed' | 'stop' | 'temperature' - | 'toolChoice' + | 'topLogprobs' | 'topP' > - [THEDRUMMER_CYDONIA_24B_V4_1.id]: OpenRouterCommonOptions & + [THEDRUMMER_ROCINANTE_12B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14792,7 +17819,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [THEDRUMMER_ROCINANTE_12B.id]: OpenRouterCommonOptions & + [THEDRUMMER_SKYFALL_36B_V2.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14807,7 +17834,7 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > - [THEDRUMMER_SKYFALL_36B_V2.id]: OpenRouterCommonOptions & + [THEDRUMMER_UNSLOPNEMO_12B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' @@ -14819,24 +17846,54 @@ export type OpenRouterModelOptionsByName = { | 'seed' | 'stop' | 'temperature' + | 'toolChoice' | 'topLogprobs' | 'topP' > - [THEDRUMMER_UNSLOPNEMO_12B.id]: OpenRouterCommonOptions & + [THINKINGMACHINES_INKLING.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, | 'frequencyPenalty' - | 'logprobs' + | 'logitBias' | 'maxCompletionTokens' | 'presencePenalty' + | 'reasoning' | 'responseFormat' | 'seed' | 'stop' | 'temperature' | 'toolChoice' + | 'topP' + > + [THINKINGMACHINES_INKLING_SMALL.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' | 'topLogprobs' | 'topP' > + [THINKINGMACHINES_INKLING_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > [UNDI95_REMM_SLERP_L2_13B.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -14855,11 +17912,26 @@ export type OpenRouterModelOptionsByName = { [UPSTAGE_SOLAR_PRO_3.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'temperature' + | 'toolChoice' + | 'topP' + > + [UPSTAGE_SOLAR_PRO4.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' | 'maxCompletionTokens' + | 'presencePenalty' | 'reasoning' | 'responseFormat' | 'temperature' | 'toolChoice' + | 'topP' > [WRITER_PALMYRA_X5.id]: OpenRouterCommonOptions & Pick< @@ -14907,6 +17979,38 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [X_AI_GROK_4_5.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > + [X_AI_GROK_4_6.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logprobs' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'seed' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topLogprobs' + | 'topP' + > [X_AI_GROK_BUILD_0_1.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15077,14 +18181,9 @@ export type OpenRouterModelOptionsByName = { [Z_AI_GLM_5_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, - | 'frequencyPenalty' - | 'logitBias' | 'maxCompletionTokens' - | 'presencePenalty' | 'reasoning' | 'responseFormat' - | 'seed' - | 'stop' | 'temperature' | 'toolChoice' | 'topP' @@ -15124,6 +18223,20 @@ export type OpenRouterModelOptionsByName = { | 'topLogprobs' | 'topP' > + [Z_AI_GLM_5_2_BATCH.id]: OpenRouterCommonOptions & + Pick< + OpenRouterBaseOptions, + | 'frequencyPenalty' + | 'logitBias' + | 'maxCompletionTokens' + | 'presencePenalty' + | 'reasoning' + | 'responseFormat' + | 'stop' + | 'temperature' + | 'toolChoice' + | 'topP' + > [Z_AI_GLM_5V_TURBO.id]: OpenRouterCommonOptions & Pick< OpenRouterBaseOptions, @@ -15150,15 +18263,17 @@ export type OpenRouterModelInputModalitiesByName = { [_ANTHROPIC_CLAUDE_SONNET_LATEST.id]: ReadonlyArray< 'text' | 'image' | 'document' > + [_DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST.id]: ReadonlyArray<'text'> [_GOOGLE_GEMINI_FLASH_LATEST.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' | 'audio' > [_GOOGLE_GEMINI_PRO_LATEST.id]: ReadonlyArray< 'audio' | 'document' | 'image' | 'text' | 'video' > - [_MOONSHOTAI_KIMI_LATEST.id]: ReadonlyArray<'text' | 'image'> + [_MOONSHOTAI_KIMI_LATEST.id]: ReadonlyArray<'text' | 'image' | 'video'> [_OPENAI_GPT_LATEST.id]: ReadonlyArray<'document' | 'image' | 'text'> [_OPENAI_GPT_MINI_LATEST.id]: ReadonlyArray<'document' | 'image' | 'text'> + [_X_AI_GROK_LATEST.id]: ReadonlyArray<'text' | 'image' | 'document'> [AI21_JAMBA_LARGE_1_7.id]: ReadonlyArray<'text'> [AION_LABS_AION_2_0.id]: ReadonlyArray<'text'> [AION_LABS_AION_3_0.id]: ReadonlyArray<'text'> @@ -15175,34 +18290,71 @@ export type OpenRouterModelInputModalitiesByName = { [ANTHRACITE_ORG_MAGNUM_V4_72B.id]: ReadonlyArray<'text'> [ANTHROPIC_CLAUDE_3_HAIKU.id]: ReadonlyArray<'text' | 'image'> [ANTHROPIC_CLAUDE_FABLE_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_FABLE_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_HAIKU_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_OPUS_4.id]: ReadonlyArray<'image' | 'text' | 'document'> [ANTHROPIC_CLAUDE_OPUS_4_1.id]: ReadonlyArray<'image' | 'text' | 'document'> + [ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id]: ReadonlyArray< + 'image' | 'text' | 'document' + > [ANTHROPIC_CLAUDE_OPUS_4_5.id]: ReadonlyArray<'document' | 'image' | 'text'> + [ANTHROPIC_CLAUDE_OPUS_4_5_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > [ANTHROPIC_CLAUDE_OPUS_4_6.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_OPUS_4_6_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_OPUS_4_7.id]: ReadonlyArray<'text' | 'image' | 'document'> [ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id]: ReadonlyArray< 'text' | 'image' | 'document' > + [ANTHROPIC_CLAUDE_OPUS_4_7_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_OPUS_4_8.id]: ReadonlyArray<'text' | 'image' | 'document'> [ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id]: ReadonlyArray< 'text' | 'image' | 'document' > + [ANTHROPIC_CLAUDE_OPUS_4_8_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > + [ANTHROPIC_CLAUDE_OPUS_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_OPUS_5_FAST.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > + [ANTHROPIC_CLAUDE_OPUS_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_SONNET_4.id]: ReadonlyArray<'image' | 'text' | 'document'> [ANTHROPIC_CLAUDE_SONNET_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_SONNET_4_6.id]: ReadonlyArray<'text' | 'image' | 'document'> + [ANTHROPIC_CLAUDE_SONNET_4_6_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ANTHROPIC_CLAUDE_SONNET_5.id]: ReadonlyArray<'text' | 'image' | 'document'> - [ARCEE_AI_CODER_LARGE.id]: ReadonlyArray<'text'> + [ANTHROPIC_CLAUDE_SONNET_5_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' + > [ARCEE_AI_TRINITY_LARGE_THINKING.id]: ReadonlyArray<'text'> - [ARCEE_AI_TRINITY_MINI.id]: ReadonlyArray<'text'> [ARCEE_AI_VIRTUOSO_LARGE.id]: ReadonlyArray<'text'> [BAIDU_ERNIE_4_5_VL_424B_A47B.id]: ReadonlyArray<'image' | 'text'> [BYTEDANCE_SEED_SEED_1_6.id]: ReadonlyArray<'image' | 'text' | 'video'> [BYTEDANCE_SEED_SEED_1_6_FLASH.id]: ReadonlyArray<'image' | 'text' | 'video'> + [BYTEDANCE_SEED_SEED_2_1_TURBO.id]: ReadonlyArray<'text' | 'image' | 'video'> + [BYTEDANCE_SEED_SEED_2_0_CODE.id]: ReadonlyArray<'text' | 'image' | 'video'> [BYTEDANCE_SEED_SEED_2_0_LITE.id]: ReadonlyArray<'text' | 'image' | 'video'> [BYTEDANCE_SEED_SEED_2_0_MINI.id]: ReadonlyArray<'text' | 'image' | 'video'> [BYTEDANCE_UI_TARS_1_5_7B.id]: ReadonlyArray<'image' | 'text'> - [COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE.id]: ReadonlyArray<'text'> + [COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION.id]: ReadonlyArray<'text'> [COHERE_COMMAND_A.id]: ReadonlyArray<'text'> [COHERE_COMMAND_R_08_2024.id]: ReadonlyArray<'text'> [COHERE_COMMAND_R_PLUS_08_2024.id]: ReadonlyArray<'text'> @@ -15219,7 +18371,10 @@ export type OpenRouterModelInputModalitiesByName = { [DEEPSEEK_DEEPSEEK_V3_2.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V3_2_EXP.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_FLASH.id]: ReadonlyArray<'text'> + [DEEPSEEK_DEEPSEEK_V4_FLASH_0731.id]: ReadonlyArray<'text'> [DEEPSEEK_DEEPSEEK_V4_PRO.id]: ReadonlyArray<'text'> + [DEEPSEEK_DEEPSEEK_V4_PRO_0813.id]: ReadonlyArray<'text'> + [DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id]: ReadonlyArray<'text' | 'image'> [GOOGLE_GEMINI_2_5_FLASH.id]: ReadonlyArray< 'document' | 'image' | 'text' | 'audio' | 'video' > @@ -15227,9 +18382,12 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_GEMINI_2_5_FLASH_LITE.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > - [GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_09_2025.id]: ReadonlyArray< + [GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > + [GOOGLE_GEMINI_2_5_FLASH_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' | 'audio' | 'video' + > [GOOGLE_GEMINI_2_5_PRO.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > @@ -15239,9 +18397,15 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > + [GOOGLE_GEMINI_2_5_PRO_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' | 'audio' | 'video' + > [GOOGLE_GEMINI_3_FLASH_PREVIEW.id]: ReadonlyArray< 'text' | 'image' | 'document' | 'audio' | 'video' > + [GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'document' | 'audio' | 'video' + > [GOOGLE_GEMINI_3_PRO_IMAGE.id]: ReadonlyArray<'image' | 'text'> [GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW.id]: ReadonlyArray<'image' | 'text'> [GOOGLE_GEMINI_3_1_FLASH_IMAGE.id]: ReadonlyArray<'image' | 'text'> @@ -15253,15 +18417,42 @@ export type OpenRouterModelInputModalitiesByName = { [GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' | 'audio' > + [GOOGLE_GEMINI_3_1_FLASH_LITE_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > [GOOGLE_GEMINI_3_1_PRO_PREVIEW.id]: ReadonlyArray< 'audio' | 'document' | 'image' | 'text' | 'video' > [GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS.id]: ReadonlyArray< 'text' | 'audio' | 'image' | 'video' | 'document' > + [GOOGLE_GEMINI_3_1_PRO_PREVIEW_BATCH.id]: ReadonlyArray< + 'audio' | 'document' | 'image' | 'text' | 'video' + > [GOOGLE_GEMINI_3_5_FLASH.id]: ReadonlyArray< 'text' | 'image' | 'video' | 'document' | 'audio' > + [GOOGLE_GEMINI_3_5_FLASH_LITE.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_5_FLASH_LITE_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_5_FLASH_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_6_FLASH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_6_FLASH_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_7_FLASH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [GOOGLE_GEMINI_3_7_FLASH_BATCH.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > [GOOGLE_GEMMA_2_27B_IT.id]: ReadonlyArray<'text'> [GOOGLE_GEMMA_3_12B_IT.id]: ReadonlyArray<'text' | 'image'> [GOOGLE_GEMMA_3_27B_IT.id]: ReadonlyArray<'text' | 'image'> @@ -15279,26 +18470,29 @@ export type OpenRouterModelInputModalitiesByName = { [INCEPTION_MERCURY_2.id]: ReadonlyArray<'text'> [INCLUSIONAI_LING_2_6_1T.id]: ReadonlyArray<'text'> [INCLUSIONAI_LING_2_6_FLASH.id]: ReadonlyArray<'text'> + [INCLUSIONAI_LING_3_0_FLASH.id]: ReadonlyArray<'text'> [INCLUSIONAI_RING_2_6_1T.id]: ReadonlyArray<'text'> - [INFLECTION_INFLECTION_3_PI.id]: ReadonlyArray<'text'> - [INFLECTION_INFLECTION_3_PRODUCTIVITY.id]: ReadonlyArray<'text'> + [KWAIPILOT_KAT_CODER_AIR_V2_5.id]: ReadonlyArray<'text'> [KWAIPILOT_KAT_CODER_PRO_V2.id]: ReadonlyArray<'text'> - [LIQUID_LFM_2_24B_A2B.id]: ReadonlyArray<'text'> - [LIQUID_LFM_2_5_1_2B_INSTRUCT_FREE.id]: ReadonlyArray<'text'> - [LIQUID_LFM_2_5_1_2B_THINKING_FREE.id]: ReadonlyArray<'text'> + [KWAIPILOT_KAT_CODER_PRO_V2_5.id]: ReadonlyArray<'text'> + [LIQUID_LFM_2_5_2_6B_FREE.id]: ReadonlyArray<'text'> [MANCER_WEAVER.id]: ReadonlyArray<'text'> - [META_LLAMA_LLAMA_3_8B_INSTRUCT.id]: ReadonlyArray<'text'> + [MEITUAN_LONGCAT_2_0.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id]: ReadonlyArray<'text'> - [META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [META_LLAMA_LLAMA_3_2_1B_INSTRUCT.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_3_2_3B_INSTRUCT.id]: ReadonlyArray<'text'> - [META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_3_3_70B_INSTRUCT.id]: ReadonlyArray<'text'> - [META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE.id]: ReadonlyArray<'text'> [META_LLAMA_LLAMA_4_MAVERICK.id]: ReadonlyArray<'text' | 'image'> [META_LLAMA_LLAMA_4_SCOUT.id]: ReadonlyArray<'text' | 'image'> [META_LLAMA_LLAMA_GUARD_4_12B.id]: ReadonlyArray<'image' | 'text'> + [META_MUSE_GLIMMER_30B.id]: ReadonlyArray<'text' | 'image'> + [META_MUSE_SPARK_1_1.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > + [META_MUSE_SPARK_1_2.id]: ReadonlyArray< + 'text' | 'image' | 'video' | 'document' | 'audio' + > [MICROSOFT_PHI_4.id]: ReadonlyArray<'text'> [MICROSOFT_WIZARDLM_2_8X22B.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_01.id]: ReadonlyArray<'text' | 'image'> @@ -15309,8 +18503,8 @@ export type OpenRouterModelInputModalitiesByName = { [MINIMAX_MINIMAX_M2_5.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_M2_7.id]: ReadonlyArray<'text'> [MINIMAX_MINIMAX_M3.id]: ReadonlyArray<'text' | 'image' | 'video'> + [MINIMAX_MINIMAX_M3_BATCH.id]: ReadonlyArray<'text' | 'image' | 'video'> [MISTRALAI_CODESTRAL_2508.id]: ReadonlyArray<'text' | 'document'> - [MISTRALAI_DEVSTRAL_2512.id]: ReadonlyArray<'text' | 'document'> [MISTRALAI_MINISTRAL_14B_2512.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MINISTRAL_3B_2512.id]: ReadonlyArray<'text' | 'image'> [MISTRALAI_MINISTRAL_8B_2512.id]: ReadonlyArray<'text' | 'image'> @@ -15342,16 +18536,16 @@ export type OpenRouterModelInputModalitiesByName = { [MOONSHOTAI_KIMI_K2_5.id]: ReadonlyArray<'text' | 'image'> [MOONSHOTAI_KIMI_K2_6.id]: ReadonlyArray<'text' | 'image'> [MOONSHOTAI_KIMI_K2_7_CODE.id]: ReadonlyArray<'text' | 'image'> + [MOONSHOTAI_KIMI_K2_7_CODE_BATCH.id]: ReadonlyArray<'text' | 'image'> + [MOONSHOTAI_KIMI_K3.id]: ReadonlyArray<'text' | 'image' | 'video'> [MORPH_MORPH_V3_FAST.id]: ReadonlyArray<'text'> [MORPH_MORPH_V3_LARGE.id]: ReadonlyArray<'text'> [NEX_AGI_NEX_N2_MINI.id]: ReadonlyArray<'text' | 'image'> [NEX_AGI_NEX_N2_PRO.id]: ReadonlyArray<'text' | 'image'> [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id]: ReadonlyArray<'text'> - [NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE.id]: ReadonlyArray<'text'> [NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id]: ReadonlyArray<'text'> [NOUSRESEARCH_HERMES_4_405B.id]: ReadonlyArray<'text'> [NOUSRESEARCH_HERMES_4_70B.id]: ReadonlyArray<'text'> - [NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_NANO_30B_A3B.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id]: ReadonlyArray< @@ -15360,8 +18554,11 @@ export type OpenRouterModelInputModalitiesByName = { [NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id]: ReadonlyArray<'text'> + [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_BATCH.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id]: ReadonlyArray<'text' | 'image'> + [NVIDIA_NEMOTRON_3_5_LIGHTNING.id]: ReadonlyArray<'text'> + [NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id]: ReadonlyArray<'text'> [NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id]: ReadonlyArray< 'image' | 'text' | 'video' > @@ -15370,12 +18567,17 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_3_5_TURBO_0613.id]: ReadonlyArray<'text'> [OPENAI_GPT_3_5_TURBO_16K.id]: ReadonlyArray<'text'> [OPENAI_GPT_3_5_TURBO_INSTRUCT.id]: ReadonlyArray<'text'> + [OPENAI_GPT_3_5_TURBO_BATCH.id]: ReadonlyArray<'text'> [OPENAI_GPT_4.id]: ReadonlyArray<'text'> [OPENAI_GPT_4_TURBO.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_4_TURBO_PREVIEW.id]: ReadonlyArray<'text'> + [OPENAI_GPT_4_TURBO_BATCH.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_4_1.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_4_1_MINI.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_4_1_MINI_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_4_1_NANO.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_4_1_NANO_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_4_1_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_4O.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_4O_2024_05_13.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_4O_2024_08_06.id]: ReadonlyArray<'text' | 'image' | 'document'> @@ -15384,66 +18586,95 @@ export type OpenRouterModelInputModalitiesByName = { [OPENAI_GPT_4O_MINI_2024_07_18.id]: ReadonlyArray< 'text' | 'image' | 'document' > - [OPENAI_GPT_4O_MINI_SEARCH_PREVIEW.id]: ReadonlyArray<'text'> - [OPENAI_GPT_4O_SEARCH_PREVIEW.id]: ReadonlyArray<'text'> + [OPENAI_GPT_4O_MINI_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_4O_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5.id]: ReadonlyArray<'text' | 'image' | 'document'> - [OPENAI_GPT_5_CHAT.id]: ReadonlyArray<'document' | 'image' | 'text'> - [OPENAI_GPT_5_CODEX.id]: ReadonlyArray<'text' | 'image'> + [OPENAI_GPT_5_CODEX_BATCH.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_5_IMAGE.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_5_IMAGE_MINI.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_MINI.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_5_MINI_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_NANO.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_5_NANO_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_PRO.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_5_PRO_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_5_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_1.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_GPT_5_1_CHAT.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_1_CODEX.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_5_1_CODEX_MAX.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_5_1_CODEX_MINI.id]: ReadonlyArray<'image' | 'text'> + [OPENAI_GPT_5_1_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_5_2.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_2_CHAT.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_2_CODEX.id]: ReadonlyArray<'text' | 'image'> [OPENAI_GPT_5_2_PRO.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_GPT_5_3_CHAT.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_5_2_PRO_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_GPT_5_2_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_3_CODEX.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_4.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_4_IMAGE_2.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_GPT_5_4_MINI.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_4_MINI_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_4_NANO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_4_NANO_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_4_PRO.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_5_4_PRO_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_GPT_5_4_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_5_5.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_5_5_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_5_PRO_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_5_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_LUNA.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_LUNA_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_LUNA_PRO_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > + [OPENAI_GPT_5_6_LUNA_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_SOL.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_SOL_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_SOL_PRO_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > + [OPENAI_GPT_5_6_SOL_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_TERRA.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_TERRA_PRO.id]: ReadonlyArray<'document' | 'image' | 'text'> + [OPENAI_GPT_5_6_TERRA_PRO_BATCH.id]: ReadonlyArray< + 'document' | 'image' | 'text' + > + [OPENAI_GPT_5_6_TERRA_BATCH.id]: ReadonlyArray<'document' | 'image' | 'text'> [OPENAI_GPT_AUDIO.id]: ReadonlyArray<'text' | 'audio'> [OPENAI_GPT_AUDIO_MINI.id]: ReadonlyArray<'text' | 'audio'> [OPENAI_GPT_CHAT_LATEST.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_GPT_OSS_120B.id]: ReadonlyArray<'text'> - [OPENAI_GPT_OSS_120B_FREE.id]: ReadonlyArray<'text'> [OPENAI_GPT_OSS_20B.id]: ReadonlyArray<'text'> [OPENAI_GPT_OSS_20B_FREE.id]: ReadonlyArray<'text'> [OPENAI_GPT_OSS_SAFEGUARD_20B.id]: ReadonlyArray<'text'> [OPENAI_O1.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_O1_PRO.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_O1_PRO_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> + [OPENAI_O1_BATCH.id]: ReadonlyArray<'text' | 'image' | 'document'> [OPENAI_O3.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_O3_DEEP_RESEARCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_O3_MINI.id]: ReadonlyArray<'text' | 'document'> [OPENAI_O3_MINI_HIGH.id]: ReadonlyArray<'text' | 'document'> + [OPENAI_O3_MINI_HIGH_BATCH.id]: ReadonlyArray<'text' | 'document'> + [OPENAI_O3_MINI_BATCH.id]: ReadonlyArray<'text' | 'document'> [OPENAI_O3_PRO.id]: ReadonlyArray<'text' | 'document' | 'image'> + [OPENAI_O3_PRO_BATCH.id]: ReadonlyArray<'text' | 'document' | 'image'> + [OPENAI_O3_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [OPENAI_O4_MINI.id]: ReadonlyArray<'image' | 'text' | 'document'> - [OPENAI_O4_MINI_DEEP_RESEARCH.id]: ReadonlyArray< - 'document' | 'image' | 'text' - > [OPENAI_O4_MINI_HIGH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_O4_MINI_HIGH_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> + [OPENAI_O4_MINI_BATCH.id]: ReadonlyArray<'image' | 'text' | 'document'> [PERCEPTRON_PERCEPTRON_MK1.id]: ReadonlyArray<'text' | 'image' | 'video'> [PERPLEXITY_SONAR.id]: ReadonlyArray<'text' | 'image'> [PERPLEXITY_SONAR_DEEP_RESEARCH.id]: ReadonlyArray<'text'> [PERPLEXITY_SONAR_PRO.id]: ReadonlyArray<'text' | 'image'> [PERPLEXITY_SONAR_PRO_SEARCH.id]: ReadonlyArray<'text' | 'image'> [PERPLEXITY_SONAR_REASONING_PRO.id]: ReadonlyArray<'text' | 'image'> - [POOLSIDE_LAGUNA_M_1.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_M_1_FREE.id]: ReadonlyArray<'text'> + [POOLSIDE_LAGUNA_S_2_1.id]: ReadonlyArray<'text'> + [POOLSIDE_LAGUNA_S_2_1_FREE.id]: ReadonlyArray<'text'> [POOLSIDE_LAGUNA_XS_2_1.id]: ReadonlyArray<'text'> [POOLSIDE_LAGUNA_XS_2_1_FREE.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_XS_2.id]: ReadonlyArray<'text'> - [POOLSIDE_LAGUNA_XS_2_FREE.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_72B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_7B_INSTRUCT.id]: ReadonlyArray<'text'> [QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id]: ReadonlyArray<'text'> @@ -15465,11 +18696,9 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_CODER_FLASH.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_NEXT.id]: ReadonlyArray<'text'> [QWEN_QWEN3_CODER_PLUS.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_CODER_FREE.id]: ReadonlyArray<'text'> [QWEN_QWEN3_MAX.id]: ReadonlyArray<'text'> [QWEN_QWEN3_MAX_THINKING.id]: ReadonlyArray<'text'> [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id]: ReadonlyArray<'text'> - [QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT_FREE.id]: ReadonlyArray<'text'> [QWEN_QWEN3_NEXT_80B_A3B_THINKING.id]: ReadonlyArray<'text'> [QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id]: ReadonlyArray<'text' | 'image'> [QWEN_QWEN3_VL_235B_A22B_THINKING.id]: ReadonlyArray<'text' | 'image'> @@ -15491,34 +18720,42 @@ export type OpenRouterModelInputModalitiesByName = { [QWEN_QWEN3_6_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_6_MAX_PREVIEW.id]: ReadonlyArray<'text'> [QWEN_QWEN3_6_PLUS.id]: ReadonlyArray<'text' | 'image' | 'video'> + [QWEN_QWEN3_7_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> [QWEN_QWEN3_7_MAX.id]: ReadonlyArray<'text'> [QWEN_QWEN3_7_PLUS.id]: ReadonlyArray<'text' | 'image'> + [QWEN_QWEN3_8_2_4T_A95B.id]: ReadonlyArray<'text'> + [QWEN_QWEN3_8_27B.id]: ReadonlyArray<'text' | 'image' | 'video'> + [QWEN_QWEN3_8_MAX.id]: ReadonlyArray<'text' | 'image' | 'video'> [REKAAI_REKA_EDGE.id]: ReadonlyArray<'image' | 'text' | 'video'> [REKAAI_REKA_FLASH_3.id]: ReadonlyArray<'text'> [RELACE_RELACE_APPLY_3.id]: ReadonlyArray<'text'> [RELACE_RELACE_SEARCH.id]: ReadonlyArray<'text'> [SAKANA_FUGU_ULTRA.id]: ReadonlyArray<'text' | 'image'> + [SAKANA_SAKANA_NAMAZU.id]: ReadonlyArray<'text' | 'image' | 'document'> [SAO10K_L3_LUNARIS_8B.id]: ReadonlyArray<'text'> - [SAO10K_L3_1_70B_HANAMI_X1.id]: ReadonlyArray<'text'> [SAO10K_L3_1_EURYALE_70B.id]: ReadonlyArray<'text'> [SAO10K_L3_3_EURYALE_70B.id]: ReadonlyArray<'text'> [STEPFUN_STEP_3_5_FLASH.id]: ReadonlyArray<'text'> [STEPFUN_STEP_3_7_FLASH.id]: ReadonlyArray<'text' | 'image' | 'video'> - [SWITCHPOINT_ROUTER.id]: ReadonlyArray<'text'> [TENCENT_HUNYUAN_A13B_INSTRUCT.id]: ReadonlyArray<'text'> [TENCENT_HY3.id]: ReadonlyArray<'text'> [TENCENT_HY3_PREVIEW.id]: ReadonlyArray<'text'> - [TENCENT_HY3_FREE.id]: ReadonlyArray<'text'> [THEDRUMMER_CYDONIA_24B_V4_1.id]: ReadonlyArray<'text'> [THEDRUMMER_ROCINANTE_12B.id]: ReadonlyArray<'text'> [THEDRUMMER_SKYFALL_36B_V2.id]: ReadonlyArray<'text'> [THEDRUMMER_UNSLOPNEMO_12B.id]: ReadonlyArray<'text'> + [THINKINGMACHINES_INKLING.id]: ReadonlyArray<'text' | 'image' | 'audio'> + [THINKINGMACHINES_INKLING_SMALL.id]: ReadonlyArray<'text' | 'image' | 'audio'> + [THINKINGMACHINES_INKLING_BATCH.id]: ReadonlyArray<'text' | 'image' | 'audio'> [UNDI95_REMM_SLERP_L2_13B.id]: ReadonlyArray<'text'> [UPSTAGE_SOLAR_PRO_3.id]: ReadonlyArray<'text'> + [UPSTAGE_SOLAR_PRO4.id]: ReadonlyArray<'text'> [WRITER_PALMYRA_X5.id]: ReadonlyArray<'text'> [X_AI_GROK_4_20.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_4_20_MULTI_AGENT.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_4_3.id]: ReadonlyArray<'text' | 'image' | 'document'> + [X_AI_GROK_4_5.id]: ReadonlyArray<'text' | 'image' | 'document'> + [X_AI_GROK_4_6.id]: ReadonlyArray<'text' | 'image' | 'document'> [X_AI_GROK_BUILD_0_1.id]: ReadonlyArray<'text' | 'image' | 'document'> [XIAOMI_MIMO_V2_5.id]: ReadonlyArray<'text' | 'audio' | 'image' | 'video'> [XIAOMI_MIMO_V2_5_PRO.id]: ReadonlyArray<'text'> @@ -15533,6 +18770,7 @@ export type OpenRouterModelInputModalitiesByName = { [Z_AI_GLM_5_TURBO.id]: ReadonlyArray<'text'> [Z_AI_GLM_5_1.id]: ReadonlyArray<'text'> [Z_AI_GLM_5_2.id]: ReadonlyArray<'text'> + [Z_AI_GLM_5_2_BATCH.id]: ReadonlyArray<'text'> [Z_AI_GLM_5V_TURBO.id]: ReadonlyArray<'image' | 'text' | 'video'> 'openrouter/auto': ReadonlyArray< 'text' | 'image' | 'audio' | 'video' | 'document' @@ -15544,11 +18782,13 @@ export const OPENROUTER_CHAT_MODELS = [ _ANTHROPIC_CLAUDE_HAIKU_LATEST.id, _ANTHROPIC_CLAUDE_OPUS_LATEST.id, _ANTHROPIC_CLAUDE_SONNET_LATEST.id, + _DEEPSEEK_DEEPSEEK_V4_FLASH_LATEST.id, _GOOGLE_GEMINI_FLASH_LATEST.id, _GOOGLE_GEMINI_PRO_LATEST.id, _MOONSHOTAI_KIMI_LATEST.id, _OPENAI_GPT_LATEST.id, _OPENAI_GPT_MINI_LATEST.id, + _X_AI_GROK_LATEST.id, AI21_JAMBA_LARGE_1_7.id, AION_LABS_AION_2_0.id, AION_LABS_AION_3_0.id, @@ -15563,30 +18803,43 @@ export const OPENROUTER_CHAT_MODELS = [ ANTHRACITE_ORG_MAGNUM_V4_72B.id, ANTHROPIC_CLAUDE_3_HAIKU.id, ANTHROPIC_CLAUDE_FABLE_5.id, + ANTHROPIC_CLAUDE_FABLE_5_BATCH.id, ANTHROPIC_CLAUDE_HAIKU_4_5.id, + ANTHROPIC_CLAUDE_HAIKU_4_5_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4.id, ANTHROPIC_CLAUDE_OPUS_4_1.id, + ANTHROPIC_CLAUDE_OPUS_4_1_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_5.id, + ANTHROPIC_CLAUDE_OPUS_4_5_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_6.id, + ANTHROPIC_CLAUDE_OPUS_4_6_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_7.id, ANTHROPIC_CLAUDE_OPUS_4_7_FAST.id, + ANTHROPIC_CLAUDE_OPUS_4_7_BATCH.id, ANTHROPIC_CLAUDE_OPUS_4_8.id, ANTHROPIC_CLAUDE_OPUS_4_8_FAST.id, + ANTHROPIC_CLAUDE_OPUS_4_8_BATCH.id, + ANTHROPIC_CLAUDE_OPUS_5.id, + ANTHROPIC_CLAUDE_OPUS_5_FAST.id, + ANTHROPIC_CLAUDE_OPUS_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_4.id, ANTHROPIC_CLAUDE_SONNET_4_5.id, + ANTHROPIC_CLAUDE_SONNET_4_5_BATCH.id, ANTHROPIC_CLAUDE_SONNET_4_6.id, + ANTHROPIC_CLAUDE_SONNET_4_6_BATCH.id, ANTHROPIC_CLAUDE_SONNET_5.id, - ARCEE_AI_CODER_LARGE.id, + ANTHROPIC_CLAUDE_SONNET_5_BATCH.id, ARCEE_AI_TRINITY_LARGE_THINKING.id, - ARCEE_AI_TRINITY_MINI.id, ARCEE_AI_VIRTUOSO_LARGE.id, BAIDU_ERNIE_4_5_VL_424B_A47B.id, BYTEDANCE_SEED_SEED_1_6.id, BYTEDANCE_SEED_SEED_1_6_FLASH.id, + BYTEDANCE_SEED_SEED_2_1_TURBO.id, + BYTEDANCE_SEED_SEED_2_0_CODE.id, BYTEDANCE_SEED_SEED_2_0_LITE.id, BYTEDANCE_SEED_SEED_2_0_MINI.id, BYTEDANCE_UI_TARS_1_5_7B.id, - COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION_FREE.id, + COGNITIVECOMPUTATIONS_DOLPHIN_MISTRAL_24B_VENICE_EDITION.id, COHERE_COMMAND_A.id, COHERE_COMMAND_R_08_2024.id, COHERE_COMMAND_R_PLUS_08_2024.id, @@ -15603,15 +18856,21 @@ export const OPENROUTER_CHAT_MODELS = [ DEEPSEEK_DEEPSEEK_V3_2.id, DEEPSEEK_DEEPSEEK_V3_2_EXP.id, DEEPSEEK_DEEPSEEK_V4_FLASH.id, + DEEPSEEK_DEEPSEEK_V4_FLASH_0731.id, DEEPSEEK_DEEPSEEK_V4_PRO.id, + DEEPSEEK_DEEPSEEK_V4_PRO_0813.id, + DOTS_STUDIO_DOTS_3_NOTE_PREVIEW_FREE.id, GOOGLE_GEMINI_2_5_FLASH.id, GOOGLE_GEMINI_2_5_FLASH_IMAGE.id, GOOGLE_GEMINI_2_5_FLASH_LITE.id, - GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_09_2025.id, + GOOGLE_GEMINI_2_5_FLASH_LITE_BATCH.id, + GOOGLE_GEMINI_2_5_FLASH_BATCH.id, GOOGLE_GEMINI_2_5_PRO.id, GOOGLE_GEMINI_2_5_PRO_PREVIEW.id, GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06.id, + GOOGLE_GEMINI_2_5_PRO_BATCH.id, GOOGLE_GEMINI_3_FLASH_PREVIEW.id, + GOOGLE_GEMINI_3_FLASH_PREVIEW_BATCH.id, GOOGLE_GEMINI_3_PRO_IMAGE.id, GOOGLE_GEMINI_3_PRO_IMAGE_PREVIEW.id, GOOGLE_GEMINI_3_1_FLASH_IMAGE.id, @@ -15619,9 +18878,18 @@ export const OPENROUTER_CHAT_MODELS = [ GOOGLE_GEMINI_3_1_FLASH_LITE.id, GOOGLE_GEMINI_3_1_FLASH_LITE_IMAGE.id, GOOGLE_GEMINI_3_1_FLASH_LITE_PREVIEW.id, + GOOGLE_GEMINI_3_1_FLASH_LITE_BATCH.id, GOOGLE_GEMINI_3_1_PRO_PREVIEW.id, GOOGLE_GEMINI_3_1_PRO_PREVIEW_CUSTOMTOOLS.id, + GOOGLE_GEMINI_3_1_PRO_PREVIEW_BATCH.id, GOOGLE_GEMINI_3_5_FLASH.id, + GOOGLE_GEMINI_3_5_FLASH_LITE.id, + GOOGLE_GEMINI_3_5_FLASH_LITE_BATCH.id, + GOOGLE_GEMINI_3_5_FLASH_BATCH.id, + GOOGLE_GEMINI_3_6_FLASH.id, + GOOGLE_GEMINI_3_6_FLASH_BATCH.id, + GOOGLE_GEMINI_3_7_FLASH.id, + GOOGLE_GEMINI_3_7_FLASH_BATCH.id, GOOGLE_GEMMA_2_27B_IT.id, GOOGLE_GEMMA_3_12B_IT.id, GOOGLE_GEMMA_3_27B_IT.id, @@ -15637,26 +18905,25 @@ export const OPENROUTER_CHAT_MODELS = [ INCEPTION_MERCURY_2.id, INCLUSIONAI_LING_2_6_1T.id, INCLUSIONAI_LING_2_6_FLASH.id, + INCLUSIONAI_LING_3_0_FLASH.id, INCLUSIONAI_RING_2_6_1T.id, - INFLECTION_INFLECTION_3_PI.id, - INFLECTION_INFLECTION_3_PRODUCTIVITY.id, + KWAIPILOT_KAT_CODER_AIR_V2_5.id, KWAIPILOT_KAT_CODER_PRO_V2.id, - LIQUID_LFM_2_24B_A2B.id, - LIQUID_LFM_2_5_1_2B_INSTRUCT_FREE.id, - LIQUID_LFM_2_5_1_2B_THINKING_FREE.id, + KWAIPILOT_KAT_CODER_PRO_V2_5.id, + LIQUID_LFM_2_5_2_6B_FREE.id, MANCER_WEAVER.id, - META_LLAMA_LLAMA_3_8B_INSTRUCT.id, + MEITUAN_LONGCAT_2_0.id, META_LLAMA_LLAMA_3_1_70B_INSTRUCT.id, META_LLAMA_LLAMA_3_1_8B_INSTRUCT.id, - META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT.id, META_LLAMA_LLAMA_3_2_1B_INSTRUCT.id, META_LLAMA_LLAMA_3_2_3B_INSTRUCT.id, - META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE.id, META_LLAMA_LLAMA_3_3_70B_INSTRUCT.id, - META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE.id, META_LLAMA_LLAMA_4_MAVERICK.id, META_LLAMA_LLAMA_4_SCOUT.id, META_LLAMA_LLAMA_GUARD_4_12B.id, + META_MUSE_GLIMMER_30B.id, + META_MUSE_SPARK_1_1.id, + META_MUSE_SPARK_1_2.id, MICROSOFT_PHI_4.id, MICROSOFT_WIZARDLM_2_8X22B.id, MINIMAX_MINIMAX_01.id, @@ -15667,8 +18934,8 @@ export const OPENROUTER_CHAT_MODELS = [ MINIMAX_MINIMAX_M2_5.id, MINIMAX_MINIMAX_M2_7.id, MINIMAX_MINIMAX_M3.id, + MINIMAX_MINIMAX_M3_BATCH.id, MISTRALAI_CODESTRAL_2508.id, - MISTRALAI_DEVSTRAL_2512.id, MISTRALAI_MINISTRAL_14B_2512.id, MISTRALAI_MINISTRAL_3B_2512.id, MISTRALAI_MINISTRAL_8B_2512.id, @@ -15692,100 +18959,133 @@ export const OPENROUTER_CHAT_MODELS = [ MOONSHOTAI_KIMI_K2_5.id, MOONSHOTAI_KIMI_K2_6.id, MOONSHOTAI_KIMI_K2_7_CODE.id, + MOONSHOTAI_KIMI_K2_7_CODE_BATCH.id, + MOONSHOTAI_KIMI_K3.id, MORPH_MORPH_V3_FAST.id, MORPH_MORPH_V3_LARGE.id, NEX_AGI_NEX_N2_MINI.id, NEX_AGI_NEX_N2_PRO.id, NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B.id, - NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B_FREE.id, NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B.id, NOUSRESEARCH_HERMES_4_405B.id, NOUSRESEARCH_HERMES_4_70B.id, - NVIDIA_LLAMA_3_3_NEMOTRON_SUPER_49B_V1_5.id, NVIDIA_NEMOTRON_3_NANO_30B_A3B.id, NVIDIA_NEMOTRON_3_NANO_30B_A3B_FREE.id, NVIDIA_NEMOTRON_3_NANO_OMNI_30B_A3B_REASONING_FREE.id, NVIDIA_NEMOTRON_3_SUPER_120B_A12B.id, NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE.id, NVIDIA_NEMOTRON_3_ULTRA_550B_A55B.id, + NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_BATCH.id, NVIDIA_NEMOTRON_3_ULTRA_550B_A55B_FREE.id, NVIDIA_NEMOTRON_3_5_CONTENT_SAFETY_FREE.id, + NVIDIA_NEMOTRON_3_5_LIGHTNING.id, + NVIDIA_NEMOTRON_3_5_LIGHTNING_FREE.id, NVIDIA_NEMOTRON_NANO_12B_V2_VL_FREE.id, NVIDIA_NEMOTRON_NANO_9B_V2_FREE.id, OPENAI_GPT_3_5_TURBO.id, OPENAI_GPT_3_5_TURBO_0613.id, OPENAI_GPT_3_5_TURBO_16K.id, OPENAI_GPT_3_5_TURBO_INSTRUCT.id, + OPENAI_GPT_3_5_TURBO_BATCH.id, OPENAI_GPT_4.id, OPENAI_GPT_4_TURBO.id, OPENAI_GPT_4_TURBO_PREVIEW.id, + OPENAI_GPT_4_TURBO_BATCH.id, OPENAI_GPT_4_1.id, OPENAI_GPT_4_1_MINI.id, + OPENAI_GPT_4_1_MINI_BATCH.id, OPENAI_GPT_4_1_NANO.id, + OPENAI_GPT_4_1_NANO_BATCH.id, + OPENAI_GPT_4_1_BATCH.id, OPENAI_GPT_4O.id, OPENAI_GPT_4O_2024_05_13.id, OPENAI_GPT_4O_2024_08_06.id, OPENAI_GPT_4O_2024_11_20.id, OPENAI_GPT_4O_MINI.id, OPENAI_GPT_4O_MINI_2024_07_18.id, - OPENAI_GPT_4O_MINI_SEARCH_PREVIEW.id, - OPENAI_GPT_4O_SEARCH_PREVIEW.id, + OPENAI_GPT_4O_MINI_BATCH.id, + OPENAI_GPT_4O_BATCH.id, OPENAI_GPT_5.id, - OPENAI_GPT_5_CHAT.id, - OPENAI_GPT_5_CODEX.id, + OPENAI_GPT_5_CODEX_BATCH.id, OPENAI_GPT_5_IMAGE.id, OPENAI_GPT_5_IMAGE_MINI.id, OPENAI_GPT_5_MINI.id, + OPENAI_GPT_5_MINI_BATCH.id, OPENAI_GPT_5_NANO.id, + OPENAI_GPT_5_NANO_BATCH.id, OPENAI_GPT_5_PRO.id, + OPENAI_GPT_5_PRO_BATCH.id, + OPENAI_GPT_5_BATCH.id, OPENAI_GPT_5_1.id, - OPENAI_GPT_5_1_CHAT.id, OPENAI_GPT_5_1_CODEX.id, OPENAI_GPT_5_1_CODEX_MAX.id, OPENAI_GPT_5_1_CODEX_MINI.id, + OPENAI_GPT_5_1_BATCH.id, OPENAI_GPT_5_2.id, OPENAI_GPT_5_2_CHAT.id, OPENAI_GPT_5_2_CODEX.id, OPENAI_GPT_5_2_PRO.id, - OPENAI_GPT_5_3_CHAT.id, + OPENAI_GPT_5_2_PRO_BATCH.id, + OPENAI_GPT_5_2_BATCH.id, OPENAI_GPT_5_3_CODEX.id, OPENAI_GPT_5_4.id, OPENAI_GPT_5_4_IMAGE_2.id, OPENAI_GPT_5_4_MINI.id, + OPENAI_GPT_5_4_MINI_BATCH.id, OPENAI_GPT_5_4_NANO.id, + OPENAI_GPT_5_4_NANO_BATCH.id, OPENAI_GPT_5_4_PRO.id, + OPENAI_GPT_5_4_PRO_BATCH.id, + OPENAI_GPT_5_4_BATCH.id, OPENAI_GPT_5_5.id, OPENAI_GPT_5_5_PRO.id, + OPENAI_GPT_5_5_PRO_BATCH.id, + OPENAI_GPT_5_5_BATCH.id, + OPENAI_GPT_5_6_LUNA.id, + OPENAI_GPT_5_6_LUNA_PRO.id, + OPENAI_GPT_5_6_LUNA_PRO_BATCH.id, + OPENAI_GPT_5_6_LUNA_BATCH.id, + OPENAI_GPT_5_6_SOL.id, + OPENAI_GPT_5_6_SOL_PRO.id, + OPENAI_GPT_5_6_SOL_PRO_BATCH.id, + OPENAI_GPT_5_6_SOL_BATCH.id, + OPENAI_GPT_5_6_TERRA.id, + OPENAI_GPT_5_6_TERRA_PRO.id, + OPENAI_GPT_5_6_TERRA_PRO_BATCH.id, + OPENAI_GPT_5_6_TERRA_BATCH.id, OPENAI_GPT_AUDIO.id, OPENAI_GPT_AUDIO_MINI.id, OPENAI_GPT_CHAT_LATEST.id, OPENAI_GPT_OSS_120B.id, - OPENAI_GPT_OSS_120B_FREE.id, OPENAI_GPT_OSS_20B.id, OPENAI_GPT_OSS_20B_FREE.id, OPENAI_GPT_OSS_SAFEGUARD_20B.id, OPENAI_O1.id, OPENAI_O1_PRO.id, + OPENAI_O1_PRO_BATCH.id, + OPENAI_O1_BATCH.id, OPENAI_O3.id, - OPENAI_O3_DEEP_RESEARCH.id, OPENAI_O3_MINI.id, OPENAI_O3_MINI_HIGH.id, + OPENAI_O3_MINI_HIGH_BATCH.id, + OPENAI_O3_MINI_BATCH.id, OPENAI_O3_PRO.id, + OPENAI_O3_PRO_BATCH.id, + OPENAI_O3_BATCH.id, OPENAI_O4_MINI.id, - OPENAI_O4_MINI_DEEP_RESEARCH.id, OPENAI_O4_MINI_HIGH.id, + OPENAI_O4_MINI_HIGH_BATCH.id, + OPENAI_O4_MINI_BATCH.id, PERCEPTRON_PERCEPTRON_MK1.id, PERPLEXITY_SONAR.id, PERPLEXITY_SONAR_DEEP_RESEARCH.id, PERPLEXITY_SONAR_PRO.id, PERPLEXITY_SONAR_PRO_SEARCH.id, PERPLEXITY_SONAR_REASONING_PRO.id, - POOLSIDE_LAGUNA_M_1.id, - POOLSIDE_LAGUNA_M_1_FREE.id, + POOLSIDE_LAGUNA_S_2_1.id, + POOLSIDE_LAGUNA_S_2_1_FREE.id, POOLSIDE_LAGUNA_XS_2_1.id, POOLSIDE_LAGUNA_XS_2_1_FREE.id, - POOLSIDE_LAGUNA_XS_2.id, - POOLSIDE_LAGUNA_XS_2_FREE.id, QWEN_QWEN_2_5_72B_INSTRUCT.id, QWEN_QWEN_2_5_7B_INSTRUCT.id, QWEN_QWEN_2_5_CODER_32B_INSTRUCT.id, @@ -15807,11 +19107,9 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN3_CODER_FLASH.id, QWEN_QWEN3_CODER_NEXT.id, QWEN_QWEN3_CODER_PLUS.id, - QWEN_QWEN3_CODER_FREE.id, QWEN_QWEN3_MAX.id, QWEN_QWEN3_MAX_THINKING.id, QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT.id, - QWEN_QWEN3_NEXT_80B_A3B_INSTRUCT_FREE.id, QWEN_QWEN3_NEXT_80B_A3B_THINKING.id, QWEN_QWEN3_VL_235B_A22B_INSTRUCT.id, QWEN_QWEN3_VL_235B_A22B_THINKING.id, @@ -15833,34 +19131,42 @@ export const OPENROUTER_CHAT_MODELS = [ QWEN_QWEN3_6_FLASH.id, QWEN_QWEN3_6_MAX_PREVIEW.id, QWEN_QWEN3_6_PLUS.id, + QWEN_QWEN3_7_FLASH.id, QWEN_QWEN3_7_MAX.id, QWEN_QWEN3_7_PLUS.id, + QWEN_QWEN3_8_2_4T_A95B.id, + QWEN_QWEN3_8_27B.id, + QWEN_QWEN3_8_MAX.id, REKAAI_REKA_EDGE.id, REKAAI_REKA_FLASH_3.id, RELACE_RELACE_APPLY_3.id, RELACE_RELACE_SEARCH.id, SAKANA_FUGU_ULTRA.id, + SAKANA_SAKANA_NAMAZU.id, SAO10K_L3_LUNARIS_8B.id, - SAO10K_L3_1_70B_HANAMI_X1.id, SAO10K_L3_1_EURYALE_70B.id, SAO10K_L3_3_EURYALE_70B.id, STEPFUN_STEP_3_5_FLASH.id, STEPFUN_STEP_3_7_FLASH.id, - SWITCHPOINT_ROUTER.id, TENCENT_HUNYUAN_A13B_INSTRUCT.id, TENCENT_HY3.id, TENCENT_HY3_PREVIEW.id, - TENCENT_HY3_FREE.id, THEDRUMMER_CYDONIA_24B_V4_1.id, THEDRUMMER_ROCINANTE_12B.id, THEDRUMMER_SKYFALL_36B_V2.id, THEDRUMMER_UNSLOPNEMO_12B.id, + THINKINGMACHINES_INKLING.id, + THINKINGMACHINES_INKLING_SMALL.id, + THINKINGMACHINES_INKLING_BATCH.id, UNDI95_REMM_SLERP_L2_13B.id, UPSTAGE_SOLAR_PRO_3.id, + UPSTAGE_SOLAR_PRO4.id, WRITER_PALMYRA_X5.id, X_AI_GROK_4_20.id, X_AI_GROK_4_20_MULTI_AGENT.id, X_AI_GROK_4_3.id, + X_AI_GROK_4_5.id, + X_AI_GROK_4_6.id, X_AI_GROK_BUILD_0_1.id, XIAOMI_MIMO_V2_5.id, XIAOMI_MIMO_V2_5_PRO.id, @@ -15875,6 +19181,7 @@ export const OPENROUTER_CHAT_MODELS = [ Z_AI_GLM_5_TURBO.id, Z_AI_GLM_5_1.id, Z_AI_GLM_5_2.id, + Z_AI_GLM_5_2_BATCH.id, Z_AI_GLM_5V_TURBO.id, 'openrouter/auto', ] as const diff --git a/packages/ai-vercel-gateway/src/model-meta.ts b/packages/ai-vercel-gateway/src/model-meta.ts index 9f291fff4a..b7994aef8b 100644 --- a/packages/ai-vercel-gateway/src/model-meta.ts +++ b/packages/ai-vercel-gateway/src/model-meta.ts @@ -39,6 +39,7 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'alibaba/qwen3.7-flash', 'alibaba/qwen3.7-max', 'alibaba/qwen3.7-plus', + 'alibaba/qwen3.8-2.4t-a95b', 'alibaba/qwen3.8-max', 'amazon/nova-2-lite', 'amazon/nova-lite', @@ -73,6 +74,7 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'deepseek/deepseek-v4-flash', 'deepseek/deepseek-v4-flash-0731', 'deepseek/deepseek-v4-pro', + 'deepseek/deepseek-v4-pro-0813', 'fish-audio/s1', 'fish-audio/s2-pro', 'fish-audio/s2.1-pro', @@ -91,13 +93,13 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'google/gemini-3.5-flash', 'google/gemini-3.5-flash-lite', 'google/gemini-3.6-flash', + 'google/gemini-3.7-flash', 'google/gemini-omni-flash-preview', 'google/gemma-4-26b-a4b-it', 'google/gemma-4-31b-it', 'inception/mercury-2', 'inception/mercury-coder-small', 'inclusionai/ling-3.0-flash', - 'inclusionai/ling-3.0-tiny-free', 'interfaze/interfaze-beta', 'kwaipilot/kat-coder-air-v2.5', 'kwaipilot/kat-coder-pro-v1', @@ -220,6 +222,7 @@ export const VERCEL_GATEWAY_CHAT_MODELS = [ 'xai/grok-4.20-reasoning-beta', 'xai/grok-4.3', 'xai/grok-4.5', + 'xai/grok-4.6', 'xai/grok-build-0.1', 'xai/grok-stt', 'xai/grok-tts', @@ -297,6 +300,7 @@ export const VERCEL_GATEWAY_MODEL_TAGS = [ 'structured-output', 'tool-use', 'video-generation', + 'video-input', 'vision', 'web-search', 'websocket-realtime', @@ -582,6 +586,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'reasoning' | 'include_reasoning' > + 'alibaba/qwen3.8-2.4t-a95b': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'reasoning' + | 'include_reasoning' + > 'alibaba/qwen3.8-max': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -877,6 +891,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'reasoning' | 'include_reasoning' > + 'deepseek/deepseek-v4-pro-0813': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'reasoning' + | 'include_reasoning' + > 'fish-audio/s1': VercelGatewayCommonOptions 'fish-audio/s2-pro': VercelGatewayCommonOptions 'fish-audio/s2.1-pro': VercelGatewayCommonOptions @@ -1011,6 +1035,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'reasoning' | 'include_reasoning' > + 'google/gemini-3.7-flash': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'reasoning' + | 'include_reasoning' + > 'google/gemini-omni-flash-preview': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -1066,16 +1100,6 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'reasoning' | 'include_reasoning' > - 'inclusionai/ling-3.0-tiny-free': VercelGatewayCommonOptions & - Pick< - VercelGatewayBaseOptions, - | 'max_tokens' - | 'max_output_tokens' - | 'temperature' - | 'stop' - | 'reasoning' - | 'include_reasoning' - > 'interfaze/interfaze-beta': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2048,6 +2072,16 @@ export type VercelGatewayChatModelProviderOptionsByName = { | 'reasoning' | 'include_reasoning' > + 'xai/grok-4.6': VercelGatewayCommonOptions & + Pick< + VercelGatewayBaseOptions, + | 'max_tokens' + | 'max_output_tokens' + | 'temperature' + | 'stop' + | 'reasoning' + | 'include_reasoning' + > 'xai/grok-build-0.1': VercelGatewayCommonOptions & Pick< VercelGatewayBaseOptions, @@ -2268,6 +2302,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'alibaba/qwen3.7-flash': readonly ['text', 'image', 'document'] 'alibaba/qwen3.7-max': readonly ['text'] 'alibaba/qwen3.7-plus': readonly ['text', 'image', 'document'] + 'alibaba/qwen3.8-2.4t-a95b': readonly ['text'] 'alibaba/qwen3.8-max': readonly ['text', 'image'] 'amazon/nova-2-lite': readonly ['text', 'image', 'document'] 'amazon/nova-lite': readonly ['text', 'image', 'document'] @@ -2302,6 +2337,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'deepseek/deepseek-v4-flash': readonly ['text'] 'deepseek/deepseek-v4-flash-0731': readonly ['text'] 'deepseek/deepseek-v4-pro': readonly ['text'] + 'deepseek/deepseek-v4-pro-0813': readonly ['text'] 'fish-audio/s1': readonly ['text'] 'fish-audio/s2-pro': readonly ['text'] 'fish-audio/s2.1-pro': readonly ['text'] @@ -2317,16 +2353,21 @@ export type VercelGatewayModelInputModalitiesByName = { 'google/gemini-3.1-flash-lite': readonly ['text', 'image', 'document'] 'google/gemini-3.1-flash-lite-image': readonly ['text', 'image'] 'google/gemini-3.1-pro-preview': readonly ['text', 'image', 'document'] - 'google/gemini-3.5-flash': readonly ['text', 'image', 'document'] - 'google/gemini-3.5-flash-lite': readonly ['text', 'image', 'document'] - 'google/gemini-3.6-flash': readonly ['text', 'image', 'document'] + 'google/gemini-3.5-flash': readonly ['text', 'image', 'document', 'video'] + 'google/gemini-3.5-flash-lite': readonly [ + 'text', + 'image', + 'document', + 'video', + ] + 'google/gemini-3.6-flash': readonly ['text', 'image', 'document', 'video'] + 'google/gemini-3.7-flash': readonly ['text', 'image', 'document', 'video'] 'google/gemini-omni-flash-preview': readonly ['text', 'image', 'document'] 'google/gemma-4-26b-a4b-it': readonly ['text', 'image', 'document'] 'google/gemma-4-31b-it': readonly ['text', 'image', 'document'] 'inception/mercury-2': readonly ['text'] 'inception/mercury-coder-small': readonly ['text'] 'inclusionai/ling-3.0-flash': readonly ['text'] - 'inclusionai/ling-3.0-tiny-free': readonly ['text'] 'interfaze/interfaze-beta': readonly ['text', 'image', 'document'] 'kwaipilot/kat-coder-air-v2.5': readonly ['text', 'image'] 'kwaipilot/kat-coder-pro-v1': readonly ['text'] @@ -2365,11 +2406,16 @@ export type VercelGatewayModelInputModalitiesByName = { 'mistral/pixtral-12b': readonly ['text', 'image'] 'moonshotai/kimi-k2': readonly ['text'] 'moonshotai/kimi-k2-thinking': readonly ['text'] - 'moonshotai/kimi-k2.5': readonly ['text', 'image'] - 'moonshotai/kimi-k2.6': readonly ['text', 'image'] - 'moonshotai/kimi-k2.7-code': readonly ['text', 'image', 'document'] - 'moonshotai/kimi-k2.7-code-highspeed': readonly ['text', 'image', 'document'] - 'moonshotai/kimi-k3': readonly ['text', 'image', 'document'] + 'moonshotai/kimi-k2.5': readonly ['text', 'image', 'video'] + 'moonshotai/kimi-k2.6': readonly ['text', 'image', 'video'] + 'moonshotai/kimi-k2.7-code': readonly ['text', 'image', 'document', 'video'] + 'moonshotai/kimi-k2.7-code-highspeed': readonly [ + 'text', + 'image', + 'document', + 'video', + ] + 'moonshotai/kimi-k3': readonly ['text', 'image', 'document', 'video'] 'moonshotai/kimi-k3-fast': readonly ['text', 'image', 'document'] 'morph/morph-v3-fast': readonly ['text'] 'morph/morph-v3-large': readonly ['text'] @@ -2449,6 +2495,7 @@ export type VercelGatewayModelInputModalitiesByName = { 'xai/grok-4.20-reasoning-beta': readonly ['text', 'image', 'document'] 'xai/grok-4.3': readonly ['text', 'image', 'document'] 'xai/grok-4.5': readonly ['text', 'image', 'document'] + 'xai/grok-4.6': readonly ['text', 'image'] 'xai/grok-build-0.1': readonly ['text', 'image'] 'xai/grok-stt': readonly ['text', 'audio'] 'xai/grok-tts': readonly ['text'] diff --git a/scripts/.sync-models-last-run b/scripts/.sync-models-last-run index d5e67f0f54..332ef47620 100644 --- a/scripts/.sync-models-last-run +++ b/scripts/.sync-models-last-run @@ -1 +1 @@ -1783497813 +1786861125 diff --git a/scripts/openrouter.models.json b/scripts/openrouter.models.json index 4b67abce89..b9cef2a5c4 100644 --- a/scripts/openrouter.models.json +++ b/scripts/openrouter.models.json @@ -2,6 +2,10 @@ { "id": "~anthropic/claude-fable-latest", "canonical_slug": "~anthropic/claude-fable-latest", + "alias_target": { + "name": "Anthropic: Claude Fable 5", + "slug": "anthropic/claude-fable-5" + }, "hugging_face_id": null, "name": "Anthropic: Claude Fable Latest", "created": 1781029944, @@ -19,12 +23,13 @@ "completion": "0.00005", "web_search": "0.01", "input_cache_read": "0.000001", - "input_cache_write": "0.0000125" + "input_cache_write": "0.0000125", + "input_cache_write_1h": "0.00002" }, "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -32,6 +37,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", @@ -56,12 +62,16 @@ "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "default_effort": "high" } }, { "id": "~anthropic/claude-haiku-latest", "canonical_slug": "~anthropic/claude-haiku-latest", + "alias_target": { + "name": "Anthropic: Claude Haiku 4.5", + "slug": "anthropic/claude-haiku-4.5" + }, "hugging_face_id": null, "name": "Anthropic Claude Haiku Latest", "created": 1777318492, @@ -85,7 +95,7 @@ "top_provider": { "context_length": 200000, "max_completion_tokens": 64000, - "is_moderated": true + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ @@ -123,6 +133,10 @@ { "id": "~anthropic/claude-opus-latest", "canonical_slug": "~anthropic/claude-opus-latest", + "alias_target": { + "name": "Claude Opus 5", + "slug": "anthropic/claude-opus-5" + }, "hugging_face_id": "", "name": "Anthropic: Claude Opus Latest", "created": 1776795361, @@ -146,7 +160,7 @@ "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -154,6 +168,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", @@ -178,13 +193,18 @@ }, "reasoning": { "mandatory": false, + "default_enabled": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "default_effort": "high" } }, { "id": "~anthropic/claude-sonnet-latest", "canonical_slug": "~anthropic/claude-sonnet-latest", + "alias_target": { + "name": "Anthropic: Claude Sonnet 5", + "slug": "anthropic/claude-sonnet-5" + }, "hugging_face_id": null, "name": "Anthropic Claude Sonnet Latest", "created": 1777318368, @@ -208,7 +228,7 @@ "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -216,6 +236,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", @@ -239,13 +260,86 @@ }, "reasoning": { "mandatory": false, + "default_enabled": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "default_effort": "high" + } + }, + { + "id": "~deepseek/deepseek-v4-flash-latest", + "canonical_slug": "~deepseek/deepseek-v4-flash-latest", + "alias_target": { + "name": "DeepSeek: DeepSeek V4 Flash 0731", + "slug": "deepseek/deepseek-v4-flash-0731" + }, + "hugging_face_id": null, + "name": "DeepSeek V4 Flash Latest", + "created": 1785606009, + "description": "This model always redirects to the latest model in the DeepSeek V4 Flash family.", + "context_length": 1048576, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Router", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000006706", + "completion": "0.00000013412", + "input_cache_read": "0.000000013412" + }, + "top_provider": { + "context_length": 1024000, + "max_completion_tokens": 384000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": [], + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/~deepseek/deepseek-v4-flash-latest/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "high", "low"], + "default_effort": "high" } }, { "id": "~google/gemini-flash-latest", "canonical_slug": "~google/gemini-flash-latest", + "alias_target": { + "name": "Google: Gemini 3.7 Flash", + "slug": "google/gemini-3.7-flash" + }, "hugging_face_id": null, "name": "Google Gemini Flash Latest", "created": 1777318398, @@ -259,14 +353,15 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000015", - "completion": "0.000009", - "image": "0.0000015", - "audio": "0.000003", + "prompt": "0.000000375", + "completion": "0.000001875", + "image": "0.000000375", + "audio": "0.000000375", + "input_audio_cache": "0.0000000375", "web_search": "0.014", - "internal_reasoning": "0.000009", - "input_cache_read": "0.00000015", - "input_cache_write": "0.00000008333333333333334" + "internal_reasoning": "0.000001875", + "input_cache_read": "0.0000000375", + "input_cache_write": "0.0000000208333333333333" }, "top_provider": { "context_length": 1048576, @@ -278,6 +373,7 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "stop", @@ -287,16 +383,9 @@ "tools", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-01", + "knowledge_cutoff": null, "expiration_date": null, "links": { "details": "/api/v1/models/~google/gemini-flash-latest/endpoints" @@ -304,13 +393,17 @@ "reasoning": { "mandatory": true, "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["high", "medium", "low"], "default_effort": "medium" } }, { "id": "~google/gemini-pro-latest", "canonical_slug": "~google/gemini-pro-latest", + "alias_target": { + "name": "Google: Gemini 3.1 Pro Preview", + "slug": "google/gemini-3.1-pro-preview" + }, "hugging_face_id": null, "name": "Google Gemini Pro Latest", "created": 1777318451, @@ -328,10 +421,21 @@ "completion": "0.000012", "image": "0.000002", "audio": "0.000002", + "input_audio_cache": "0.0000002", "web_search": "0.014", "internal_reasoning": "0.000012", "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375" + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000018", + "audio": "0.000004", + "input_audio_cache": "0.0000004", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { "context_length": 1048576, @@ -343,6 +447,7 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "stop", @@ -375,26 +480,30 @@ { "id": "~moonshotai/kimi-latest", "canonical_slug": "~moonshotai/kimi-latest", + "alias_target": { + "name": "MoonshotAI: Kimi K3", + "slug": "moonshotai/kimi-k3" + }, "hugging_face_id": null, "name": "MoonshotAI Kimi Latest", "created": 1777318428, "description": "This model always redirects to the latest model in the MoonshotAI Kimi family.", - "context_length": 262144, + "context_length": 1048576, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Router", "instruct_type": null }, "pricing": { - "prompt": "0.00000066", - "completion": "0.00000341", - "input_cache_read": "0.00000014" + "prompt": "0.0000028", + "completion": "0.000014", + "input_cache_read": "0.00000029" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 1048576, + "max_completion_tokens": 1048576, "is_moderated": false }, "per_request_limits": null, @@ -405,9 +514,9 @@ "logprobs", "max_tokens", "min_p", - "parallel_tool_calls", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -422,7 +531,7 @@ ], "default_parameters": { "temperature": null, - "top_p": null, + "top_p": 0.95, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -436,12 +545,18 @@ }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supported_efforts": ["max", "high", "low"], + "default_effort": "max" } }, { "id": "~openai/gpt-latest", "canonical_slug": "~openai/gpt-latest", + "alias_target": { + "name": "OpenAI: GPT-5.6 Sol", + "slug": "openai/gpt-5.6-sol" + }, "hugging_face_id": null, "name": "OpenAI GPT Latest", "created": 1777318334, @@ -458,7 +573,17 @@ "prompt": "0.000005", "completion": "0.00003", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00001", + "completion": "0.000045", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125" + } + ] }, "top_provider": { "context_length": 1050000, @@ -471,6 +596,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -486,7 +612,7 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-12-01", + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { "details": "/api/v1/models/~openai/gpt-latest/endpoints" @@ -494,13 +620,17 @@ "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { "id": "~openai/gpt-mini-latest", "canonical_slug": "~openai/gpt-mini-latest", + "alias_target": { + "name": "OpenAI: GPT-5.4 Mini", + "slug": "openai/gpt-5.4-mini" + }, "hugging_face_id": null, "name": "OpenAI GPT Mini Latest", "created": 1777318471, @@ -530,6 +660,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -557,6 +688,77 @@ "default_effort": "medium" } }, + { + "id": "~x-ai/grok-latest", + "canonical_slug": "~x-ai/grok-latest", + "alias_target": { + "name": "SpaceXAI: Grok 4.6", + "slug": "x-ai/grok-4.6" + }, + "hugging_face_id": null, + "name": "xAI: Grok Latest", + "created": 1783519360, + "description": "This model always redirects to the latest Grok model from xAI.", + "context_length": 500000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Router", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000006", + "web_search": "0.005", + "input_cache_read": "0.0000005", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000012", + "input_cache_read": "0.000001" + } + ] + }, + "top_provider": { + "context_length": 500000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/~x-ai/grok-latest/endpoints" + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "high" + } + }, { "id": "ai21/jamba-large-1.7", "canonical_slug": "ai21/jamba-large-1.7", @@ -884,9 +1086,9 @@ "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 18.2, + "intelligence_index": null, "coding_index": 23, - "agentic_index": 3.1 + "agentic_index": null } }, "reasoning": { @@ -1025,9 +1227,9 @@ { "arena": "models", "category": "website", - "elo": 878, + "elo": 846, "win_rate": 26.2, - "rank": 109 + "rank": 123 } ] } @@ -1077,9 +1279,9 @@ { "arena": "models", "category": "website", - "elo": 839, + "elo": 807, "win_rate": 21.4, - "rank": 112 + "rank": 126 } ] } @@ -1104,8 +1306,8 @@ "completion": "0.000005" }, "top_provider": { - "context_length": 16384, - "max_completion_tokens": 2048, + "context_length": 32768, + "max_completion_tokens": 4096, "is_moderated": false }, "per_request_limits": null, @@ -1201,12 +1403,13 @@ "completion": "0.00005", "web_search": "0.01", "input_cache_read": "0.000001", - "input_cache_write": "0.0000125" + "input_cache_write": "0.0000125", + "input_cache_write_1h": "0.00002" }, "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -1214,6 +1417,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", @@ -1237,6 +1441,13 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1296, + "win_rate": 65.1, + "rank": 1 + }, { "arena": "agents", "category": "agentichtmlslides", @@ -1253,88 +1464,130 @@ }, { "arena": "agents", - "category": "htmlslides", - "elo": 1262, - "win_rate": 60.8, + "category": "androidnative", + "elo": 1295, + "win_rate": 63.6, "rank": 1 }, { - "arena": "models", - "category": "3d", - "elo": 1369, - "win_rate": 67.2, - "rank": 2 + "arena": "agents", + "category": "fullstack", + "elo": 1293, + "win_rate": 61.1, + "rank": 4 }, { - "arena": "models", - "category": "asciiart", - "elo": 1369, - "win_rate": 70.1, + "arena": "agents", + "category": "godotgamedev", + "elo": 1346, + "win_rate": 70.2, "rank": 1 }, { - "arena": "models", - "category": "codecategories", - "elo": 1349, - "win_rate": 63.3, - "rank": 2 + "arena": "agents", + "category": "htmlslides", + "elo": 1265, + "win_rate": 59.1, + "rank": 1 }, { - "arena": "models", - "category": "dataviz", - "elo": 1381, - "win_rate": 70.1, - "rank": 1 + "arena": "agents", + "category": "mobileapps", + "elo": 1256, + "win_rate": 56.7, + "rank": 5 }, { - "arena": "models", - "category": "gamedev", - "elo": 1379, - "win_rate": 65.1, - "rank": 1 + "arena": "agents", + "category": "python-pptxslides", + "elo": 1303, + "win_rate": 62.3, + "rank": 3 }, { - "arena": "models", - "category": "svg", - "elo": 1370, - "win_rate": 71.8, + "arena": "agents", + "category": "webapps", + "elo": 1296, + "win_rate": 59.4, + "rank": 3 + }, + { + "arena": "models", + "category": "3d", + "elo": 1373, + "win_rate": 62.5, + "rank": 4 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1353, + "win_rate": 69.2, "rank": 1 }, + { + "arena": "models", + "category": "codecategories", + "elo": 1334, + "win_rate": 59.1, + "rank": 4 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1343, + "win_rate": 58.6, + "rank": 5 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1383, + "win_rate": 62.4, + "rank": 3 + }, + { + "arena": "models", + "category": "svg", + "elo": 1340, + "win_rate": 64.3, + "rank": 2 + }, { "arena": "models", "category": "uicomponent", - "elo": 1414, - "win_rate": 71.3, - "rank": 1 + "elo": 1336, + "win_rate": 56.1, + "rank": 6 }, { "arena": "models", "category": "website", - "elo": 1341, - "win_rate": 62.5, - "rank": 2 + "elo": 1314, + "win_rate": 58.7, + "rank": 6 } ], "artificial_analysis": { - "intelligence_index": 59.9, + "intelligence_index": 62.1, "coding_index": 76.5, - "agentic_index": 52.8 + "agentic_index": 56.6 } }, "reasoning": { "mandatory": true, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "default_effort": "high" } }, { - "id": "anthropic/claude-haiku-4.5", - "canonical_slug": "anthropic/claude-4.5-haiku-20251001", - "hugging_face_id": "", - "name": "Anthropic: Claude Haiku 4.5", - "created": 1760547638, - "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...", - "context_length": 200000, + "id": "anthropic/claude-fable-5:batch", + "canonical_slug": "anthropic/claude-5-fable-20260609", + "hugging_face_id": null, + "name": "Anthropic: Claude Fable 5 (batch)", + "created": 1781007515, + "description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...", + "context_length": 1000000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -1343,32 +1596,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000005", + "prompt": "0.000005", + "completion": "0.000025", "web_search": "0.01", - "input_cache_read": "0.0000001", - "input_cache_write": "0.00000125", - "input_cache_write_1h": "0.000002" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { - "context_length": 200000, - "max_completion_tokens": 64000, + "context_length": 1000000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, @@ -1382,114 +1633,190 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" + "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1296, + "win_rate": 65.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1254, + "win_rate": 59.4, + "rank": 1 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1252, + "win_rate": 59.5, + "rank": 1 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1295, + "win_rate": 63.6, + "rank": 1 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1293, + "win_rate": 61.1, + "rank": 4 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1346, + "win_rate": 70.2, + "rank": 1 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1265, + "win_rate": 59.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1256, + "win_rate": 56.7, + "rank": 5 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1303, + "win_rate": 62.3, + "rank": 3 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1296, + "win_rate": 59.4, + "rank": 3 + }, { "arena": "models", "category": "3d", - "elo": 1150, - "win_rate": 41.2, - "rank": 64 + "elo": 1373, + "win_rate": 62.5, + "rank": 4 }, { "arena": "models", "category": "asciiart", - "elo": 1186, - "win_rate": 49.3, - "rank": 30 + "elo": 1353, + "win_rate": 69.2, + "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1164, - "win_rate": 44.8, - "rank": 64 + "elo": 1334, + "win_rate": 59.1, + "rank": 4 }, { "arena": "models", "category": "dataviz", - "elo": 1167, - "win_rate": 45.6, - "rank": 61 + "elo": 1343, + "win_rate": 58.6, + "rank": 5 }, { "arena": "models", "category": "gamedev", - "elo": 1162, - "win_rate": 44.6, - "rank": 61 + "elo": 1383, + "win_rate": 62.4, + "rank": 3 }, { "arena": "models", "category": "svg", - "elo": 1083, - "win_rate": 39.1, - "rank": 58 + "elo": 1340, + "win_rate": 64.3, + "rank": 2 }, { "arena": "models", "category": "uicomponent", - "elo": 1153, - "win_rate": 42.7, - "rank": 61 + "elo": 1336, + "win_rate": 56.1, + "rank": 6 }, { "arena": "models", "category": "website", - "elo": 1164, - "win_rate": 45, - "rank": 65 + "elo": 1314, + "win_rate": 58.7, + "rank": 6 } ], "artificial_analysis": { - "intelligence_index": 29.6, - "coding_index": 43.9, - "agentic_index": 16.4 + "intelligence_index": 62.1, + "coding_index": 76.5, + "agentic_index": 56.6 } }, "reasoning": { - "mandatory": false + "mandatory": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "anthropic/claude-opus-4", - "canonical_slug": "anthropic/claude-4-opus-20250522", + "id": "anthropic/claude-haiku-4.5", + "canonical_slug": "anthropic/claude-4.5-haiku-20251001", "hugging_face_id": "", - "name": "Anthropic: Claude Opus 4", - "created": 1747931245, - "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...", + "name": "Anthropic: Claude Haiku 4.5", + "created": 1760547638, + "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...", "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000015", - "completion": "0.000075", + "prompt": "0.000001", + "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.0000015", - "input_cache_write": "0.00001875", - "input_cache_write_1h": "0.00003" + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", + "input_cache_write_1h": "0.000002" }, "top_provider": { "context_length": 200000, - "max_completion_tokens": 32000, - "is_moderated": false + "max_completion_tokens": 64000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "response_format", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_p" ], "default_parameters": { @@ -1501,100 +1828,111 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4-opus-20250522/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1216, - "win_rate": 57.7, - "rank": 40 + "elo": 1126, + "win_rate": 41.2, + "rank": 81 }, { "arena": "models", - "category": "codecategories", - "elo": 1210, - "win_rate": 55.6, - "rank": 50 + "category": "asciiart", + "elo": 1173, + "win_rate": 49.3, + "rank": 33 }, { "arena": "models", - "category": "dataviz", - "elo": 1189, - "win_rate": 57.9, - "rank": 54 + "category": "codecategories", + "elo": 1134, + "win_rate": 44.9, + "rank": 79 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1148, + "win_rate": 45.7, + "rank": 75 }, { "arena": "models", "category": "gamedev", - "elo": 1236, - "win_rate": 59.9, - "rank": 37 + "elo": 1135, + "win_rate": 44.7, + "rank": 76 }, { "arena": "models", "category": "svg", - "elo": 1185, - "win_rate": 57.7, - "rank": 38 + "elo": 1062, + "win_rate": 39, + "rank": 64 }, { "arena": "models", "category": "uicomponent", - "elo": 1207, - "win_rate": 59.2, - "rank": 46 + "elo": 1130, + "win_rate": 43, + "rank": 73 }, { "arena": "models", "category": "website", - "elo": 1207, - "win_rate": 54.6, - "rank": 52 + "elo": 1133, + "win_rate": 45, + "rank": 81 } - ] + ], + "artificial_analysis": { + "intelligence_index": 29.9, + "coding_index": 43.9, + "agentic_index": 16.5 + } }, "reasoning": { "mandatory": false } }, { - "id": "anthropic/claude-opus-4.1", - "canonical_slug": "anthropic/claude-4.1-opus-20250805", + "id": "anthropic/claude-haiku-4.5:batch", + "canonical_slug": "anthropic/claude-4.5-haiku-20251001", "hugging_face_id": "", - "name": "Anthropic: Claude Opus 4.1", - "created": 1754411591, - "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...", + "name": "Anthropic: Claude Haiku 4.5 (batch)", + "created": 1760547638, + "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...", "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000015", - "completion": "0.000075", + "prompt": "0.0000005", + "completion": "0.0000025", "web_search": "0.01", - "input_cache_read": "0.0000015", - "input_cache_write": "0.00001875", - "input_cache_write_1h": "0.00003" + "input_cache_read": "0.00000005", + "input_cache_write": "0.000000625", + "input_cache_write_1h": "0.000001" }, "top_provider": { "context_length": 200000, - "max_completion_tokens": 32000, + "max_completion_tokens": 64000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", "response_format", @@ -1615,117 +1953,118 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1228, - "win_rate": 51.7, - "rank": 36 + "elo": 1126, + "win_rate": 41.2, + "rank": 81 }, { "arena": "models", "category": "asciiart", - "elo": 1212, - "win_rate": 51.6, - "rank": 19 + "elo": 1173, + "win_rate": 49.3, + "rank": 33 }, { "arena": "models", "category": "codecategories", - "elo": 1220, - "win_rate": 55.8, - "rank": 40 + "elo": 1134, + "win_rate": 44.9, + "rank": 79 }, { "arena": "models", "category": "dataviz", - "elo": 1209, - "win_rate": 56.4, - "rank": 44 + "elo": 1148, + "win_rate": 45.7, + "rank": 75 }, { "arena": "models", "category": "gamedev", - "elo": 1237, - "win_rate": 58.5, - "rank": 36 + "elo": 1135, + "win_rate": 44.7, + "rank": 76 }, { "arena": "models", "category": "svg", - "elo": 1210, - "win_rate": 60.8, - "rank": 26 + "elo": 1062, + "win_rate": 39, + "rank": 64 }, { "arena": "models", "category": "uicomponent", - "elo": 1217, - "win_rate": 58, - "rank": 41 + "elo": 1130, + "win_rate": 43, + "rank": 73 }, { "arena": "models", "category": "website", - "elo": 1219, - "win_rate": 55.3, - "rank": 46 + "elo": 1133, + "win_rate": 45, + "rank": 81 } - ] + ], + "artificial_analysis": { + "intelligence_index": 29.9, + "coding_index": 43.9, + "agentic_index": 16.5 + } }, "reasoning": { "mandatory": false } }, { - "id": "anthropic/claude-opus-4.5", - "canonical_slug": "anthropic/claude-4.5-opus-20251124", + "id": "anthropic/claude-opus-4", + "canonical_slug": "anthropic/claude-4-opus-20250522", "hugging_face_id": "", - "name": "Anthropic: Claude Opus 4.5", - "created": 1764010580, - "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...", + "name": "Anthropic: Claude Opus 4", + "created": 1747931245, + "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...", "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.000025", + "prompt": "0.000015", + "completion": "0.000075", "web_search": "0.01", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "input_cache_write_1h": "0.00001" + "input_cache_read": "0.0000015", + "input_cache_write": "0.00001875", + "input_cache_write_1h": "0.00003" }, "top_provider": { "context_length": 200000, - "max_completion_tokens": 64000, - "is_moderated": true + "max_completion_tokens": 32000, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", - "response_format", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "verbosity" + "top_p" ], "default_parameters": { "temperature": null, @@ -1736,96 +2075,61 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" + "details": "/api/v1/models/anthropic/claude-4-opus-20250522/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1292, - "win_rate": 58.8, - "rank": 20 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1234, - "win_rate": 54.6, - "rank": 12 + "elo": 1192, + "win_rate": 57.7, + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1292, - "win_rate": 59.7, - "rank": 18 + "elo": 1180, + "win_rate": 55.6, + "rank": 63 }, { "arena": "models", "category": "dataviz", - "elo": 1286, - "win_rate": 58.9, - "rank": 14 + "elo": 1168, + "win_rate": 58, + "rank": 65 }, { "arena": "models", "category": "gamedev", - "elo": 1295, - "win_rate": 59.5, - "rank": 19 + "elo": 1209, + "win_rate": 60.2, + "rank": 48 }, { "arena": "models", "category": "svg", - "elo": 1238, - "win_rate": 58.7, - "rank": 17 + "elo": 1160, + "win_rate": 56.5, + "rank": 43 }, { "arena": "models", "category": "uicomponent", - "elo": 1291, - "win_rate": 58.5, - "rank": 19 + "elo": 1181, + "win_rate": 59.5, + "rank": 60 }, { "arena": "models", "category": "website", - "elo": 1290, - "win_rate": 59.9, - "rank": 18 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1188, - "win_rate": 65.5, - "rank": 14 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1222, - "win_rate": 59.9, - "rank": 9 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1236, - "win_rate": 57.5, - "rank": 7 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1222, - "win_rate": 54.2, - "rank": 11 + "elo": 1176, + "win_rate": 54.5, + "rank": 65 } ] }, @@ -1834,48 +2138,44 @@ } }, { - "id": "anthropic/claude-opus-4.6", - "canonical_slug": "anthropic/claude-4.6-opus-20260205", + "id": "anthropic/claude-opus-4.1", + "canonical_slug": "anthropic/claude-4.1-opus-20250805", "hugging_face_id": "", - "name": "Anthropic: Claude Opus 4.6", - "created": 1770219050, - "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...", - "context_length": 1000000, + "name": "Anthropic: Claude Opus 4.1", + "created": 1754411591, + "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...", + "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.000025", + "prompt": "0.000015", + "completion": "0.000075", "web_search": "0.01", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "input_cache_write_1h": "0.00001" + "input_cache_read": "0.0000015", + "input_cache_write": "0.00001875", + "input_cache_write_1h": "0.00003" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 128000, - "is_moderated": false + "context_length": 200000, + "max_completion_tokens": 32000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", - "response_format", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_p", - "verbosity" + "top_p" ], "default_parameters": { "temperature": null, @@ -1886,146 +2186,114 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" + "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "androidnative", - "elo": 1214, - "win_rate": 68.8, - "rank": 11 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1286, - "win_rate": 68.6, - "rank": 4 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1256, - "win_rate": 60.5, - "rank": 3 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1268, - "win_rate": 60.9, - "rank": 5 - }, { "arena": "models", "category": "3d", - "elo": 1353, - "win_rate": 64.3, - "rank": 3 + "elo": 1207, + "win_rate": 52, + "rank": 48 }, { "arena": "models", "category": "asciiart", - "elo": 1304, - "win_rate": 63.2, - "rank": 6 + "elo": 1198, + "win_rate": 51.4, + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1342, - "win_rate": 63.5, - "rank": 3 + "elo": 1190, + "win_rate": 55.7, + "rank": 54 }, { "arena": "models", "category": "dataviz", - "elo": 1325, - "win_rate": 61.9, - "rank": 4 + "elo": 1189, + "win_rate": 57.1, + "rank": 56 }, { "arena": "models", "category": "gamedev", - "elo": 1344, - "win_rate": 63.2, - "rank": 4 + "elo": 1211, + "win_rate": 58.8, + "rank": 47 }, { "arena": "models", "category": "svg", - "elo": 1286, - "win_rate": 62.4, - "rank": 4 + "elo": 1184, + "win_rate": 58.8, + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1350, - "win_rate": 64.2, - "rank": 3 + "elo": 1191, + "win_rate": 57.7, + "rank": 59 }, { "arena": "models", "category": "website", - "elo": 1338, - "win_rate": 63.2, - "rank": 3 + "elo": 1188, + "win_rate": 55.1, + "rank": 60 } ] }, "reasoning": { - "mandatory": false, - "supports_max_tokens": true, - "supported_efforts": ["max", "high", "medium", "low"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "anthropic/claude-opus-4.7", - "canonical_slug": "anthropic/claude-4.7-opus-20260416", - "hugging_face_id": null, - "name": "Anthropic: Claude Opus 4.7", - "created": 1776351100, - "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...", - "context_length": 1000000, + "id": "anthropic/claude-opus-4.1:batch", + "canonical_slug": "anthropic/claude-4.1-opus-20250805", + "hugging_face_id": "", + "name": "Anthropic: Claude Opus 4.1 (batch)", + "created": 1754411591, + "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...", + "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.000025", + "prompt": "0.0000075", + "completion": "0.0000375", "web_search": "0.01", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "input_cache_write_1h": "0.00001" + "input_cache_read": "0.00000075", + "input_cache_write": "0.000009375", + "input_cache_write_1h": "0.000015" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 128000, - "is_moderated": false + "context_length": 200000, + "max_completion_tokens": 32000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", + "temperature", "tool_choice", - "tools", - "verbosity" + "tools" ], "default_parameters": { "temperature": null, @@ -2036,211 +2304,116 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" + "details": "/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1276, - "win_rate": 63.3, - "rank": 1 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1243, - "win_rate": 58, - "rank": 3 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1334, - "win_rate": 64.7, - "rank": 1 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1242, - "win_rate": 57.8, - "rank": 3 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1335, - "win_rate": 66.5, - "rank": 1 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1325, - "win_rate": 61.7, - "rank": 2 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1503, - "win_rate": 80.1, - "rank": 1 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1211, - "win_rate": 50.8, - "rank": 11 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1239, - "win_rate": 57.6, - "rank": 3 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1193, - "win_rate": 50.9, - "rank": 16 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1344, - "win_rate": 67.3, - "rank": 1 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1351, - "win_rate": 66.3, - "rank": 1 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1330, - "win_rate": 65.5, - "rank": 1 - }, { "arena": "models", "category": "3d", - "elo": 1322, - "win_rate": 59.1, - "rank": 9 + "elo": 1207, + "win_rate": 52, + "rank": 48 }, { "arena": "models", "category": "asciiart", - "elo": 1328, - "win_rate": 66.6, - "rank": 2 + "elo": 1198, + "win_rate": 51.4, + "rank": 21 }, { "arena": "models", "category": "codecategories", - "elo": 1336, - "win_rate": 60.7, - "rank": 4 + "elo": 1190, + "win_rate": 55.7, + "rank": 54 }, { "arena": "models", "category": "dataviz", - "elo": 1323, - "win_rate": 61.4, - "rank": 5 + "elo": 1189, + "win_rate": 57.1, + "rank": 56 }, { "arena": "models", "category": "gamedev", - "elo": 1343, - "win_rate": 63.1, - "rank": 6 + "elo": 1211, + "win_rate": 58.8, + "rank": 47 }, { "arena": "models", "category": "svg", - "elo": 1282, - "win_rate": 61.5, - "rank": 6 + "elo": 1184, + "win_rate": 58.8, + "rank": 32 }, { "arena": "models", "category": "uicomponent", - "elo": 1365, - "win_rate": 64.7, - "rank": 2 + "elo": 1191, + "win_rate": 57.7, + "rank": 59 }, { "arena": "models", "category": "website", - "elo": 1335, - "win_rate": 60.4, - "rank": 4 + "elo": 1188, + "win_rate": 55.1, + "rank": 60 } - ], - "artificial_analysis": { - "intelligence_index": 53.5, - "coding_index": 73.6, - "agentic_index": 44.4 - } + ] }, "reasoning": { - "mandatory": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "anthropic/claude-opus-4.7-fast", - "canonical_slug": "anthropic/claude-4.7-opus-fast-20260512", - "hugging_face_id": null, - "name": "Anthropic: Claude Opus 4.7 (Fast)", - "created": 1778613011, - "description": "Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", - "context_length": 1000000, + "id": "anthropic/claude-opus-4.5", + "canonical_slug": "anthropic/claude-4.5-opus-20251124", + "hugging_face_id": "", + "name": "Anthropic: Claude Opus 4.5", + "created": 1764010580, + "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...", + "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00003", - "completion": "0.00015", + "prompt": "0.000005", + "completion": "0.000025", "web_search": "0.01", - "input_cache_read": "0.000003", - "input_cache_write": "0.0000375", - "input_cache_write_1h": "0.00006" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 128000, + "context_length": 200000, + "max_completion_tokens": 64000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", + "temperature", "tool_choice", "tools", + "top_k", "verbosity" ], "default_parameters": { @@ -2255,46 +2428,131 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1268, + "win_rate": 58.6, + "rank": 30 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1222, + "win_rate": 54.7, + "rank": 17 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1262, + "win_rate": 59.5, + "rank": 29 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1266, + "win_rate": 58.5, + "rank": 22 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1267, + "win_rate": 59.3, + "rank": 29 + }, + { + "arena": "models", + "category": "svg", + "elo": 1217, + "win_rate": 58.5, + "rank": 20 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1266, + "win_rate": 58.1, + "rank": 29 + }, + { + "arena": "models", + "category": "website", + "elo": 1259, + "win_rate": 59.6, + "rank": 31 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1211, + "win_rate": 65.5, + "rank": 15 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1193, + "win_rate": 59.9, + "rank": 20 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1242, + "win_rate": 60.5, + "rank": 9 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1192, + "win_rate": 53, + "rank": 21 + } + ] }, "reasoning": { - "mandatory": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "anthropic/claude-opus-4.8", - "canonical_slug": "anthropic/claude-4.8-opus-20260528", - "hugging_face_id": null, - "name": "Anthropic: Claude Opus 4.8", - "created": 1779905091, - "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...", - "context_length": 1000000, + "id": "anthropic/claude-opus-4.5:batch", + "canonical_slug": "anthropic/claude-4.5-opus-20251124", + "hugging_face_id": "", + "name": "Anthropic: Claude Opus 4.5 (batch)", + "created": 1764010580, + "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...", + "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.000025", + "prompt": "0.0000025", + "completion": "0.0000125", "web_search": "0.01", - "input_cache_read": "0.0000005", - "input_cache_write": "0.00000625", - "input_cache_write_1h": "0.00001" + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125", + "input_cache_write_1h": "0.000005" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 128000, - "is_moderated": false + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", "response_format", @@ -2317,170 +2575,107 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1252, - "win_rate": 61.8, - "rank": 2 + "arena": "models", + "category": "3d", + "elo": 1268, + "win_rate": 58.6, + "rank": 30 }, { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1227, - "win_rate": 55.6, - "rank": 4 + "arena": "models", + "category": "asciiart", + "elo": 1222, + "win_rate": 54.7, + "rank": 17 }, { - "arena": "agents", - "category": "agenticslides", - "elo": 1294, - "win_rate": 64.8, - "rank": 2 + "arena": "models", + "category": "codecategories", + "elo": 1262, + "win_rate": 59.5, + "rank": 29 }, { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1230, - "win_rate": 56, - "rank": 4 + "arena": "models", + "category": "dataviz", + "elo": 1266, + "win_rate": 58.5, + "rank": 22 }, { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1310, - "win_rate": 68.9, - "rank": 2 + "arena": "models", + "category": "gamedev", + "elo": 1267, + "win_rate": 59.3, + "rank": 29 }, { - "arena": "agents", - "category": "androidnative", - "elo": 1340, - "win_rate": 67.2, - "rank": 1 + "arena": "models", + "category": "svg", + "elo": 1217, + "win_rate": 58.5, + "rank": 20 }, { - "arena": "agents", - "category": "fullstack", - "elo": 1319, - "win_rate": 65.2, - "rank": 2 + "arena": "models", + "category": "uicomponent", + "elo": 1266, + "win_rate": 58.1, + "rank": 29 }, { - "arena": "agents", - "category": "htmlslides", - "elo": 1223, - "win_rate": 55.5, - "rank": 4 + "arena": "models", + "category": "website", + "elo": 1259, + "win_rate": 59.6, + "rank": 31 }, { "arena": "agents", - "category": "mobileapps", - "elo": 1283, - "win_rate": 59.4, - "rank": 1 + "category": "androidnative", + "elo": 1211, + "win_rate": 65.5, + "rank": 15 }, { "arena": "agents", - "category": "pptxslides", - "elo": 1306, - "win_rate": 67.9, - "rank": 2 + "category": "fullstack", + "elo": 1193, + "win_rate": 59.9, + "rank": 20 }, { "arena": "agents", - "category": "python-pptxslides", - "elo": 1298, - "win_rate": 65.9, - "rank": 2 + "category": "mobileapps", + "elo": 1242, + "win_rate": 60.5, + "rank": 9 }, { "arena": "agents", "category": "webapps", - "elo": 1286, - "win_rate": 55, - "rank": 2 - }, - { - "arena": "models", - "category": "3d", - "elo": 1289, - "win_rate": 56.2, - "rank": 21 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1302, - "win_rate": 62.1, - "rank": 7 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1282, - "win_rate": 54.7, - "rank": 22 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1281, - "win_rate": 55.6, - "rank": 17 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1301, - "win_rate": 54.8, - "rank": 15 - }, - { - "arena": "models", - "category": "svg", - "elo": 1233, - "win_rate": 53.6, - "rank": 20 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1288, - "win_rate": 55.3, + "elo": 1192, + "win_rate": 53, "rank": 21 - }, - { - "arena": "models", - "category": "website", - "elo": 1280, - "win_rate": 54.6, - "rank": 22 } - ], - "artificial_analysis": { - "intelligence_index": 55.7, - "coding_index": 74.3, - "agentic_index": 47.2 - } + ] }, "reasoning": { - "mandatory": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "anthropic/claude-opus-4.8-fast", - "canonical_slug": "anthropic/claude-4.8-opus-fast-20260528", - "hugging_face_id": null, - "name": "Anthropic: Claude Opus 4.8 (Fast)", - "created": 1779913703, - "description": "Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", + "id": "anthropic/claude-opus-4.6", + "canonical_slug": "anthropic/claude-4.6-opus-20260205", + "hugging_face_id": "", + "name": "Anthropic: Claude Opus 4.6", + "created": 1770219050, + "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...", "context_length": 1000000, "architecture": { "modality": "text+image+file->text", @@ -2490,12 +2685,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00005", + "prompt": "0.000005", + "completion": "0.000025", "web_search": "0.01", - "input_cache_read": "0.000001", - "input_cache_write": "0.0000125", - "input_cache_write_1h": "0.00002" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { "context_length": 1000000, @@ -2505,13 +2700,18 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", + "temperature", "tool_choice", "tools", + "top_k", + "top_p", "verbosity" ], "default_parameters": { @@ -2526,53 +2726,146 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.8-opus-fast-20260528/endpoints" + "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1241, + "win_rate": 66.4, + "rank": 8 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1255, + "win_rate": 63.4, + "rank": 10 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1267, + "win_rate": 63, + "rank": 3 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1235, + "win_rate": 56, + "rank": 17 + }, + { + "arena": "models", + "category": "3d", + "elo": 1329, + "win_rate": 62.4, + "rank": 9 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1285, + "win_rate": 63, + "rank": 9 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1309, + "win_rate": 61, + "rank": 9 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1306, + "win_rate": 58.1, + "rank": 10 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1314, + "win_rate": 59.3, + "rank": 12 + }, + { + "arena": "models", + "category": "svg", + "elo": 1264, + "win_rate": 60.6, + "rank": 7 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1313, + "win_rate": 59.1, + "rank": 12 + }, + { + "arena": "models", + "category": "website", + "elo": 1304, + "win_rate": 61.1, + "rank": 10 + } + ] }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" + "default_enabled": false, + "supports_max_tokens": true, + "supported_efforts": ["max", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "anthropic/claude-sonnet-4", - "canonical_slug": "anthropic/claude-4-sonnet-20250522", + "id": "anthropic/claude-opus-4.6:batch", + "canonical_slug": "anthropic/claude-4.6-opus-20260205", "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4", - "created": 1747930371, - "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...", + "name": "Anthropic: Claude Opus 4.6 (batch)", + "created": 1770219050, + "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...", "context_length": 1000000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000003", - "completion": "0.000015", + "prompt": "0.0000025", + "completion": "0.0000125", "web_search": "0.01", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "input_cache_write_1h": "0.000006" + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125", + "input_cache_write_1h": "0.000005" }, "top_provider": { "context_length": 1000000, - "max_completion_tokens": 64000, - "is_moderated": false + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", + "response_format", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "top_p", + "verbosity" ], "default_parameters": { "temperature": null, @@ -2583,227 +2876,114 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints" + "details": "/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "models", - "category": "3d", - "elo": 1217, - "win_rate": 57.8, - "rank": 39 + "arena": "agents", + "category": "androidnative", + "elo": 1241, + "win_rate": 66.4, + "rank": 8 }, { - "arena": "models", - "category": "codecategories", - "elo": 1191, - "win_rate": 53.4, - "rank": 56 + "arena": "agents", + "category": "fullstack", + "elo": 1255, + "win_rate": 63.4, + "rank": 10 }, { - "arena": "models", - "category": "dataviz", - "elo": 1195, - "win_rate": 55.8, - "rank": 52 + "arena": "agents", + "category": "mobileapps", + "elo": 1267, + "win_rate": 63, + "rank": 3 }, { - "arena": "models", - "category": "gamedev", - "elo": 1204, - "win_rate": 54.9, - "rank": 47 - }, - { - "arena": "models", - "category": "svg", - "elo": 1136, - "win_rate": 51.1, - "rank": 48 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1183, - "win_rate": 58, - "rank": 54 + "arena": "agents", + "category": "webapps", + "elo": 1235, + "win_rate": 56, + "rank": 17 }, - { - "arena": "models", - "category": "website", - "elo": 1188, - "win_rate": 52.4, - "rank": 59 - } - ], - "artificial_analysis": { - "intelligence_index": 28.9, - "coding_index": 37.6, - "agentic_index": 16.6 - } - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "anthropic/claude-sonnet-4.5", - "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", - "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4.5", - "created": 1759161676, - "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", - "context_length": 1000000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "Claude", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000003", - "completion": "0.000015", - "web_search": "0.01", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "input_cache_write_1h": "0.000006" - }, - "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 64000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_completion_tokens", - "max_tokens", - "reasoning", - "response_format", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 1, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" - }, - "benchmarks": { - "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1236, - "win_rate": 53.1, - "rank": 35 + "elo": 1329, + "win_rate": 62.4, + "rank": 9 }, { "arena": "models", "category": "asciiart", - "elo": 1242, - "win_rate": 55.7, - "rank": 11 + "elo": 1285, + "win_rate": 63, + "rank": 9 }, { "arena": "models", "category": "codecategories", - "elo": 1232, - "win_rate": 52.9, - "rank": 35 + "elo": 1309, + "win_rate": 61, + "rank": 9 }, { "arena": "models", "category": "dataviz", - "elo": 1213, - "win_rate": 49.2, - "rank": 42 + "elo": 1306, + "win_rate": 58.1, + "rank": 10 }, { "arena": "models", "category": "gamedev", - "elo": 1233, - "win_rate": 52, - "rank": 38 + "elo": 1314, + "win_rate": 59.3, + "rank": 12 }, { "arena": "models", "category": "svg", - "elo": 1173, - "win_rate": 52.8, - "rank": 39 + "elo": 1264, + "win_rate": 60.6, + "rank": 7 }, { "arena": "models", "category": "uicomponent", - "elo": 1232, - "win_rate": 52, - "rank": 36 + "elo": 1313, + "win_rate": 59.1, + "rank": 12 }, { "arena": "models", "category": "website", - "elo": 1232, - "win_rate": 53.3, - "rank": 39 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1118, - "win_rate": 43.5, - "rank": 19 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1179, - "win_rate": 48.9, - "rank": 22 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1131, - "win_rate": 43.1, - "rank": 21 + "elo": 1304, + "win_rate": 61.1, + "rank": 10 } - ], - "artificial_analysis": { - "intelligence_index": 36.4, - "coding_index": 52.1, - "agentic_index": 24.6 - } + ] }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": false, + "supports_max_tokens": true, + "supported_efforts": ["max", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "anthropic/claude-sonnet-4.6", - "canonical_slug": "anthropic/claude-4.6-sonnet-20260217", - "hugging_face_id": "", - "name": "Anthropic: Claude Sonnet 4.6", - "created": 1771342990, - "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...", + "id": "anthropic/claude-opus-4.7", + "canonical_slug": "anthropic/claude-4.7-opus-20260416", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.7", + "created": 1776351100, + "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...", "context_length": 1000000, "architecture": { "modality": "text+image+file->text", @@ -2813,12 +2993,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000003", - "completion": "0.000015", + "prompt": "0.000005", + "completion": "0.000025", "web_search": "0.01", - "input_cache_read": "0.0000003", - "input_cache_write": "0.00000375", - "input_cache_write_1h": "0.000006" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { "context_length": 1000000, @@ -2831,14 +3011,12 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_p", "verbosity" ], "default_parameters": { @@ -2853,128 +3031,171 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" + "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "agents", "category": "agenticgamedev", - "elo": 1192, - "win_rate": 50.9, - "rank": 6 + "elo": 1250, + "win_rate": 61.4, + "rank": 3 }, { "arena": "agents", - "category": "androidnative", - "elo": 1235, - "win_rate": 61.9, - "rank": 9 + "category": "agentichtmlslides", + "elo": 1243, + "win_rate": 58, + "rank": 3 }, { "arena": "agents", - "category": "fullstack", - "elo": 1272, - "win_rate": 63.1, - "rank": 5 + "category": "agenticslides", + "elo": 1334, + "win_rate": 64.7, + "rank": 1 }, { "arena": "agents", - "category": "godotgamedev", - "elo": 1271, - "win_rate": 60.6, + "category": "agenticslides(html)", + "elo": 1242, + "win_rate": 57.8, + "rank": 3 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1331, + "win_rate": 65.2, "rank": 1 }, { "arena": "agents", - "category": "mobileapps", - "elo": 1252, - "win_rate": 59.2, + "category": "androidnative", + "elo": 1260, + "win_rate": 56, "rank": 5 }, { "arena": "agents", - "category": "webapps", - "elo": 1248, - "win_rate": 55.8, - "rank": 8 + "category": "fullstack", + "elo": 1503, + "win_rate": 80.1, + "rank": 1 }, { - "arena": "models", - "category": "3d", - "elo": 1314, - "win_rate": 58.9, - "rank": 14 + "arena": "agents", + "category": "godotgamedev", + "elo": 1270, + "win_rate": 60.9, + "rank": 3 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1248, + "win_rate": 58.3, + "rank": 2 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1333, + "win_rate": 64.9, + "rank": 1 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1336, + "win_rate": 63.1, + "rank": 2 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1299, + "win_rate": 62.1, + "rank": 2 + }, + { + "arena": "models", + "category": "3d", + "elo": 1304, + "win_rate": 56.8, + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1280, - "win_rate": 60.7, - "rank": 8 + "elo": 1317, + "win_rate": 65.6, + "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1326, - "win_rate": 61.2, - "rank": 7 + "elo": 1310, + "win_rate": 58.1, + "rank": 8 }, { "arena": "models", "category": "dataviz", - "elo": 1322, - "win_rate": 61.3, - "rank": 6 + "elo": 1308, + "win_rate": 56.7, + "rank": 9 }, { "arena": "models", "category": "gamedev", - "elo": 1322, - "win_rate": 60.4, - "rank": 12 + "elo": 1327, + "win_rate": 59.1, + "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1255, - "win_rate": 59.5, - "rank": 11 + "elo": 1260, + "win_rate": 58.8, + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1326, - "win_rate": 61.8, - "rank": 7 + "elo": 1332, + "win_rate": 59.3, + "rank": 9 }, { "arena": "models", "category": "website", - "elo": 1328, - "win_rate": 61.7, - "rank": 5 + "elo": 1306, + "win_rate": 58.5, + "rank": 9 } ], "artificial_analysis": { - "intelligence_index": 47.2, - "coding_index": 63, - "agentic_index": 40.8 + "intelligence_index": 55, + "coding_index": 73.6, + "agentic_index": 46.3 } }, "reasoning": { "mandatory": false, - "supported_efforts": ["max", "high", "medium", "low"], - "default_effort": "medium" + "default_enabled": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "anthropic/claude-sonnet-5", - "canonical_slug": "anthropic/claude-sonnet-5-20260630", + "id": "anthropic/claude-opus-4.7-fast", + "canonical_slug": "anthropic/claude-4.7-opus-fast-20260512", "hugging_face_id": null, - "name": "Anthropic: Claude Sonnet 5", - "created": 1782843083, - "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...", + "name": "Anthropic: Claude Opus 4.7 (Fast)", + "created": 1778613011, + "description": "Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", "context_length": 1000000, "architecture": { "modality": "text+image+file->text", @@ -2984,24 +3205,24 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.00001", + "prompt": "0.00003", + "completion": "0.00015", "web_search": "0.01", - "input_cache_read": "0.0000002", - "input_cache_write": "0.0000025", - "input_cache_write_1h": "0.000004" + "input_cache_read": "0.000003", + "input_cache_write": "0.0000375", + "input_cache_write_1h": "0.00006" }, "top_provider": { "context_length": 1000000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", @@ -3021,163 +3242,59 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1321, - "win_rate": 56.6, - "rank": 10 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1227, - "win_rate": 51.2, - "rank": 13 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1319, - "win_rate": 56.8, - "rank": 8 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1278, - "win_rate": 54, - "rank": 18 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1344, - "win_rate": 59.8, - "rank": 5 - }, - { - "arena": "models", - "category": "svg", - "elo": 1254, - "win_rate": 54.8, - "rank": 12 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1319, - "win_rate": 56.7, - "rank": 10 - }, - { - "arena": "models", - "category": "website", - "elo": 1319, - "win_rate": 57.7, - "rank": 6 - } - ], - "artificial_analysis": { - "intelligence_index": 53.4, - "coding_index": 71.5, - "agentic_index": 46.7 - } + "details": "/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints" }, "reasoning": { "mandatory": false, + "default_enabled": false, "supported_efforts": ["max", "xhigh", "high", "medium", "low"], - "default_effort": "medium" - } - }, - { - "id": "arcee-ai/coder-large", - "canonical_slug": "arcee-ai/coder-large", - "hugging_face_id": "", - "name": "Arcee AI: Coder Large", - "created": 1746478663, - "description": "Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...", - "context_length": 32768, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000005", - "completion": "0.0000008" - }, - "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/arcee-ai/coder-large/endpoints" + "default_effort": "high" } }, { - "id": "arcee-ai/trinity-large-thinking", - "canonical_slug": "arcee-ai/trinity-large-thinking", - "hugging_face_id": "arcee-ai/Trinity-Large-Thinking", - "name": "Arcee AI: Trinity Large Thinking", - "created": 1775058318, - "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...", - "context_length": 262144, + "id": "anthropic/claude-opus-4.7:batch", + "canonical_slug": "anthropic/claude-4.7-opus-20260416", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.7 (batch)", + "created": 1776351100, + "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.0000008", - "input_cache_read": "0.00000006" + "prompt": "0.0000025", + "completion": "0.0000125", + "web_search": "0.01", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125", + "input_cache_write_1h": "0.000005" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 80000, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", "max_tokens", "reasoning", - "temperature", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", "tool_choice", "tools", - "top_k", - "top_p" + "verbosity" ], "default_parameters": { - "temperature": 0.3, - "top_p": 0.8, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -3187,367 +3304,486 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/arcee-ai/trinity-large-thinking/endpoints" + "details": "/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "models", - "category": "3d", - "elo": 1159, - "win_rate": 41.3, - "rank": 60 + "arena": "agents", + "category": "agenticgamedev", + "elo": 1250, + "win_rate": 61.4, + "rank": 3 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1243, + "win_rate": 58, + "rank": 3 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1334, + "win_rate": 64.7, + "rank": 1 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1242, + "win_rate": 57.8, + "rank": 3 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1331, + "win_rate": 65.2, + "rank": 1 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1260, + "win_rate": 56, + "rank": 5 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1503, + "win_rate": 80.1, + "rank": 1 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1270, + "win_rate": 60.9, + "rank": 3 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1248, + "win_rate": 58.3, + "rank": 2 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1333, + "win_rate": 64.9, + "rank": 1 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1336, + "win_rate": 63.1, + "rank": 2 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1299, + "win_rate": 62.1, + "rank": 2 + }, + { + "arena": "models", + "category": "3d", + "elo": 1304, + "win_rate": 56.8, + "rank": 17 }, { "arena": "models", "category": "asciiart", - "elo": 1087, - "win_rate": 37.1, - "rank": 46 + "elo": 1317, + "win_rate": 65.6, + "rank": 3 }, { "arena": "models", "category": "codecategories", - "elo": 1165, - "win_rate": 40.1, - "rank": 63 + "elo": 1310, + "win_rate": 58.1, + "rank": 8 }, { "arena": "models", "category": "dataviz", - "elo": 1142, - "win_rate": 39.3, - "rank": 69 + "elo": 1308, + "win_rate": 56.7, + "rank": 9 }, { "arena": "models", "category": "gamedev", - "elo": 1142, - "win_rate": 38.1, - "rank": 69 + "elo": 1327, + "win_rate": 59.1, + "rank": 10 }, { "arena": "models", "category": "svg", - "elo": 1073, - "win_rate": 35.2, - "rank": 61 + "elo": 1260, + "win_rate": 58.8, + "rank": 8 }, { "arena": "models", "category": "uicomponent", - "elo": 1098, - "win_rate": 32.5, - "rank": 74 + "elo": 1332, + "win_rate": 59.3, + "rank": 9 }, { "arena": "models", "category": "website", - "elo": 1177, - "win_rate": 41.3, - "rank": 61 + "elo": 1306, + "win_rate": 58.5, + "rank": 9 } - ] + ], + "artificial_analysis": { + "intelligence_index": 55, + "coding_index": 73.6, + "agentic_index": 46.3 + } }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "arcee-ai/trinity-mini", - "canonical_slug": "arcee-ai/trinity-mini-20251201", - "hugging_face_id": "arcee-ai/Trinity-Mini", - "name": "Arcee AI: Trinity Mini", - "created": 1764601720, - "description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...", - "context_length": 131072, + "id": "anthropic/claude-opus-4.8", + "canonical_slug": "anthropic/claude-4.8-opus-20260528", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.8", + "created": 1779905091, + "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000000045", - "completion": "0.00000015" + "prompt": "0.000005", + "completion": "0.000025", + "web_search": "0.01", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "logprobs", "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", - "top_p" + "verbosity" ], "default_parameters": { - "temperature": 0.15, - "top_p": 0.75, - "frequency_penalty": null + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-07-10", - "links": { - "details": "/api/v1/models/arcee-ai/trinity-mini-20251201/endpoints" - }, - "reasoning": { - "mandatory": true - } - }, - { - "id": "arcee-ai/virtuoso-large", - "canonical_slug": "arcee-ai/virtuoso-large", - "hugging_face_id": "", - "name": "Arcee AI: Virtuoso Large", - "created": 1746478885, - "description": "Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000075", - "completion": "0.0000012" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 64000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/arcee-ai/virtuoso-large/endpoints" - } - }, - { - "id": "baidu/ernie-4.5-vl-424b-a47b", - "canonical_slug": "baidu/ernie-4.5-vl-424b-a47b", - "hugging_face_id": "baidu/ERNIE-4.5-VL-424B-A47B-PT", - "name": "Baidu: ERNIE 4.5 VL 424B A47B ", - "created": 1751300903, - "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000042", - "completion": "0.00000125" - }, - "top_provider": { - "context_length": 123000, - "max_completion_tokens": 16000, - "is_moderated": false + "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints" + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1257, + "win_rate": 61.5, + "rank": 2 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1227, + "win_rate": 55.6, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1294, + "win_rate": 64.8, + "rank": 2 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1230, + "win_rate": 56, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1310, + "win_rate": 68.9, + "rank": 2 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1261, + "win_rate": 58.7, + "rank": 4 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1280, + "win_rate": 59.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1255, + "win_rate": 58.9, + "rank": 5 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1237, + "win_rate": 56, + "rank": 3 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1253, + "win_rate": 56.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1306, + "win_rate": 67.9, + "rank": 2 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1298, + "win_rate": 65.9, + "rank": 4 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1263, + "win_rate": 53.5, + "rank": 9 + }, + { + "arena": "models", + "category": "3d", + "elo": 1276, + "win_rate": 53.6, + "rank": 27 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1297, + "win_rate": 61.8, + "rank": 6 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1265, + "win_rate": 53.8, + "rank": 27 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1262, + "win_rate": 54.6, + "rank": 23 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1289, + "win_rate": 54.9, + "rank": 23 + }, + { + "arena": "models", + "category": "svg", + "elo": 1215, + "win_rate": 53.8, + "rank": 21 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1280, + "win_rate": 54.9, + "rank": 25 + }, + { + "arena": "models", + "category": "website", + "elo": 1261, + "win_rate": 54, + "rank": 28 + } + ], + "artificial_analysis": { + "intelligence_index": 57.3, + "coding_index": 74.3, + "agentic_index": 49.4 + } }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "bytedance-seed/seed-1.6", - "canonical_slug": "bytedance-seed/seed-1.6-20250625", - "hugging_face_id": "", - "name": "ByteDance Seed: Seed 1.6", - "created": 1766504997, - "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", - "context_length": 262144, + "id": "anthropic/claude-opus-4.8-fast", + "canonical_slug": "anthropic/claude-4.8-opus-fast-20260528", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.8 (Fast)", + "created": 1779913703, + "description": "Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", + "context_length": 1000000, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.000002" + "prompt": "0.00001", + "completion": "0.00005", + "web_search": "0.01", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125", + "input_cache_write_1h": "0.00002" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints" + "details": "/api/v1/models/anthropic/claude-4.8-opus-fast-20260528/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "bytedance-seed/seed-1.6-flash", - "canonical_slug": "bytedance-seed/seed-1.6-flash-20250625", - "hugging_face_id": "", - "name": "ByteDance Seed: Seed 1.6 Flash", - "created": 1766505011, - "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...", - "context_length": 262144, + "id": "anthropic/claude-opus-4.8:batch", + "canonical_slug": "anthropic/claude-4.8-opus-20260528", + "hugging_face_id": null, + "name": "Anthropic: Claude Opus 4.8 (batch)", + "created": 1779905091, + "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...", + "context_length": 1000000, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.000000075", - "completion": "0.0000003" + "prompt": "0.0000025", + "completion": "0.0000125", + "web_search": "0.01", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125", + "input_cache_write_1h": "0.000005" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "bytedance-seed/seed-2.0-lite", - "canonical_slug": "bytedance-seed/seed-2.0-lite-20260309", - "hugging_face_id": null, - "name": "ByteDance Seed: Seed-2.0-Lite", - "created": 1773157231, - "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...", - "context_length": 262144, - "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000025", - "completion": "0.000002" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 131072, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, @@ -3561,386 +3797,539 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints" + "details": "/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1257, + "win_rate": 61.5, + "rank": 2 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1227, + "win_rate": 55.6, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1294, + "win_rate": 64.8, + "rank": 2 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1230, + "win_rate": 56, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1310, + "win_rate": 68.9, + "rank": 2 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1261, + "win_rate": 58.7, + "rank": 4 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1280, + "win_rate": 59.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1255, + "win_rate": 58.9, + "rank": 5 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1237, + "win_rate": 56, + "rank": 3 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1253, + "win_rate": 56.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1306, + "win_rate": 67.9, + "rank": 2 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1298, + "win_rate": 65.9, + "rank": 4 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1263, + "win_rate": 53.5, + "rank": 9 + }, + { + "arena": "models", + "category": "3d", + "elo": 1276, + "win_rate": 53.6, + "rank": 27 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1297, + "win_rate": 61.8, + "rank": 6 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1265, + "win_rate": 53.8, + "rank": 27 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1262, + "win_rate": 54.6, + "rank": 23 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1289, + "win_rate": 54.9, + "rank": 23 + }, + { + "arena": "models", + "category": "svg", + "elo": 1215, + "win_rate": 53.8, + "rank": 21 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1280, + "win_rate": 54.9, + "rank": 25 + }, + { + "arena": "models", + "category": "website", + "elo": 1261, + "win_rate": 54, + "rank": 28 + } + ], + "artificial_analysis": { + "intelligence_index": 57.3, + "coding_index": 74.3, + "agentic_index": 49.4 + } }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "medium" + "default_enabled": false, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "bytedance-seed/seed-2.0-mini", - "canonical_slug": "bytedance-seed/seed-2.0-mini-20260224", - "hugging_face_id": "", - "name": "ByteDance Seed: Seed-2.0-Mini", - "created": 1772131107, - "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...", - "context_length": 262144, + "id": "anthropic/claude-opus-5", + "canonical_slug": "anthropic/claude-opus-5-20260723", + "hugging_face_id": null, + "name": "Claude Opus 5", + "created": 1784912544, + "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...", + "context_length": 1000000, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000004" + "prompt": "0.000005", + "completion": "0.000025", + "web_search": "0.01", + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "input_cache_write_1h": "0.00001" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 131072, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints" + "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints" }, - "reasoning": { - "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "medium" - } - }, - { - "id": "bytedance/ui-tars-1.5-7b", - "canonical_slug": "bytedance/ui-tars-1.5-7b", - "hugging_face_id": "ByteDance-Seed/UI-TARS-1.5-7B", - "name": "ByteDance: UI-TARS 7B ", - "created": 1753205056, - "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...", - "context_length": 128000, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000001", - "completion": "0.0000002", - "input_cache_read": "0.0000001" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 2048, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "presence_penalty", - "repetition_penalty", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-01-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints" - } - }, - { - "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", - "canonical_slug": "venice/uncensored", - "hugging_face_id": "cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", - "name": "Venice: Uncensored (free)", - "created": 1752094966, - "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...", - "context_length": 32768, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, - "is_moderated": false + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "fullstack", + "elo": 1352, + "win_rate": 69.2, + "rank": 3 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1282, + "win_rate": 56.3, + "rank": 5 + }, + { + "arena": "models", + "category": "3d", + "elo": 1385, + "win_rate": 63, + "rank": 3 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1347, + "win_rate": 59.4, + "rank": 2 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1372, + "win_rate": 61.3, + "rank": 2 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1385, + "win_rate": 62.4, + "rank": 2 + }, + { + "arena": "models", + "category": "svg", + "elo": 1363, + "win_rate": 60.2, + "rank": 1 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1370, + "win_rate": 59.6, + "rank": 2 + }, + { + "arena": "models", + "category": "website", + "elo": 1328, + "win_rate": 58.3, + "rank": 3 + } + ], + "artificial_analysis": { + "intelligence_index": 63.1, + "coding_index": 78, + "agentic_index": 59.2 + } }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-04-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/venice/uncensored/endpoints" + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "cohere/command-a", - "canonical_slug": "cohere/command-a-03-2025", - "hugging_face_id": "CohereForAI/c4ai-command-a-03-2025", - "name": "Cohere: Command A", - "created": 1741894342, - "description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...", - "context_length": 256000, + "id": "anthropic/claude-opus-5-fast", + "canonical_slug": "anthropic/claude-opus-5-fast-20260723", + "hugging_face_id": null, + "name": "Claude Opus 5 (Fast)", + "created": 1784912546, + "description": "Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.00001" + "prompt": "0.00001", + "completion": "0.00005", + "web_search": "0.01", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125", + "input_cache_write_1h": "0.00002" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": 8192, + "context_length": 1000000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", - "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "verbosity" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/cohere/command-a-03-2025/endpoints" + "details": "/api/v1/models/anthropic/claude-opus-5-fast-20260723/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 22.5, - "coding_index": 27.8, - "agentic_index": 9.2 - } + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "cohere/command-r-08-2024", - "canonical_slug": "cohere/command-r-08-2024", + "id": "anthropic/claude-opus-5:batch", + "canonical_slug": "anthropic/claude-opus-5-20260723", "hugging_face_id": null, - "name": "Cohere: Command R (08-2024)", - "created": 1724976000, - "description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...", - "context_length": 128000, + "name": "Claude Opus 5 (batch)", + "created": 1784912544, + "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Cohere", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006" + "prompt": "0.0000025", + "completion": "0.0000125", + "web_search": "0.01", + "input_cache_read": "0.00000025", + "input_cache_write": "0.000003125", + "input_cache_write_1h": "0.000005" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4000, + "context_length": 1000000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "verbosity" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/cohere/command-r-08-2024/endpoints" - } - }, - { - "id": "cohere/command-r-plus-08-2024", - "canonical_slug": "cohere/command-r-plus-08-2024", - "hugging_face_id": null, - "name": "Cohere: Command R+ (08-2024)", - "created": 1724976000, - "description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Cohere", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000025", - "completion": "0.00001" + "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints" }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4000, - "is_moderated": true + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "fullstack", + "elo": 1352, + "win_rate": 69.2, + "rank": 3 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1282, + "win_rate": 56.3, + "rank": 5 + }, + { + "arena": "models", + "category": "3d", + "elo": 1385, + "win_rate": 63, + "rank": 3 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1347, + "win_rate": 59.4, + "rank": 2 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1372, + "win_rate": 61.3, + "rank": 2 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1385, + "win_rate": 62.4, + "rank": 2 + }, + { + "arena": "models", + "category": "svg", + "elo": 1363, + "win_rate": 60.2, + "rank": 1 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1370, + "win_rate": 59.6, + "rank": 2 + }, + { + "arena": "models", + "category": "website", + "elo": 1328, + "win_rate": 58.3, + "rank": 3 + } + ], + "artificial_analysis": { + "intelligence_index": 63.1, + "coding_index": 78, + "agentic_index": 59.2 + } }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/cohere/command-r-plus-08-2024/endpoints" + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "cohere/command-r7b-12-2024", - "canonical_slug": "cohere/command-r7b-12-2024", + "id": "anthropic/claude-sonnet-4", + "canonical_slug": "anthropic/claude-4-sonnet-20250522", "hugging_face_id": "", - "name": "Cohere: Command R7B (12-2024)", - "created": 1734158152, - "description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Cohere", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000000375", - "completion": "0.00000015" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-08-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/cohere/command-r7b-12-2024/endpoints" - } - }, - { - "id": "cohere/north-mini-code:free", - "canonical_slug": "cohere/north-mini-code-20260617", - "hugging_face_id": "CohereLabs/North-Mini-Code-1.0", - "name": "Cohere: North Mini Code (free)", - "created": 1781723748, - "description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...", - "context_length": 256000, + "name": "Anthropic: Claude Sonnet 4", + "created": 1747930371, + "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], - "tokenizer": "Cohere", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000003", + "completion": "0.000015", + "web_search": "0.01", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "input_cache_write_1h": "0.000006", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000006", + "completion": "0.0000225", + "input_cache_read": "0.0000006", + "input_cache_write": "0.0000075", + "input_cache_write_1h": "0.000012" + } + ] }, "top_provider": { - "context_length": 256000, + "context_length": 200000, "max_completion_tokens": 64000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", - "presence_penalty", "reasoning", - "seed", "stop", "temperature", "tool_choice", @@ -3957,17 +4346,67 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/cohere/north-mini-code-20260617/endpoints" + "details": "/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1194, + "win_rate": 58, + "rank": 50 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1160, + "win_rate": 53.4, + "rank": 69 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1180, + "win_rate": 56.3, + "rank": 62 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1178, + "win_rate": 55.2, + "rank": 59 + }, + { + "arena": "models", + "category": "svg", + "elo": 1112, + "win_rate": 50, + "rank": 53 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1157, + "win_rate": 58.1, + "rank": 68 + }, + { + "arena": "models", + "category": "website", + "elo": 1157, + "win_rate": 52.3, + "rank": 73 + } + ], "artificial_analysis": { - "intelligence_index": null, - "coding_index": 36.5, - "agentic_index": null + "intelligence_index": 29.8, + "coding_index": 37.6, + "agentic_index": 17.6 } }, "reasoning": { @@ -3975,95 +4414,206 @@ } }, { - "id": "deepcogito/cogito-v2.1-671b", - "canonical_slug": "deepcogito/cogito-v2.1-671b-20251118", + "id": "anthropic/claude-sonnet-4.5", + "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", "hugging_face_id": "", - "name": "Deep Cogito: Cogito v2.1 671B", - "created": 1763071233, - "description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "name": "Anthropic: Claude Sonnet 4.5", + "created": 1759161676, + "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", + "context_length": 1000000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00000125" + "prompt": "0.000003", + "completion": "0.000015", + "web_search": "0.01", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "input_cache_write_1h": "0.000006", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000006", + "completion": "0.0000225", + "input_cache_read": "0.0000006", + "input_cache_write": "0.0000075", + "input_cache_write_1h": "0.000012" + } + ] }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 64000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", + "max_completion_tokens", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null + "temperature": 1, + "top_p": 1, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/deepcogito/cogito-v2.1-671b-20251118/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1211, + "win_rate": 51.1, + "rank": 47 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1237, + "win_rate": 56.1, + "rank": 15 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1202, + "win_rate": 51.4, + "rank": 48 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1190, + "win_rate": 47.4, + "rank": 55 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1204, + "win_rate": 51.1, + "rank": 49 + }, + { + "arena": "models", + "category": "svg", + "elo": 1151, + "win_rate": 51.8, + "rank": 44 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1200, + "win_rate": 49.5, + "rank": 52 + }, + { + "arena": "models", + "category": "website", + "elo": 1201, + "win_rate": 51.7, + "rank": 52 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1088, + "win_rate": 43.5, + "rank": 29 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1188, + "win_rate": 52.3, + "rank": 24 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1103, + "win_rate": 43.6, + "rank": 31 + } + ], + "artificial_analysis": { + "intelligence_index": 37.4, + "coding_index": 52.1, + "agentic_index": 26.4 + } }, "reasoning": { "mandatory": false } }, { - "id": "deepseek/deepseek-chat", - "canonical_slug": "deepseek/deepseek-chat-v3", - "hugging_face_id": "deepseek-ai/DeepSeek-V3", - "name": "DeepSeek: DeepSeek V3", - "created": 1735241320, - "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...", - "context_length": 131072, + "id": "anthropic/claude-sonnet-4.5:batch", + "canonical_slug": "anthropic/claude-4.5-sonnet-20250929", + "hugging_face_id": "", + "name": "Anthropic: Claude Sonnet 4.5 (batch)", + "created": 1759161676, + "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.0000002002", - "completion": "0.0000008001" + "prompt": "0.0000015", + "completion": "0.0000075", + "web_search": "0.01", + "input_cache_read": "0.00000015", + "input_cache_write": "0.000001875", + "input_cache_write_1h": "0.000003", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000003", + "completion": "0.00001125", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "input_cache_write_1h": "0.000006" + } + ] }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16000, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 64000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", - "seed", "stop", "structured_outputs", "temperature", @@ -4072,279 +4622,324 @@ "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 1, + "top_p": 1, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-07-31", + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-chat-v3/endpoints" + "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1165, - "win_rate": 50.7, - "rank": 55 + "elo": 1211, + "win_rate": 51.1, + "rank": 47 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1237, + "win_rate": 56.1, + "rank": 15 }, { "arena": "models", "category": "codecategories", - "elo": 1158, - "win_rate": 48.5, - "rank": 68 + "elo": 1202, + "win_rate": 51.4, + "rank": 48 }, { "arena": "models", "category": "dataviz", - "elo": 1141, - "win_rate": 51.4, - "rank": 70 + "elo": 1190, + "win_rate": 47.4, + "rank": 55 }, { "arena": "models", "category": "gamedev", - "elo": 1120, - "win_rate": 43.9, - "rank": 75 + "elo": 1204, + "win_rate": 51.1, + "rank": 49 }, { "arena": "models", "category": "svg", - "elo": 1034, - "win_rate": 38.8, - "rank": 69 + "elo": 1151, + "win_rate": 51.8, + "rank": 44 }, { "arena": "models", "category": "uicomponent", - "elo": 1148, - "win_rate": 52.8, - "rank": 63 + "elo": 1200, + "win_rate": 49.5, + "rank": 52 }, { "arena": "models", "category": "website", - "elo": 1163, - "win_rate": 48.5, - "rank": 66 + "elo": 1201, + "win_rate": 51.7, + "rank": 52 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1088, + "win_rate": 43.5, + "rank": 29 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1188, + "win_rate": 52.3, + "rank": 24 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1103, + "win_rate": 43.6, + "rank": 31 } - ] + ], + "artificial_analysis": { + "intelligence_index": 37.4, + "coding_index": 52.1, + "agentic_index": 26.4 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "deepseek/deepseek-chat-v3-0324", - "canonical_slug": "deepseek/deepseek-chat-v3-0324", - "hugging_face_id": "deepseek-ai/DeepSeek-V3-0324", - "name": "DeepSeek: DeepSeek V3 0324", - "created": 1742824755, - "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...", - "context_length": 163840, + "id": "anthropic/claude-sonnet-4.6", + "canonical_slug": "anthropic/claude-4.6-sonnet-20260217", + "hugging_face_id": "", + "name": "Anthropic: Claude Sonnet 4.6", + "created": 1771342990, + "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", + "tokenizer": "Claude", "instruct_type": null }, "pricing": { - "prompt": "0.00000024", - "completion": "0.0000009", - "input_cache_read": "0.000000135" - }, - "top_provider": { - "context_length": 163840, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-07-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 15.4, - "coding_index": 21.2, - "agentic_index": 1.5 - } - } - }, - { - "id": "deepseek/deepseek-chat-v3.1", - "canonical_slug": "deepseek/deepseek-chat-v3.1", - "hugging_face_id": "deepseek-ai/DeepSeek-V3.1", - "name": "DeepSeek: DeepSeek V3.1", - "created": 1755779628, - "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...", - "context_length": 163840, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-v3.1" - }, - "pricing": { - "prompt": "0.00000021", - "completion": "0.00000079", - "input_cache_read": "0.00000013" + "prompt": "0.000003", + "completion": "0.000015", + "web_search": "0.01", + "input_cache_read": "0.0000003", + "input_cache_write": "0.00000375", + "input_cache_write_1h": "0.000006" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", + "max_completion_tokens", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", - "top_p" + "top_p", + "verbosity" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints" + "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1185, + "win_rate": 52.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1231, + "win_rate": 62.1, + "rank": 10 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1249, + "win_rate": 64.1, + "rank": 11 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1226, + "win_rate": 60.6, + "rank": 7 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1265, + "win_rate": 63.4, + "rank": 4 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1229, + "win_rate": 55.4, + "rank": 18 + }, { "arena": "models", "category": "3d", - "elo": 1155, - "win_rate": 48, - "rank": 62 + "elo": 1289, + "win_rate": 57.6, + "rank": 24 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1267, + "win_rate": 60.1, + "rank": 10 }, { "arena": "models", "category": "codecategories", - "elo": 1161, - "win_rate": 47.9, - "rank": 66 + "elo": 1296, + "win_rate": 59.1, + "rank": 13 }, { "arena": "models", "category": "dataviz", - "elo": 1143, - "win_rate": 46.8, - "rank": 67 + "elo": 1303, + "win_rate": 57.4, + "rank": 12 }, { "arena": "models", "category": "gamedev", - "elo": 1150, - "win_rate": 47.2, - "rank": 65 + "elo": 1297, + "win_rate": 58.8, + "rank": 19 }, { "arena": "models", "category": "svg", - "elo": 1024, - "win_rate": 38.2, - "rank": 71 + "elo": 1233, + "win_rate": 59, + "rank": 15 }, { "arena": "models", "category": "uicomponent", - "elo": 1138, - "win_rate": 47.5, - "rank": 65 + "elo": 1299, + "win_rate": 57.3, + "rank": 18 }, { "arena": "models", "category": "website", - "elo": 1165, - "win_rate": 48, - "rank": 64 + "elo": 1296, + "win_rate": 59.8, + "rank": 13 } - ] + ], + "artificial_analysis": { + "intelligence_index": 48.4, + "coding_index": 63, + "agentic_index": 42.1 + } }, "reasoning": { - "mandatory": false + "mandatory": false, + "supported_efforts": ["max", "high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "deepseek/deepseek-r1", - "canonical_slug": "deepseek/deepseek-r1", - "hugging_face_id": "deepseek-ai/DeepSeek-R1", - "name": "DeepSeek: R1", - "created": 1737381095, - "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....", - "context_length": 163840, + "id": "anthropic/claude-sonnet-4.6:batch", + "canonical_slug": "anthropic/claude-4.6-sonnet-20260217", + "hugging_face_id": "", + "name": "Anthropic: Claude Sonnet 4.6 (batch)", + "created": 1771342990, + "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-r1" + "tokenizer": "Claude", + "instruct_type": null }, "pricing": { - "prompt": "0.0000007", - "completion": "0.0000025" + "prompt": "0.0000015", + "completion": "0.0000075", + "web_search": "0.01", + "input_cache_read": "0.00000015", + "input_cache_write": "0.000001875", + "input_cache_write_1h": "0.000003" }, "top_provider": { - "context_length": 64000, - "max_completion_tokens": 16000, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "max_completion_tokens", "max_tokens", - "presence_penalty", "reasoning", - "repetition_penalty", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "top_p", + "verbosity" ], "default_parameters": { "temperature": null, @@ -4355,328 +4950,514 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-07-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-r1/endpoints" + "details": "/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1185, + "win_rate": 52.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1231, + "win_rate": 62.1, + "rank": 10 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1249, + "win_rate": 64.1, + "rank": 11 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1226, + "win_rate": 60.6, + "rank": 7 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1265, + "win_rate": 63.4, + "rank": 4 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1229, + "win_rate": 55.4, + "rank": 18 + }, + { + "arena": "models", + "category": "3d", + "elo": 1289, + "win_rate": 57.6, + "rank": 24 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1267, + "win_rate": 60.1, + "rank": 10 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1296, + "win_rate": 59.1, + "rank": 13 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1303, + "win_rate": 57.4, + "rank": 12 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1297, + "win_rate": 58.8, + "rank": 19 + }, + { + "arena": "models", + "category": "svg", + "elo": 1233, + "win_rate": 59, + "rank": 15 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1299, + "win_rate": 57.3, + "rank": 18 + }, + { + "arena": "models", + "category": "website", + "elo": 1296, + "win_rate": 59.8, + "rank": 13 + } + ], "artificial_analysis": { - "intelligence_index": 18.5, - "coding_index": 24.6, - "agentic_index": 3.1 + "intelligence_index": 48.4, + "coding_index": 63, + "agentic_index": 42.1 } }, "reasoning": { - "mandatory": true + "mandatory": false, + "supported_efforts": ["max", "high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "deepseek/deepseek-r1-0528", - "canonical_slug": "deepseek/deepseek-r1-0528", - "hugging_face_id": "deepseek-ai/DeepSeek-R1-0528", - "name": "DeepSeek: R1 0528", - "created": 1748455170, - "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...", - "context_length": 163840, + "id": "anthropic/claude-sonnet-5", + "canonical_slug": "anthropic/claude-sonnet-5-20260630", + "hugging_face_id": null, + "name": "Anthropic: Claude Sonnet 5", + "created": 1782843083, + "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-r1" + "tokenizer": "Claude", + "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.00000215", - "input_cache_read": "0.00000035" + "prompt": "0.000002", + "completion": "0.00001", + "web_search": "0.01", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025", + "input_cache_write_1h": "0.000004" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", + "max_completion_tokens", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-r1-0528/endpoints" + "details": "/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1234, + "win_rate": 55.7, + "rank": 4 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1243, + "win_rate": 55.3, + "rank": 7 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1280, + "win_rate": 57.9, + "rank": 7 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1270, + "win_rate": 60.4, + "rank": 4 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1226, + "win_rate": 52.2, + "rank": 4 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1236, + "win_rate": 52.2, + "rank": 10 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1249, + "win_rate": 54.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1291, + "win_rate": 58, + "rank": 4 + }, { "arena": "models", "category": "3d", - "elo": 1189, - "win_rate": 53.4, - "rank": 50 + "elo": 1311, + "win_rate": 55.3, + "rank": 13 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1240, + "win_rate": 52.4, + "rank": 14 }, { "arena": "models", "category": "codecategories", - "elo": 1188, - "win_rate": 52.6, - "rank": 58 + "elo": 1296, + "win_rate": 54.3, + "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1221, - "win_rate": 60.7, - "rank": 37 + "elo": 1260, + "win_rate": 52.4, + "rank": 25 }, { "arena": "models", "category": "gamedev", - "elo": 1164, - "win_rate": 49.5, - "rank": 60 + "elo": 1343, + "win_rate": 55.5, + "rank": 6 }, { "arena": "models", "category": "svg", - "elo": 1096, - "win_rate": 48.7, - "rank": 53 + "elo": 1225, + "win_rate": 53.2, + "rank": 18 }, { "arena": "models", "category": "uicomponent", - "elo": 1158, - "win_rate": 55.1, - "rank": 58 + "elo": 1309, + "win_rate": 54.5, + "rank": 13 }, { "arena": "models", "category": "website", - "elo": 1192, - "win_rate": 52.7, - "rank": 57 + "elo": 1286, + "win_rate": 54.4, + "rank": 15 } - ] - }, - "reasoning": { - "mandatory": true - } - }, - { - "id": "deepseek/deepseek-r1-distill-llama-70b", - "canonical_slug": "deepseek/deepseek-r1-distill-llama-70b", - "hugging_face_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", - "name": "DeepSeek: R1 Distill Llama 70B", - "created": 1737663169, - "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "deepseek-r1" - }, - "pricing": { - "prompt": "0.0000008", - "completion": "0.0000008" - }, - "top_provider": { - "context_length": 8192, - "max_completion_tokens": 8192, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "max_tokens", - "presence_penalty", - "reasoning", - "repetition_penalty", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-07-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints" + ], + "artificial_analysis": { + "intelligence_index": 55.3, + "coding_index": 71.5, + "agentic_index": 49.7 + } }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "deepseek/deepseek-v3.1-terminus", - "canonical_slug": "deepseek/deepseek-v3.1-terminus", - "hugging_face_id": "deepseek-ai/DeepSeek-V3.1-Terminus", - "name": "DeepSeek: DeepSeek V3.1 Terminus", - "created": 1758548275, - "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...", - "context_length": 163840, + "id": "anthropic/claude-sonnet-5:batch", + "canonical_slug": "anthropic/claude-sonnet-5-20260630", + "hugging_face_id": null, + "name": "Anthropic: Claude Sonnet 5 (batch)", + "created": 1782843083, + "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-v3.1" + "tokenizer": "Claude", + "instruct_type": null }, "pricing": { - "prompt": "0.00000027", - "completion": "0.00000095", - "input_cache_read": "0.00000013" + "prompt": "0.000001", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", + "input_cache_write_1h": "0.000002" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", - "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "verbosity" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints" + "details": "/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1234, + "win_rate": 55.7, + "rank": 4 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1243, + "win_rate": 55.3, + "rank": 7 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1280, + "win_rate": 57.9, + "rank": 7 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1270, + "win_rate": 60.4, + "rank": 4 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1226, + "win_rate": 52.2, + "rank": 4 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1236, + "win_rate": 52.2, + "rank": 10 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1249, + "win_rate": 54.5, + "rank": 6 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1291, + "win_rate": 58, + "rank": 4 + }, { "arena": "models", "category": "3d", - "elo": 1218, - "win_rate": 56, - "rank": 38 + "elo": 1311, + "win_rate": 55.3, + "rank": 13 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1240, + "win_rate": 52.4, + "rank": 14 }, { "arena": "models", "category": "codecategories", - "elo": 1225, - "win_rate": 56, - "rank": 39 + "elo": 1296, + "win_rate": 54.3, + "rank": 14 }, { "arena": "models", "category": "dataviz", - "elo": 1207, - "win_rate": 53, - "rank": 46 + "elo": 1260, + "win_rate": 52.4, + "rank": 25 }, { "arena": "models", "category": "gamedev", - "elo": 1196, - "win_rate": 52.5, - "rank": 53 + "elo": 1343, + "win_rate": 55.5, + "rank": 6 }, { "arena": "models", "category": "svg", - "elo": 1123, - "win_rate": 50.1, - "rank": 51 + "elo": 1225, + "win_rate": 53.2, + "rank": 18 }, { "arena": "models", "category": "uicomponent", - "elo": 1235, - "win_rate": 59.3, - "rank": 35 + "elo": 1309, + "win_rate": 54.5, + "rank": 13 }, { "arena": "models", "category": "website", - "elo": 1229, - "win_rate": 56.4, - "rank": 42 + "elo": 1286, + "win_rate": 54.4, + "rank": 15 } ], "artificial_analysis": { - "intelligence_index": null, - "coding_index": 43.5, - "agentic_index": null + "intelligence_index": 55.3, + "coding_index": 71.5, + "agentic_index": 49.7 } }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { - "id": "deepseek/deepseek-v3.2", - "canonical_slug": "deepseek/deepseek-v3.2-20251201", - "hugging_face_id": "deepseek-ai/DeepSeek-V3.2", - "name": "DeepSeek: DeepSeek V3.2", - "created": 1764594642, - "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", - "context_length": 131072, + "id": "arcee-ai/trinity-large-thinking", + "canonical_slug": "arcee-ai/trinity-large-thinking", + "hugging_face_id": "arcee-ai/Trinity-Large-Thinking", + "name": "Arcee AI: Trinity Large Thinking", + "created": 1775058318, + "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000002288", - "completion": "0.0000003432", - "input_cache_read": "0.00000002288" + "prompt": "0.00000022", + "completion": "0.00000085", + "input_cache_read": "0.00000006" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 64000, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -4686,7 +5467,6 @@ "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", "repetition_penalty", @@ -4702,8 +5482,8 @@ "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, + "temperature": 0.3, + "top_p": 0.8, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -4713,514 +5493,324 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints" + "details": "/api/v1/models/arcee-ai/trinity-large-thinking/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1211, - "win_rate": 49.7, - "rank": 42 + "elo": 1135, + "win_rate": 41.3, + "rank": 73 }, { "arena": "models", "category": "asciiart", - "elo": 1129, - "win_rate": 40.5, - "rank": 43 + "elo": 1074, + "win_rate": 37.1, + "rank": 53 }, { "arena": "models", "category": "codecategories", - "elo": 1213, - "win_rate": 49.5, - "rank": 49 + "elo": 1136, + "win_rate": 40.1, + "rank": 78 }, { "arena": "models", "category": "dataviz", - "elo": 1202, - "win_rate": 48.5, - "rank": 49 + "elo": 1121, + "win_rate": 39.3, + "rank": 83 }, { "arena": "models", "category": "gamedev", - "elo": 1198, - "win_rate": 46.7, - "rank": 51 + "elo": 1117, + "win_rate": 38.4, + "rank": 85 }, { "arena": "models", "category": "svg", - "elo": 1090, - "win_rate": 40.9, - "rank": 55 + "elo": 1050, + "win_rate": 35.2, + "rank": 67 }, { "arena": "models", "category": "uicomponent", - "elo": 1202, - "win_rate": 46.9, - "rank": 48 + "elo": 1074, + "win_rate": 32.6, + "rank": 88 }, { "arena": "models", "category": "website", - "elo": 1216, - "win_rate": 50.3, - "rank": 48 + "elo": 1148, + "win_rate": 41.3, + "rank": 77 } ], "artificial_analysis": { "intelligence_index": null, - "coding_index": 44.2, + "coding_index": 25.8, "agentic_index": null } }, "reasoning": { - "mandatory": false, - "default_enabled": false + "mandatory": true } }, { - "id": "deepseek/deepseek-v3.2-exp", - "canonical_slug": "deepseek/deepseek-v3.2-exp", - "hugging_face_id": "deepseek-ai/DeepSeek-V3.2-Exp", - "name": "DeepSeek: DeepSeek V3.2 Exp", - "created": 1759150481, - "description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", - "context_length": 163840, + "id": "arcee-ai/virtuoso-large", + "canonical_slug": "arcee-ai/virtuoso-large", + "hugging_face_id": "", + "name": "Arcee AI: Virtuoso Large", + "created": 1746478885, + "description": "Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", - "instruct_type": "deepseek-v3.1" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000027", - "completion": "0.00000041" + "prompt": "0.00000075", + "completion": "0.0000012" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 65536, + "context_length": 131072, + "max_completion_tokens": 64000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", - "reasoning", "repetition_penalty", - "response_format", - "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-07-31", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints" + "details": "/api/v1/models/arcee-ai/virtuoso-large/endpoints" + } + }, + { + "id": "baidu/ernie-4.5-vl-424b-a47b", + "canonical_slug": "baidu/ernie-4.5-vl-424b-a47b", + "hugging_face_id": "baidu/ERNIE-4.5-VL-424B-A47B-PT", + "name": "Baidu: ERNIE 4.5 VL 424B A47B ", + "created": 1751300903, + "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...", + "context_length": 123000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["image", "text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1226, - "win_rate": 56.4, - "rank": 37 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1220, - "win_rate": 54.2, - "rank": 41 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1196, - "win_rate": 50.6, - "rank": 51 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1210, - "win_rate": 53.1, - "rank": 43 - }, - { - "arena": "models", - "category": "svg", - "elo": 1090, - "win_rate": 42, - "rank": 56 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1220, - "win_rate": 53.3, - "rank": 39 - }, - { - "arena": "models", - "category": "website", - "elo": 1221, - "win_rate": 54.2, - "rank": 45 - } - ] + "pricing": { + "prompt": "0.00000042", + "completion": "0.00000125" + }, + "top_provider": { + "context_length": 123000, + "max_completion_tokens": 16000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints" }, "reasoning": { "mandatory": false } }, { - "id": "deepseek/deepseek-v4-flash", - "canonical_slug": "deepseek/deepseek-v4-flash-20260423", - "hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash", - "name": "DeepSeek: DeepSeek V4 Flash", - "created": 1777000666, - "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...", - "context_length": 1048576, + "id": "bytedance-seed/seed-1.6", + "canonical_slug": "bytedance-seed/seed-1.6-20250625", + "hugging_face_id": "", + "name": "ByteDance Seed: Seed 1.6", + "created": 1766504997, + "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.00000018", - "input_cache_read": "0.000000018" + "prompt": "0.00000025", + "completion": "0.000002", + "overrides": [ + { + "min_prompt_tokens": 128000, + "prompt": "0.0000005", + "completion": "0.000004" + } + ] }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 262144, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1268, - "win_rate": 50, - "rank": 25 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1169, - "win_rate": 44.9, - "rank": 35 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1255, - "win_rate": 50, - "rank": 31 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1165, - "win_rate": 41.4, - "rank": 63 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1263, - "win_rate": 50.7, - "rank": 28 - }, - { - "arena": "models", - "category": "svg", - "elo": 1214, - "win_rate": 49.1, - "rank": 25 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1217, - "win_rate": 46, - "rank": 42 - }, - { - "arena": "models", - "category": "website", - "elo": 1250, - "win_rate": 50.6, - "rank": 31 - } - ], - "artificial_analysis": { - "intelligence_index": 40.3, - "coding_index": 56.2, - "agentic_index": 31.1 - } + "details": "/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints" }, "reasoning": { - "mandatory": false, - "supported_efforts": ["xhigh", "high"], - "default_effort": "high" + "mandatory": false } }, { - "id": "deepseek/deepseek-v4-pro", - "canonical_slug": "deepseek/deepseek-v4-pro-20260423", - "hugging_face_id": "deepseek-ai/DeepSeek-V4-Pro", - "name": "DeepSeek: DeepSeek V4 Pro", - "created": 1777000679, - "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...", - "context_length": 1048576, + "id": "bytedance-seed/seed-1.6-flash", + "canonical_slug": "bytedance-seed/seed-1.6-flash-20250625", + "hugging_face_id": "", + "name": "ByteDance Seed: Seed 1.6 Flash", + "created": 1766505011, + "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], "output_modalities": ["text"], - "tokenizer": "DeepSeek", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000000435", - "completion": "0.00000087", - "input_cache_read": "0.000000003625" + "prompt": "0.000000075", + "completion": "0.0000003", + "overrides": [ + { + "min_prompt_tokens": 128000, + "prompt": "0.0000001", + "completion": "0.0000008" + } + ] }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 384000, + "context_length": 262144, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 1, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "fullstack", - "elo": 948, - "win_rate": 22.1, - "rank": 29 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1098, - "win_rate": 34, - "rank": 20 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1019, - "win_rate": 26.6, - "rank": 25 - }, - { - "arena": "models", - "category": "3d", - "elo": 1330, - "win_rate": 59.6, - "rank": 6 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1203, - "win_rate": 47.6, - "rank": 21 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1288, - "win_rate": 54.7, - "rank": 20 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1220, - "win_rate": 48.4, - "rank": 38 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1296, - "win_rate": 56.1, - "rank": 18 - }, - { - "arena": "models", - "category": "svg", - "elo": 1191, - "win_rate": 46.6, - "rank": 35 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1272, - "win_rate": 52, - "rank": 25 - }, - { - "arena": "models", - "category": "website", - "elo": 1278, - "win_rate": 53.5, - "rank": 23 - } - ], - "artificial_analysis": { - "intelligence_index": 44.3, - "coding_index": 59.4, - "agentic_index": 36.4 - } + "details": "/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints" }, "reasoning": { - "mandatory": false, - "supported_efforts": ["xhigh", "high"], - "default_effort": "high" + "mandatory": false } }, { - "id": "google/gemini-2.5-flash", - "canonical_slug": "google/gemini-2.5-flash", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Flash", - "created": 1750172488, - "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", - "context_length": 1048576, + "id": "bytedance-seed/seed-2-1-turbo", + "canonical_slug": "bytedance-seed/seed-2-1-turbo-20260810", + "hugging_face_id": null, + "name": "ByteDance Seed: Seed 2.1 Turbo", + "created": 1786552176, + "description": "Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...", + "context_length": 262144, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["file", "image", "text", "audio", "video"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000025", - "image": "0.0000003", - "audio": "0.000001", - "web_search": "0.014", - "internal_reasoning": "0.0000025", - "input_cache_read": "0.00000003", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.0000005", + "completion": "0.0000025" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", - "seed", "stop", "structured_outputs", "temperature", @@ -5228,191 +5818,181 @@ "tools", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" + "details": "/api/v1/models/bytedance-seed/seed-2-1-turbo-20260810/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1149, - "win_rate": 47.4, - "rank": 65 - }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "bytedance-seed/seed-2.0-code", + "canonical_slug": "bytedance-seed/seed-2.0-code-20260730", + "hugging_face_id": null, + "name": "ByteDance Seed: Seed-2.0-Code", + "created": 1786550701, + "description": "Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000005", + "completion": "0.000003", + "overrides": [ { - "arena": "models", - "category": "codecategories", - "elo": 1153, - "win_rate": 46.9, - "rank": 70 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1170, - "win_rate": 48.4, - "rank": 59 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1131, - "win_rate": 44.3, - "rank": 73 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1146, - "win_rate": 48.9, - "rank": 64 - }, - { - "arena": "models", - "category": "website", - "elo": 1158, - "win_rate": 47.1, - "rank": 69 - }, - { - "arena": "models", - "category": "svg", - "elo": 1077, - "win_rate": 43.1, - "rank": 60 + "min_prompt_tokens": 128000, + "prompt": "0.000001", + "completion": "0.000006" } ] }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/bytedance-seed/seed-2.0-code-20260730/endpoints" + }, "reasoning": { - "mandatory": false + "mandatory": false, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "google/gemini-2.5-flash-image", - "canonical_slug": "google/gemini-2.5-flash-image", - "hugging_face_id": "", - "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", - "created": 1759870431, - "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...", - "context_length": 32768, + "id": "bytedance-seed/seed-2.0-lite", + "canonical_slug": "bytedance-seed/seed-2.0-lite-20260309", + "hugging_face_id": null, + "name": "ByteDance Seed: Seed-2.0-Lite", + "created": 1773157231, + "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...", + "context_length": 262144, "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000025", - "image": "0.0000003", - "audio": "0.000001", - "web_search": "0.014", - "internal_reasoning": "0.0000025", - "input_cache_read": "0.00000003", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.00000025", + "completion": "0.000002", + "overrides": [ + { + "min_prompt_tokens": 128000, + "prompt": "0.0000005", + "completion": "0.000004" + } + ] }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", "max_tokens", + "reasoning", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-flash-image/endpoints" + "details": "/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "graphicdesign", - "elo": 1203, - "win_rate": 56.9, - "rank": 8 - }, - { - "arena": "models", - "category": "image", - "elo": 1214, - "win_rate": 55.6, - "rank": 8 - }, - { - "arena": "models", - "category": "logo", - "elo": 1189, - "win_rate": 51.4, - "rank": 9 - } - ] + "reasoning": { + "mandatory": false, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "google/gemini-2.5-flash-lite", - "canonical_slug": "google/gemini-2.5-flash-lite", + "id": "bytedance-seed/seed-2.0-mini", + "canonical_slug": "bytedance-seed/seed-2.0-mini-20260224", "hugging_face_id": "", - "name": "Google: Gemini 2.5 Flash Lite", - "created": 1753200276, - "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", - "context_length": 1048576, + "name": "ByteDance Seed: Seed-2.0-Mini", + "created": 1772131107, + "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...", + "context_length": 262144, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Other", "instruct_type": null }, "pricing": { "prompt": "0.0000001", "completion": "0.0000004", - "image": "0.0000001", - "audio": "0.0000003", - "web_search": "0.014", - "internal_reasoning": "0.0000004", - "input_cache_read": "0.00000001", - "input_cache_write": "0.00000008333333333333334" + "overrides": [ + { + "min_prompt_tokens": 128000, + "prompt": "0.0000002", + "completion": "0.0000008" + } + ] }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, + "context_length": 262144, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", - "seed", "stop", "structured_outputs", "temperature", @@ -5426,320 +6006,191 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" + "details": "/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": false, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "google/gemini-2.5-flash-lite-preview-09-2025", - "canonical_slug": "google/gemini-2.5-flash-lite-preview-09-2025", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", - "created": 1758819686, - "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", - "context_length": 1048576, + "id": "bytedance/ui-tars-1.5-7b", + "canonical_slug": "bytedance/ui-tars-1.5-7b", + "hugging_face_id": "ByteDance-Seed/UI-TARS-1.5-7B", + "name": "ByteDance: UI-TARS 7B ", + "created": 1753205056, + "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...", + "context_length": 128000, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], + "modality": "text+image->text", + "input_modalities": ["image", "text"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Other", "instruct_type": null }, "pricing": { "prompt": "0.0000001", - "completion": "0.0000004", - "image": "0.0000001", - "audio": "0.0000003", - "web_search": "0.014", - "internal_reasoning": "0.0000004", - "input_cache_read": "0.00000001", - "input_cache_write": "0.00000008333333333333334" + "completion": "0.0000002", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, + "context_length": 128000, + "max_completion_tokens": 2048, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", - "reasoning", - "response_format", + "presence_penalty", + "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", + "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2025-01-31", - "expiration_date": "2026-07-09", + "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-flash-lite-preview-09-2025/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1045, - "win_rate": 36.5, - "rank": 86 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1130, - "win_rate": 47, - "rank": 76 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1133, - "win_rate": 45.5, - "rank": 72 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1113, - "win_rate": 45.9, - "rank": 76 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1075, - "win_rate": 41.4, - "rank": 78 - }, - { - "arena": "models", - "category": "website", - "elo": 1142, - "win_rate": 48.1, - "rank": 76 - } - ] - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "google/gemini-2.5-pro", - "canonical_slug": "google/gemini-2.5-pro", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Pro", - "created": 1750169544, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, - "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null + "details": "/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints" + } + }, + { + "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition", + "canonical_slug": "venice/uncensored", + "hugging_face_id": "cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition", + "name": "Venice: Uncensored", + "created": 1752094966, + "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", - "image": "0.00000125", - "audio": "0.00000125", - "web_search": "0.014", - "internal_reasoning": "0.00001", - "input_cache_read": "0.000000125", - "input_cache_write": "0.000000375" + "prompt": "0.0000002", + "completion": "0.0000009" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 128000, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", "max_tokens", - "reasoning", + "presence_penalty", "response_format", - "seed", "stop", - "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": "2024-04-30", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1160, - "win_rate": 52.2, - "rank": 57 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1203, - "win_rate": 58.3, - "rank": 52 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1289, - "win_rate": 71.8, - "rank": 12 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1178, - "win_rate": 55.1, - "rank": 57 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1198, - "win_rate": 60.5, - "rank": 49 - }, - { - "arena": "models", - "category": "website", - "elo": 1210, - "win_rate": 58.8, - "rank": 50 - } - ], - "artificial_analysis": { - "intelligence_index": 25.8, - "coding_index": 33.3, - "agentic_index": 7.1 - } - }, - "reasoning": { - "mandatory": true + "details": "/api/v1/models/venice/uncensored/endpoints" } }, { - "id": "google/gemini-2.5-pro-preview", - "canonical_slug": "google/gemini-2.5-pro-preview-06-05", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Pro Preview 06-05", - "created": 1749137257, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, + "id": "cohere/command-a", + "canonical_slug": "cohere/command-a-03-2025", + "hugging_face_id": "CohereForAI/c4ai-command-a-03-2025", + "name": "Cohere: Command A", + "created": 1741894342, + "description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...", + "context_length": 256000, "architecture": { - "modality": "text+image+file+audio->text", - "input_modalities": ["file", "image", "text", "audio"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", - "image": "0.00000125", - "audio": "0.00000125", - "web_search": "0.014", - "internal_reasoning": "0.00001", - "input_cache_read": "0.000000125", - "input_cache_write": "0.000000375" + "prompt": "0.0000025", + "completion": "0.00001" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, - "is_moderated": false + "context_length": 256000, + "max_completion_tokens": 8192, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", "max_tokens", - "reasoning", + "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": "2024-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints" + "details": "/api/v1/models/cohere/command-a-03-2025/endpoints" }, - "reasoning": { - "mandatory": true + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 22.8, + "coding_index": 27.8, + "agentic_index": 9.2 + } } }, { - "id": "google/gemini-2.5-pro-preview-05-06", - "canonical_slug": "google/gemini-2.5-pro-preview-03-25", - "hugging_face_id": "", - "name": "Google: Gemini 2.5 Pro Preview 05-06", - "created": 1746578513, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, + "id": "cohere/command-r-08-2024", + "canonical_slug": "cohere/command-r-08-2024", + "hugging_face_id": null, + "name": "Cohere: Command R (08-2024)", + "created": 1724976000, + "description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...", + "context_length": 128000, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Cohere", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", - "image": "0.00000125", - "audio": "0.00000125", - "web_search": "0.014", - "internal_reasoning": "0.00001", - "input_cache_read": "0.000000125", - "input_cache_write": "0.000000375" + "prompt": "0.00000015", + "completion": "0.0000006" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", "max_tokens", - "reasoning", + "presence_penalty", "response_format", "seed", "stop", @@ -5747,58 +6198,46 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-31", + "knowledge_cutoff": "2024-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints" - }, - "reasoning": { - "mandatory": true + "details": "/api/v1/models/cohere/command-r-08-2024/endpoints" } }, { - "id": "google/gemini-3-flash-preview", - "canonical_slug": "google/gemini-3-flash-preview-20251217", - "hugging_face_id": "", - "name": "Google: Gemini 3 Flash Preview", - "created": 1765987078, - "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...", - "context_length": 1048576, + "id": "cohere/command-r-plus-08-2024", + "canonical_slug": "cohere/command-r-plus-08-2024", + "hugging_face_id": null, + "name": "Cohere: Command R+ (08-2024)", + "created": 1724976000, + "description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...", + "context_length": 128000, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "file", "audio", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "Cohere", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.000003", - "image": "0.0000005", - "audio": "0.000001", - "web_search": "0.014", - "internal_reasoning": "0.000003", - "input_cache_read": "0.00000005", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.0000025", + "completion": "0.00001" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65535, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", "max_tokens", - "reasoning", + "presence_penalty", "response_format", "seed", "stop", @@ -5806,420 +6245,319 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "agenticslides", - "elo": 1073, - "win_rate": 39.3, - "rank": 9 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1075, - "win_rate": 39.3, - "rank": 9 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1060, - "win_rate": 48, - "rank": 24 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1128, - "win_rate": 47.1, - "rank": 17 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1218, - "win_rate": 52.3, - "rank": 8 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1183, - "win_rate": 49.8, - "rank": 18 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1187, - "win_rate": 49.5, - "rank": 17 - }, - { - "arena": "models", - "category": "3d", - "elo": 1261, - "win_rate": 62.7, - "rank": 30 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1238, - "win_rate": 57.6, - "rank": 34 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1232, - "win_rate": 58.3, - "rank": 39 - }, - { - "arena": "models", - "category": "website", - "elo": 1239, - "win_rate": 57, - "rank": 34 - } - ] - }, - "reasoning": { - "mandatory": false, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "medium" + "details": "/api/v1/models/cohere/command-r-plus-08-2024/endpoints" } }, { - "id": "google/gemini-3-pro-image", - "canonical_slug": "google/gemini-3-pro-image-20260528", - "hugging_face_id": null, - "name": "Google: Nano Banana Pro (Gemini 3 Pro Image)", - "created": 1781754054, - "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", - "context_length": 65536, + "id": "cohere/command-r7b-12-2024", + "canonical_slug": "cohere/command-r7b-12-2024", + "hugging_face_id": "", + "name": "Cohere: Command R7B (12-2024)", + "created": 1734158152, + "description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...", + "context_length": 128000, "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Cohere", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000012", - "image": "0.000002", - "audio": "0.000002", - "web_search": "0.014", - "internal_reasoning": "0.000012", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375" + "prompt": "0.0000000375", + "completion": "0.00000015" }, "top_provider": { - "context_length": 65536, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", "max_tokens", - "reasoning", + "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3-pro-image-20260528/endpoints" - }, - "reasoning": { - "mandatory": true + "details": "/api/v1/models/cohere/command-r7b-12-2024/endpoints" } }, { - "id": "google/gemini-3-pro-image-preview", - "canonical_slug": "google/gemini-3-pro-image-preview-20251120", - "hugging_face_id": "", - "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", - "created": 1763653797, - "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", - "context_length": 65536, + "id": "cohere/north-mini-code:free", + "canonical_slug": "cohere/north-mini-code-20260617", + "hugging_face_id": "CohereLabs/North-Mini-Code-1.0", + "name": "Cohere: North Mini Code (free)", + "created": 1781723748, + "description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...", + "context_length": 256000, "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Cohere", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000012", - "image": "0.000002", - "audio": "0.000002", - "web_search": "0.014", - "internal_reasoning": "0.000012", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 65536, - "max_completion_tokens": 32768, - "is_moderated": false + "context_length": 256000, + "max_completion_tokens": 64000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", + "presence_penalty", "reasoning", - "response_format", "seed", "stop", - "structured_outputs", "temperature", + "tool_choice", + "tools", + "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints" + "details": "/api/v1/models/cohere/north-mini-code-20260617/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "graphicdesign", - "elo": 1286, - "win_rate": 66, - "rank": 3 - }, - { - "arena": "models", - "category": "image", - "elo": 1272, - "win_rate": 62.2, - "rank": 3 - }, - { - "arena": "models", - "category": "logo", - "elo": 1260, - "win_rate": 61, - "rank": 3 - }, - { - "arena": "models", - "category": "imageediting", - "elo": 1273, - "win_rate": 66.1, - "rank": 2 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 20.2, + "coding_index": 36.5, + "agentic_index": 3.1 + } }, "reasoning": { - "mandatory": true + "mandatory": false } }, { - "id": "google/gemini-3.1-flash-image", - "canonical_slug": "google/gemini-3.1-flash-image-20260528", - "hugging_face_id": null, - "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", - "created": 1781754065, - "description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...", - "context_length": 131072, + "id": "deepcogito/cogito-v2.1-671b", + "canonical_slug": "deepcogito/cogito-v2.1-671b-20251118", + "hugging_face_id": "", + "name": "Deep Cogito: Cogito v2.1 671B", + "created": 1763071233, + "description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...", + "context_length": 128000, "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.000003", - "web_search": "0.014" + "prompt": "0.00000125", + "completion": "0.00000125" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 128000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", "max_tokens", + "min_p", + "presence_penalty", "reasoning", + "repetition_penalty", "response_format", - "seed", + "stop", "structured_outputs", "temperature", + "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints" + "details": "/api/v1/models/deepcogito/cogito-v2.1-671b-20251118/endpoints" }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "minimal"], - "default_effort": "minimal" + "mandatory": false } }, { - "id": "google/gemini-3.1-flash-image-preview", - "canonical_slug": "google/gemini-3.1-flash-image-preview-20260226", - "hugging_face_id": "", - "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", - "created": 1772119558, - "description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...", - "context_length": 131072, + "id": "deepseek/deepseek-chat", + "canonical_slug": "deepseek/deepseek-chat-v3", + "hugging_face_id": "deepseek-ai/DeepSeek-V3", + "name": "DeepSeek: DeepSeek V3", + "created": 1735241320, + "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...", + "context_length": 163840, "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "DeepSeek", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.000003", - "web_search": "0.014" + "prompt": "0.0000002574", + "completion": "0.0000010287" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 128000, + "max_completion_tokens": 16000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", "max_tokens", - "reasoning", + "min_p", + "presence_penalty", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-07-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints" + "details": "/api/v1/models/deepseek/deepseek-chat-v3/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", - "category": "graphicdesign", - "elo": 1295, - "win_rate": 66.5, - "rank": 2 + "category": "3d", + "elo": 1142, + "win_rate": 50.8, + "rank": 69 }, { "arena": "models", - "category": "image", - "elo": 1304, - "win_rate": 65.3, - "rank": 2 + "category": "codecategories", + "elo": 1128, + "win_rate": 48.4, + "rank": 83 }, { "arena": "models", - "category": "logo", - "elo": 1282, - "win_rate": 63.1, - "rank": 2 + "category": "dataviz", + "elo": 1111, + "win_rate": 51.4, + "rank": 87 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1092, + "win_rate": 43.9, + "rank": 89 + }, + { + "arena": "models", + "category": "svg", + "elo": 1007, + "win_rate": 37.6, + "rank": 76 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1122, + "win_rate": 52.7, + "rank": 78 + }, + { + "arena": "models", + "category": "website", + "elo": 1131, + "win_rate": 48.5, + "rank": 83 } ] - }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "minimal"], - "default_effort": "minimal" } }, { - "id": "google/gemini-3.1-flash-lite", - "canonical_slug": "google/gemini-3.1-flash-lite-20260507", - "hugging_face_id": null, - "name": "Google: Gemini 3.1 Flash Lite", - "created": 1778168828, - "description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...", - "context_length": 1048576, + "id": "deepseek/deepseek-chat-v3-0324", + "canonical_slug": "deepseek/deepseek-chat-v3-0324", + "hugging_face_id": "deepseek-ai/DeepSeek-V3-0324", + "name": "DeepSeek: DeepSeek V3 0324", + "created": 1742824755, + "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...", + "context_length": 163840, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "video", "file", "audio"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", + "tokenizer": "DeepSeek", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.0000015", - "image": "0.00000025", - "audio": "0.0000005", - "web_search": "0.014", - "internal_reasoning": "0.0000015", - "input_cache_read": "0.000000025", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.00000027", + "completion": "0.00000112", + "input_cache_read": "0.000000135" }, "top_provider": { - "context_length": 1048576, + "context_length": 163840, "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", "max_tokens", - "reasoning", + "min_p", + "presence_penalty", + "repetition_penalty", "response_format", "seed", "stop", @@ -6227,113 +6565,168 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-07-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" + "details": "/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints" }, - "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "minimal" + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 15.2, + "coding_index": 21.2, + "agentic_index": 1.6 + } } }, { - "id": "google/gemini-3.1-flash-lite-image", - "canonical_slug": "google/gemini-3.1-flash-lite-image-20260630", - "hugging_face_id": null, - "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", - "created": 1782837225, - "description": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...", - "context_length": 65536, - "architecture": { - "modality": "text+image->text+image", - "input_modalities": ["image", "text"], - "output_modalities": ["image", "text"], - "tokenizer": "Gemini", - "instruct_type": null + "id": "deepseek/deepseek-chat-v3.1", + "canonical_slug": "deepseek/deepseek-chat-v3.1", + "hugging_face_id": "deepseek-ai/DeepSeek-V3.1", + "name": "DeepSeek: DeepSeek V3.1", + "created": 1755779628, + "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...", + "context_length": 163840, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" }, "pricing": { "prompt": "0.00000025", - "completion": "0.0000015", - "web_search": "0.014" + "completion": "0.00000095", + "input_cache_read": "0.00000013" }, "top_provider": { - "context_length": 65536, - "max_completion_tokens": 66000, + "context_length": 163840, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", + "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", + "structured_outputs", "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-01-01", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-flash-lite-image-20260630/endpoints" + "details": "/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1133, + "win_rate": 48.5, + "rank": 75 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1131, + "win_rate": 47.8, + "rank": 81 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1119, + "win_rate": 46, + "rank": 86 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1123, + "win_rate": 47.3, + "rank": 82 + }, + { + "arena": "models", + "category": "svg", + "elo": 998, + "win_rate": 37.3, + "rank": 77 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1113, + "win_rate": 47.3, + "rank": 80 + }, + { + "arena": "models", + "category": "website", + "elo": 1133, + "win_rate": 47.9, + "rank": 82 + } + ] }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "minimal"], - "default_effort": "minimal" + "mandatory": false } }, { - "id": "google/gemini-3.1-flash-lite-preview", - "canonical_slug": "google/gemini-3.1-flash-lite-preview-20260303", - "hugging_face_id": "", - "name": "Google: Gemini 3.1 Flash Lite Preview", - "created": 1772512673, - "description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...", - "context_length": 1048576, + "id": "deepseek/deepseek-r1", + "canonical_slug": "deepseek/deepseek-r1", + "hugging_face_id": "deepseek-ai/DeepSeek-R1", + "name": "DeepSeek: R1", + "created": 1737381095, + "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....", + "context_length": 64000, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "video", "file", "audio"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-r1" }, "pricing": { - "prompt": "0.00000025", - "completion": "0.0000015", - "image": "0.00000025", - "audio": "0.0000005", - "web_search": "0.014", - "internal_reasoning": "0.0000015", - "input_cache_read": "0.000000025", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.0000007", + "completion": "0.0000025" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 64000, + "max_completion_tokens": 16000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", + "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", "stop", @@ -6341,6 +6734,7 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], "default_parameters": { @@ -6352,118 +6746,59 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-07-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints" + "details": "/api/v1/models/deepseek/deepseek-r1/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1126, - "win_rate": 38.8, - "rank": 73 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1214, - "win_rate": 50.7, - "rank": 16 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1121, - "win_rate": 36.4, - "rank": 77 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1088, - "win_rate": 33.3, - "rank": 79 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1097, - "win_rate": 34, - "rank": 80 - }, - { - "arena": "models", - "category": "svg", - "elo": 1109, - "win_rate": 42.5, - "rank": 52 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1125, - "win_rate": 37.7, - "rank": 70 - }, - { - "arena": "models", - "category": "website", - "elo": 1124, - "win_rate": 36.5, - "rank": 79 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 25, - "coding_index": 34.7, - "agentic_index": 6.2 + "intelligence_index": 18.6, + "coding_index": 24.6, + "agentic_index": 3.1 } }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "minimal" + "mandatory": true } }, { - "id": "google/gemini-3.1-pro-preview", - "canonical_slug": "google/gemini-3.1-pro-preview-20260219", - "hugging_face_id": "", - "name": "Google: Gemini 3.1 Pro Preview", - "created": 1771509627, - "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...", - "context_length": 1048576, + "id": "deepseek/deepseek-r1-0528", + "canonical_slug": "deepseek/deepseek-r1-0528", + "hugging_face_id": "deepseek-ai/DeepSeek-R1-0528", + "name": "DeepSeek: R1 0528", + "created": 1748455170, + "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...", + "context_length": 163840, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["audio", "file", "image", "text", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-r1" }, "pricing": { - "prompt": "0.000002", - "completion": "0.000012", - "image": "0.000002", - "audio": "0.000002", - "web_search": "0.014", - "internal_reasoning": "0.000012", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375" + "prompt": "0.0000005", + "completion": "0.00000215", + "input_cache_read": "0.00000035" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 163840, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", + "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", "stop", @@ -6471,279 +6806,162 @@ "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" + "details": "/api/v1/models/deepseek/deepseek-r1-0528/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1141, - "win_rate": 43.7, - "rank": 10 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1226, - "win_rate": 55.8, - "rank": 5 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1112, - "win_rate": 33.8, - "rank": 8 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1219, - "win_rate": 54.4, - "rank": 5 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1107, - "win_rate": 33.9, - "rank": 8 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1056, - "win_rate": 39, - "rank": 25 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1138, - "win_rate": 44.7, - "rank": 16 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1219, - "win_rate": 53.5, - "rank": 7 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1206, - "win_rate": 52.3, - "rank": 6 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1172, - "win_rate": 46.5, - "rank": 23 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1110, - "win_rate": 34.1, - "rank": 8 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1109, - "win_rate": 31.9, - "rank": 10 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1197, - "win_rate": 48, - "rank": 13 - }, { "arena": "models", "category": "3d", - "elo": 1308, - "win_rate": 60.7, - "rank": 15 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1315, - "win_rate": 63.6, - "rank": 3 + "elo": 1165, + "win_rate": 53.5, + "rank": 63 }, { "arena": "models", "category": "codecategories", - "elo": 1290, - "win_rate": 64.2, - "rank": 19 + "elo": 1158, + "win_rate": 52.6, + "rank": 70 }, { "arena": "models", "category": "dataviz", - "elo": 1269, - "win_rate": 60.6, - "rank": 23 + "elo": 1204, + "win_rate": 61, + "rank": 48 }, { "arena": "models", "category": "gamedev", - "elo": 1264, - "win_rate": 54.5, - "rank": 27 + "elo": 1137, + "win_rate": 49.6, + "rank": 74 }, { "arena": "models", "category": "svg", - "elo": 1347, - "win_rate": 70.3, - "rank": 2 + "elo": 1070, + "win_rate": 47.2, + "rank": 60 }, { "arena": "models", "category": "uicomponent", - "elo": 1320, - "win_rate": 68.1, - "rank": 8 + "elo": 1131, + "win_rate": 55.1, + "rank": 72 }, { "arena": "models", "category": "website", - "elo": 1294, - "win_rate": 64.3, - "rank": 16 + "elo": 1160, + "win_rate": 52.6, + "rank": 70 } - ], - "artificial_analysis": { - "intelligence_index": 46.5, - "coding_index": 68.8, - "agentic_index": 21.4 - } + ] }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low"], - "default_effort": "medium" + "mandatory": true } }, { - "id": "google/gemini-3.1-pro-preview-customtools", - "canonical_slug": "google/gemini-3.1-pro-preview-customtools-20260219", - "hugging_face_id": null, - "name": "Google: Gemini 3.1 Pro Preview Custom Tools", - "created": 1772045923, - "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...", - "context_length": 1048756, + "id": "deepseek/deepseek-r1-distill-llama-70b", + "canonical_slug": "deepseek/deepseek-r1-distill-llama-70b", + "hugging_face_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "name": "DeepSeek: R1 Distill Llama 70B", + "created": 1737663169, + "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...", + "context_length": 8192, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "audio", "image", "video", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null + "tokenizer": "Llama3", + "instruct_type": "deepseek-r1" }, "pricing": { - "prompt": "0.000002", - "completion": "0.000012", - "image": "0.000002", - "audio": "0.000002", - "web_search": "0.014", - "internal_reasoning": "0.000012", - "input_cache_read": "0.0000002", - "input_cache_write": "0.000000375" + "prompt": "0.0000008", + "completion": "0.0000008" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 8192, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", + "presence_penalty", "reasoning", - "response_format", + "repetition_penalty", "seed", - "structured_outputs", + "stop", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-07-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints" + "details": "/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints" }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "google/gemini-3.5-flash", - "canonical_slug": "google/gemini-3.5-flash-20260519", - "hugging_face_id": null, - "name": "Google: Gemini 3.5 Flash", - "created": 1779193800, - "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...", - "context_length": 1048576, + "id": "deepseek/deepseek-v3.1-terminus", + "canonical_slug": "deepseek/deepseek-v3.1-terminus", + "hugging_face_id": "deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "DeepSeek: DeepSeek V3.1 Terminus", + "created": 1758548275, + "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...", + "context_length": 163840, "architecture": { - "modality": "text+image+file+audio+video->text", - "input_modalities": ["text", "image", "video", "file", "audio"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": null + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" }, "pricing": { - "prompt": "0.0000015", - "completion": "0.000009", - "image": "0.0000015", - "audio": "0.000003", - "web_search": "0.014", - "internal_reasoning": "0.000009", - "input_cache_read": "0.00000015", - "input_cache_write": "0.00000008333333333333334" + "prompt": "0.00000027", + "completion": "0.00000095", + "input_cache_read": "0.00000013" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 163840, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", "max_tokens", + "min_p", + "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", "stop", @@ -6751,254 +6969,117 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-01-01", - "expiration_date": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": "2026-08-17", "links": { - "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1209, - "win_rate": 55.1, - "rank": 3 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1162, - "win_rate": 45.8, - "rank": 7 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1244, - "win_rate": 57.5, - "rank": 4 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1162, - "win_rate": 45.7, - "rank": 7 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1242, - "win_rate": 57.8, - "rank": 3 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1255, - "win_rate": 54.2, - "rank": 5 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1265, - "win_rate": 57.9, - "rank": 6 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1183, - "win_rate": 49, - "rank": 9 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1256, - "win_rate": 56.5, - "rank": 4 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1244, - "win_rate": 57.7, - "rank": 3 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1247, - "win_rate": 57.4, - "rank": 4 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1265, - "win_rate": 54.3, - "rank": 6 - }, { "arena": "models", "category": "3d", - "elo": 1315, - "win_rate": 59, - "rank": 13 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1308, - "win_rate": 61.6, - "rank": 4 + "elo": 1194, + "win_rate": 56.1, + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1306, - "win_rate": 57.9, - "rank": 13 + "elo": 1194, + "win_rate": 56, + "rank": 53 }, { "arena": "models", "category": "dataviz", - "elo": 1264, - "win_rate": 54.5, - "rank": 24 + "elo": 1191, + "win_rate": 53.9, + "rank": 53 }, { "arena": "models", "category": "gamedev", - "elo": 1330, - "win_rate": 59.3, - "rank": 9 + "elo": 1170, + "win_rate": 52.7, + "rank": 65 }, { "arena": "models", "category": "svg", - "elo": 1305, - "win_rate": 62.8, - "rank": 3 + "elo": 1094, + "win_rate": 48.1, + "rank": 56 }, { "arena": "models", "category": "uicomponent", - "elo": 1310, - "win_rate": 59.2, - "rank": 12 + "elo": 1210, + "win_rate": 59.5, + "rank": 45 }, { "arena": "models", "category": "website", - "elo": 1298, - "win_rate": 57.1, - "rank": 15 + "elo": 1198, + "win_rate": 56.2, + "rank": 55 } ], "artificial_analysis": { - "intelligence_index": 50.2, - "coding_index": 70.1, - "agentic_index": 37.4 + "intelligence_index": null, + "coding_index": 43.5, + "agentic_index": null } }, "reasoning": { - "mandatory": true, - "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "minimal"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "google/gemma-2-27b-it", - "canonical_slug": "google/gemma-2-27b-it", - "hugging_face_id": "google/gemma-2-27b-it", - "name": "Google: Gemma 2 27B", - "created": 1720828800, - "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...", - "context_length": 8192, + "id": "deepseek/deepseek-v3.2", + "canonical_slug": "deepseek/deepseek-v3.2-20251201", + "hugging_face_id": "deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek: DeepSeek V3.2", + "created": 1764594642, + "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", + "context_length": 163840, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": "gemma" - }, - "pricing": { - "prompt": "0.00000065", - "completion": "0.00000065" - }, - "top_provider": { - "context_length": 8192, - "max_completion_tokens": 2048, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-06-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/google/gemma-2-27b-it/endpoints" - } - }, - { - "id": "google/gemma-3-12b-it", - "canonical_slug": "google/gemma-3-12b-it", - "hugging_face_id": "google/gemma-3-12b-it", - "name": "Google: Gemma 3 12B", - "created": 1741902625, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": "gemma" + "tokenizer": "DeepSeek", + "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000015" + "prompt": "0.000000269", + "completion": "0.0000004", + "input_cache_read": "0.0000001345" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 163840, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", @@ -7008,301 +7089,367 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-3-12b-it/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 5.5, - "coding_index": 5.8, - "agentic_index": 0.3 - } - } - }, - { - "id": "google/gemma-3-27b-it", - "canonical_slug": "google/gemma-3-27b-it", - "hugging_face_id": "google/gemma-3-27b-it", - "name": "Google: Gemma 3 27B", - "created": 1741756359, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": "gemma" - }, - "pricing": { - "prompt": "0.00000008", - "completion": "0.00000016" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2024-08-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/google/gemma-3-27b-it/endpoints" - }, - "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1187, + "win_rate": 49.6, + "rank": 54 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1115, + "win_rate": 40.5, + "rank": 50 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1183, + "win_rate": 49.3, + "rank": 62 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1181, + "win_rate": 48.2, + "rank": 61 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1169, + "win_rate": 46.6, + "rank": 66 + }, + { + "arena": "models", + "category": "svg", + "elo": 1062, + "win_rate": 39.8, + "rank": 65 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1176, + "win_rate": 46.8, + "rank": 61 + }, + { + "arena": "models", + "category": "website", + "elo": 1186, + "win_rate": 50.1, + "rank": 61 + } + ], "artificial_analysis": { - "intelligence_index": 7.4, - "coding_index": 10.1, - "agentic_index": 0.3 + "intelligence_index": null, + "coding_index": 44.2, + "agentic_index": null } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false } }, { - "id": "google/gemma-3-4b-it", - "canonical_slug": "google/gemma-3-4b-it", - "hugging_face_id": "google/gemma-3-4b-it", - "name": "Google: Gemma 3 4B", - "created": 1741905510, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, + "id": "deepseek/deepseek-v3.2-exp", + "canonical_slug": "deepseek/deepseek-v3.2-exp", + "hugging_face_id": "deepseek-ai/DeepSeek-V3.2-Exp", + "name": "DeepSeek: DeepSeek V3.2 Exp", + "created": 1759150481, + "description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", + "context_length": 163840, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemini", - "instruct_type": "gemma" + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000001" + "prompt": "0.00000027", + "completion": "0.00000041" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 163840, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 0.6, + "top_p": 0.95, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": "2025-07-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-3-4b-it/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 2.7, - "agentic_index": null - } + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1202, + "win_rate": 56.4, + "rank": 49 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1190, + "win_rate": 54.2, + "rank": 55 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1175, + "win_rate": 50.9, + "rank": 64 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1183, + "win_rate": 53.2, + "rank": 58 + }, + { + "arena": "models", + "category": "svg", + "elo": 1065, + "win_rate": 41.2, + "rank": 61 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1195, + "win_rate": 53.4, + "rank": 55 + }, + { + "arena": "models", + "category": "website", + "elo": 1190, + "win_rate": 54.2, + "rank": 59 + } + ] + }, + "reasoning": { + "mandatory": false } }, { - "id": "google/gemma-3n-e4b-it", - "canonical_slug": "google/gemma-3n-e4b-it", - "hugging_face_id": "google/gemma-3n-E4B-it", - "name": "Google: Gemma 3n 4B", - "created": 1747776824, - "description": "Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...", - "context_length": 32768, + "id": "deepseek/deepseek-v4-flash", + "canonical_slug": "deepseek/deepseek-v4-flash-20260423", + "hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash", + "name": "DeepSeek: DeepSeek V4 Flash 0423", + "created": 1777000666, + "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...", + "context_length": 1048576, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "DeepSeek", "instruct_type": null }, "pricing": { - "prompt": "0.00000006", - "completion": "0.00000012" + "prompt": "0.00000006146", + "completion": "0.00000012292", + "input_cache_read": "0.000000012292" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, + "context_length": 1024000, + "max_completion_tokens": 384000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", + "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", + "seed", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", + "top_a", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-3n-e4b-it/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 3.2, - "agentic_index": null - } - } - }, - { - "id": "google/gemma-4-26b-a4b-it", - "canonical_slug": "google/gemma-4-26b-a4b-it-20260403", - "hugging_face_id": "google/gemma-4-26B-A4B-it", - "name": "Google: Gemma 4 26B A4B ", - "created": 1775227989, - "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", - "context_length": 262144, - "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemma", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000006", - "completion": "0.00000033" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", - "logprobs", - "max_tokens", - "min_p", - "presence_penalty", - "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": 64 - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 25.7, - "coding_index": 39.3, - "agentic_index": 11 - } + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1242, + "win_rate": 49.3, + "rank": 39 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1143, + "win_rate": 42.8, + "rank": 45 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1225, + "win_rate": 48.9, + "rank": 42 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1149, + "win_rate": 40.6, + "rank": 73 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1234, + "win_rate": 50.2, + "rank": 39 + }, + { + "arena": "models", + "category": "svg", + "elo": 1188, + "win_rate": 48.9, + "rank": 30 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1193, + "win_rate": 44.7, + "rank": 57 + }, + { + "arena": "models", + "category": "website", + "elo": 1219, + "win_rate": 49.1, + "rank": 44 + } + ] }, "reasoning": { "mandatory": false, - "default_enabled": false + "supported_efforts": ["xhigh", "high"], + "default_effort": "high" } }, { - "id": "google/gemma-4-26b-a4b-it:free", - "canonical_slug": "google/gemma-4-26b-a4b-it-20260403", - "hugging_face_id": "google/gemma-4-26B-A4B-it", - "name": "Google: Gemma 4 26B A4B (free)", - "created": 1775227989, - "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", - "context_length": 262144, + "id": "deepseek/deepseek-v4-flash-0731", + "canonical_slug": "deepseek/deepseek-v4-flash-20260731", + "hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash-0731", + "name": "DeepSeek: DeepSeek V4 Flash 0731", + "created": 1785478908, + "description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....", + "context_length": 1048576, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemma", + "tokenizer": "DeepSeek", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00000014", + "completion": "0.00000028", + "input_cache_read": "0.000000028" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 1048576, + "max_completion_tokens": 393216, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -7311,57 +7458,99 @@ "temperature", "tool_choice", "tools", + "top_a", "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": 64 - }, - "supported_voices": null, + "default_parameters": {}, + "supported_voices": [], "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1271, + "win_rate": 52.1, + "rank": 28 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1253, + "win_rate": 47.7, + "rank": 34 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1185, + "win_rate": 38.7, + "rank": 58 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1256, + "win_rate": 46.9, + "rank": 31 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1263, + "win_rate": 46.9, + "rank": 33 + }, + { + "arena": "models", + "category": "website", + "elo": 1252, + "win_rate": 47.6, + "rank": 33 + } + ], "artificial_analysis": { - "intelligence_index": 25.7, - "coding_index": 39.3, - "agentic_index": 11 + "intelligence_index": 51.8, + "coding_index": 69.1, + "agentic_index": 48.4 } }, "reasoning": { "mandatory": false, - "default_enabled": false + "default_enabled": true, + "supported_efforts": ["max", "high", "low"], + "default_effort": "high" } }, { - "id": "google/gemma-4-31b-it", - "canonical_slug": "google/gemma-4-31b-it-20260402", - "hugging_face_id": "google/gemma-4-31B-it", - "name": "Google: Gemma 4 31B", - "created": 1775148486, - "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", - "context_length": 262144, + "id": "deepseek/deepseek-v4-pro", + "canonical_slug": "deepseek/deepseek-v4-pro-20260423", + "hugging_face_id": "deepseek-ai/DeepSeek-V4-Pro", + "name": "DeepSeek: DeepSeek V4 Pro", + "created": 1777000679, + "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...", + "context_length": 1048576, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Gemma", + "tokenizer": "DeepSeek", "instruct_type": null }, "pricing": { - "prompt": "0.00000012", - "completion": "0.00000035", - "input_cache_read": "0.00000009" + "prompt": "0.000001168", + "completion": "0.000002336", + "input_cache_read": "0.00000009855" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 1048576, + "max_completion_tokens": 393216, "is_moderated": false }, "per_request_limits": null, @@ -7370,10 +7559,12 @@ "include_reasoning", "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -7388,110 +7579,185 @@ ], "default_parameters": { "temperature": 1, - "top_p": 0.95, - "top_k": 64, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "top_p": 1 }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 29.4, - "coding_index": 43.4, - "agentic_index": 14.4 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": false - } - }, - { - "id": "google/gemma-4-31b-it:free", - "canonical_slug": "google/gemma-4-31b-it-20260402", - "hugging_face_id": "google/gemma-4-31B-it", - "name": "Google: Gemma 4 31B (free)", - "created": 1775148486, - "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", - "context_length": 262144, - "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], - "output_modalities": ["text"], - "tokenizer": "Gemma", - "instruct_type": null + "design_arena": [ + { + "arena": "agents", + "category": "fullstack", + "elo": 948, + "win_rate": 22.1, + "rank": 39 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1059, + "win_rate": 34, + "rank": 27 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1000, + "win_rate": 26.4, + "rank": 37 + }, + { + "arena": "models", + "category": "3d", + "elo": 1309, + "win_rate": 57.5, + "rank": 15 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1182, + "win_rate": 46.5, + "rank": 29 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1261, + "win_rate": 53, + "rank": 30 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1226, + "win_rate": 49.2, + "rank": 42 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1270, + "win_rate": 54.3, + "rank": 28 + }, + { + "arena": "models", + "category": "svg", + "elo": 1172, + "win_rate": 46.8, + "rank": 38 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1251, + "win_rate": 51.4, + "rank": 36 + }, + { + "arena": "models", + "category": "website", + "elo": 1246, + "win_rate": 51.5, + "rank": 35 + } + ] + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["xhigh", "high"], + "default_effort": "high" + } + }, + { + "id": "deepseek/deepseek-v4-pro-0813", + "canonical_slug": "deepseek/deepseek-v4-pro-20260813", + "hugging_face_id": "deepseek-ai/DeepSeek-V4-Pro-0813", + "name": "DeepSeek: DeepSeek V4 Pro 0813", + "created": 1786549364, + "description": "DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.", + "context_length": 1048576, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "DeepSeek", + "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000000435", + "completion": "0.00000087", + "input_cache_read": "0.000000003625" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 8192, - "is_moderated": true + "context_length": 1048576, + "max_completion_tokens": 384000, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", "min_p", + "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_a", "top_k", + "top_logprobs", "top_p" ], "default_parameters": { "temperature": 1, - "top_p": 0.95, - "top_k": 64, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "top_p": 1 }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" + "details": "/api/v1/models/deepseek/deepseek-v4-pro-20260813/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 29.4, - "coding_index": 43.4, - "agentic_index": 14.4 + "intelligence_index": 53.2, + "coding_index": 68.8, + "agentic_index": 49.6 } }, "reasoning": { "mandatory": false, - "default_enabled": false + "supported_efforts": ["max", "high", "low"], + "default_effort": "high" } }, { - "id": "google/lyria-3-clip-preview", - "canonical_slug": "google/lyria-3-clip-preview-20260330", + "id": "dots-studio/dots-3-note-preview:free", + "canonical_slug": "dots-studio/dots-3-note-preview-20260813", "hugging_face_id": null, - "name": "Google: Lyria 3 Clip Preview", - "created": 1774907255, - "description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...", - "context_length": 1048576, + "name": "Dots Studio: Dots3-Note Preview (free)", + "created": 1786680361, + "description": "Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...", + "context_length": 512000, "architecture": { - "modality": "text+image->text+audio", + "modality": "text+image->text", "input_modalities": ["text", "image"], - "output_modalities": ["text", "audio"], + "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, @@ -7500,63 +7766,76 @@ "completion": "0" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 65536, + "context_length": 512000, + "max_completion_tokens": 512000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "include_reasoning", "max_tokens", + "reasoning", "response_format", - "seed", + "structured_outputs", "temperature", + "tool_choice", + "tools", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints" + "details": "/api/v1/models/dots-studio/dots-3-note-preview-20260813/endpoints" + }, + "reasoning": { + "mandatory": false } }, { - "id": "google/lyria-3-pro-preview", - "canonical_slug": "google/lyria-3-pro-preview-20260330", - "hugging_face_id": null, - "name": "Google: Lyria 3 Pro Preview", - "created": 1774907286, - "description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...", + "id": "google/gemini-2.5-flash", + "canonical_slug": "google/gemini-2.5-flash", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Flash", + "created": 1750172488, + "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", "context_length": 1048576, "architecture": { - "modality": "text+image->text+audio", - "input_modalities": ["text", "image"], - "output_modalities": ["text", "audio"], - "tokenizer": "Other", + "modality": "text+image+file+audio+video->text", + "input_modalities": ["file", "image", "text", "audio", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.0000003", + "completion": "0.0000025", + "image": "0.0000003", + "audio": "0.000001", + "input_audio_cache": "0.0000001", + "web_search": "0.014", + "internal_reasoning": "0.0000025", + "input_cache_read": "0.00000003", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { "context_length": 1048576, - "max_completion_tokens": 65536, + "max_completion_tokens": 65535, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "include_reasoning", "max_tokens", + "reasoning", "response_format", "seed", + "stop", + "structured_outputs", "temperature", + "tool_choice", + "tools", "top_p" ], "default_parameters": { @@ -7568,102 +7847,190 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints" + "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1125, + "win_rate": 47.8, + "rank": 82 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1123, + "win_rate": 46.9, + "rank": 84 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1157, + "win_rate": 49.1, + "rank": 70 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1103, + "win_rate": 44.5, + "rank": 88 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1121, + "win_rate": 48.8, + "rank": 79 + }, + { + "arena": "models", + "category": "website", + "elo": 1126, + "win_rate": 47.1, + "rank": 86 + }, + { + "arena": "models", + "category": "svg", + "elo": 1051, + "win_rate": 42, + "rank": 66 + } + ] + }, + "reasoning": { + "mandatory": false } }, { - "id": "gryphe/mythomax-l2-13b", - "canonical_slug": "gryphe/mythomax-l2-13b", - "hugging_face_id": "Gryphe/MythoMax-L2-13b", - "name": "MythoMax 13B", - "created": 1688256000, - "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge", - "context_length": 4096, + "id": "google/gemini-2.5-flash-image", + "canonical_slug": "google/gemini-2.5-flash-image", + "hugging_face_id": "", + "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", + "created": 1759870431, + "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...", + "context_length": 32768, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama2", - "instruct_type": "alpaca" + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.00000006", - "completion": "0.00000006" + "prompt": "0.0000003", + "completion": "0.0000025", + "image": "0.0000003", + "image_output": "0.00003", + "audio": "0.000001", + "input_audio_cache": "0.0000001", + "web_search": "0.014", + "internal_reasoning": "0.0000025", + "input_cache_read": "0.00000003", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { - "context_length": 4096, - "max_completion_tokens": 4096, + "context_length": 32768, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "top_a", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-06-30", + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/gryphe/mythomax-l2-13b/endpoints" + "details": "/api/v1/models/google/gemini-2.5-flash-image/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "graphicdesign", + "elo": 1192, + "win_rate": 56.9, + "rank": 8 + }, + { + "arena": "models", + "category": "image", + "elo": 1206, + "win_rate": 55.6, + "rank": 8 + }, + { + "arena": "models", + "category": "logo", + "elo": 1181, + "win_rate": 51.4, + "rank": 9 + } + ] } }, { - "id": "ibm-granite/granite-4.0-h-micro", - "canonical_slug": "ibm-granite/granite-4.0-h-micro", - "hugging_face_id": "ibm-granite/granite-4.0-h-micro", - "name": "IBM: Granite 4.0 Micro", - "created": 1760927695, - "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...", - "context_length": 131000, + "id": "google/gemini-2.5-flash-lite", + "canonical_slug": "google/gemini-2.5-flash-lite", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Flash Lite", + "created": 1753200276, + "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.000000017", - "completion": "0.000000112" + "prompt": "0.0000001", + "completion": "0.0000004", + "image": "0.0000001", + "audio": "0.0000003", + "input_audio_cache": "0.00000003", + "web_search": "0.014", + "internal_reasoning": "0.0000004", + "input_cache_read": "0.00000001", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { - "context_length": 131000, - "max_completion_tokens": 131000, + "context_length": 1048576, + "max_completion_tokens": 65535, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", "seed", "stop", + "structured_outputs", "temperature", - "top_k", - "top_logprobs", + "tool_choice", + "tools", "top_p" ], "default_parameters": { @@ -7672,44 +8039,50 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints" + "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" + }, + "reasoning": { + "mandatory": false } }, { - "id": "ibm-granite/granite-4.1-8b", - "canonical_slug": "ibm-granite/granite-4.1-8b-20260429", - "hugging_face_id": "ibm-granite/granite-4.1-8b", - "name": "IBM: Granite 4.1 8B", - "created": 1777577071, - "description": "Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...", - "context_length": 131072, + "id": "google/gemini-2.5-flash-lite:batch", + "canonical_slug": "google/gemini-2.5-flash-lite", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Flash Lite (batch)", + "created": 1753200276, + "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { "prompt": "0.00000005", - "completion": "0.0000001", - "input_cache_read": "0.00000005" + "completion": "0.0000002", + "image": "0.00000005", + "audio": "0.00000015", + "input_audio_cache": "0.00000003", + "web_search": "0.014", + "internal_reasoning": "0.0000002", + "input_cache_read": "0.00000001" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, + "context_length": 1048576, + "max_completion_tokens": 65535, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", "seed", "stop", @@ -7717,56 +8090,51 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/ibm-granite/granite-4.1-8b-20260429/endpoints" + "details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 9.5, - "agentic_index": null - } + "reasoning": { + "mandatory": false } }, { - "id": "inception/mercury-2", - "canonical_slug": "inception/mercury-2-20260304", - "hugging_face_id": null, - "name": "Inception: Mercury 2", - "created": 1772636275, - "description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...", - "context_length": 128000, + "id": "google/gemini-2.5-flash:batch", + "canonical_slug": "google/gemini-2.5-flash", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Flash (batch)", + "created": 1750172488, + "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["file", "image", "text", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.00000075", - "input_cache_read": "0.000000025" + "prompt": "0.00000015", + "completion": "0.00000125", + "image": "0.00000015", + "audio": "0.0000005", + "input_audio_cache": "0.0000001", + "web_search": "0.014", + "internal_reasoning": "0.00000125", + "input_cache_read": "0.00000003" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 50000, + "context_length": 1048576, + "max_completion_tokens": 65535, "is_moderated": false }, "per_request_limits": null, @@ -7775,14 +8143,16 @@ "max_tokens", "reasoning", "response_format", + "seed", "stop", "structured_outputs", "temperature", "tool_choice", - "tools" + "tools", + "top_p" ], "default_parameters": { - "temperature": 0.75, + "temperature": null, "top_p": null, "top_k": null, "frequency_penalty": null, @@ -7790,96 +8160,114 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/inception/mercury-2-20260304/endpoints" + "details": "/api/v1/models/google/gemini-2.5-flash/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1059, - "win_rate": 25.1, - "rank": 85 + "elo": 1125, + "win_rate": 47.8, + "rank": 82 }, { "arena": "models", "category": "codecategories", - "elo": 1042, - "win_rate": 21.8, - "rank": 94 + "elo": 1123, + "win_rate": 46.9, + "rank": 84 }, { "arena": "models", "category": "dataviz", - "elo": 991, - "win_rate": 18.9, - "rank": 90 + "elo": 1157, + "win_rate": 49.1, + "rank": 70 }, { "arena": "models", "category": "gamedev", - "elo": 1044, - "win_rate": 21.4, - "rank": 89 + "elo": 1103, + "win_rate": 44.5, + "rank": 88 }, { "arena": "models", "category": "uicomponent", - "elo": 1023, - "win_rate": 20.4, - "rank": 86 + "elo": 1121, + "win_rate": 48.8, + "rank": 79 }, { "arena": "models", "category": "website", - "elo": 1034, - "win_rate": 21, - "rank": 96 + "elo": 1126, + "win_rate": 47.1, + "rank": 86 + }, + { + "arena": "models", + "category": "svg", + "elo": 1051, + "win_rate": 42, + "rank": 66 } ] }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "none"], - "default_effort": "medium" + "mandatory": false } }, { - "id": "inclusionai/ling-2.6-1t", - "canonical_slug": "inclusionai/ling-2.6-1t-20260423", - "hugging_face_id": null, - "name": "inclusionAI: Ling-2.6-1T", - "created": 1776948238, - "description": "Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...", - "context_length": 262144, + "id": "google/gemini-2.5-pro", + "canonical_slug": "google/gemini-2.5-pro", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Pro", + "created": 1750169544, + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.000000075", - "completion": "0.000000625", - "input_cache_read": "0.000000015" + "prompt": "0.00000125", + "completion": "0.00001", + "image": "0.00000125", + "audio": "0.00000125", + "input_audio_cache": "0.000000125", + "web_search": "0.014", + "internal_reasoning": "0.00001", + "input_cache_read": "0.000000125", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000015", + "audio": "0.0000025", + "input_audio_cache": "0.00000025", + "input_cache_read": "0.00000025" + } + ] }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", "seed", "stop", @@ -7887,57 +8275,120 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/inclusionai/ling-2.6-1t-20260423/endpoints" + "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1134, + "win_rate": 50.6, + "rank": 74 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1171, + "win_rate": 57.5, + "rank": 64 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1244, + "win_rate": 68.2, + "rank": 34 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1150, + "win_rate": 54.2, + "rank": 71 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1168, + "win_rate": 57.5, + "rank": 66 + }, + { + "arena": "models", + "category": "website", + "elo": 1178, + "win_rate": 58.4, + "rank": 64 + } + ], + "artificial_analysis": { + "intelligence_index": 25.9, + "coding_index": 33.3, + "agentic_index": 7.2 + } + }, + "reasoning": { + "mandatory": true } }, { - "id": "inclusionai/ling-2.6-flash", - "canonical_slug": "inclusionai/ling-2.6-flash-20260421", + "id": "google/gemini-2.5-pro-preview", + "canonical_slug": "google/gemini-2.5-pro-preview-06-05", "hugging_face_id": "", - "name": "inclusionAI: Ling-2.6-flash", - "created": 1776795886, - "description": "Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....", - "context_length": 262144, + "name": "Google: Gemini 2.5 Pro Preview 06-05", + "created": 1749137257, + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio->text", + "input_modalities": ["file", "image", "text", "audio"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.00000001", - "completion": "0.00000003", - "input_cache_read": "0.000000002" + "prompt": "0.00000125", + "completion": "0.00001", + "image": "0.00000125", + "audio": "0.00000125", + "input_audio_cache": "0.000000125", + "web_search": "0.014", + "internal_reasoning": "0.00001", + "input_cache_read": "0.000000125", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000015", + "audio": "0.0000025", + "input_audio_cache": "0.00000025", + "input_cache_read": "0.00000025" + } + ] }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", "seed", "stop", @@ -7945,205 +8396,246 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/inclusionai/ling-2.6-flash-20260421/endpoints" + "details": "/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 14.1, - "coding_index": 25.3, - "agentic_index": 2.3 - } + "reasoning": { + "mandatory": true } }, { - "id": "inclusionai/ring-2.6-1t", - "canonical_slug": "inclusionai/ring-2.6-1t-20260508", - "hugging_face_id": null, - "name": "inclusionAI: Ring-2.6-1T", - "created": 1778247440, - "description": "Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...", - "context_length": 262144, + "id": "google/gemini-2.5-pro-preview-05-06", + "canonical_slug": "google/gemini-2.5-pro-preview-03-25", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Pro Preview 05-06", + "created": 1746578513, + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.000000075", - "completion": "0.000000625", - "input_cache_read": "0.000000015" + "prompt": "0.00000125", + "completion": "0.00001", + "image": "0.00000125", + "audio": "0.00000125", + "input_audio_cache": "0.000000125", + "web_search": "0.014", + "internal_reasoning": "0.00001", + "input_cache_read": "0.000000125", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000015", + "audio": "0.0000025", + "input_audio_cache": "0.00000025", + "input_cache_read": "0.00000025" + } + ] }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 65536, + "context_length": 1048576, + "max_completion_tokens": 65535, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/inclusionai/ring-2.6-1t-20260508/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 30.6, - "coding_index": 42.8, - "agentic_index": 18.9 - } + "details": "/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints" }, "reasoning": { - "mandatory": true, - "supported_efforts": ["xhigh", "high"], - "default_effort": "high" + "mandatory": true } }, { - "id": "inflection/inflection-3-pi", - "canonical_slug": "inflection/inflection-3-pi", - "hugging_face_id": null, - "name": "Inflection: Inflection 3 Pi", - "created": 1728604800, - "description": "Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...", - "context_length": 8000, + "id": "google/gemini-2.5-pro:batch", + "canonical_slug": "google/gemini-2.5-pro", + "hugging_face_id": "", + "name": "Google: Gemini 2.5 Pro (batch)", + "created": 1750169544, + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.00001" + "prompt": "0.000000625", + "completion": "0.000005", + "image": "0.000000625", + "audio": "0.000000625", + "input_audio_cache": "0.000000125", + "web_search": "0.014", + "internal_reasoning": "0.000005", + "input_cache_read": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.00000125", + "completion": "0.0000075", + "audio": "0.00000125", + "input_audio_cache": "0.00000025", + "input_cache_read": "0.00000025" + } + ] }, "top_provider": { - "context_length": 8000, - "max_completion_tokens": 1024, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, - "supported_parameters": ["max_tokens", "stop", "temperature", "top_p"], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/inflection/inflection-3-pi/endpoints" - } - }, - { - "id": "inflection/inflection-3-productivity", - "canonical_slug": "inflection/inflection-3-productivity", - "hugging_face_id": null, - "name": "Inflection: Inflection 3 Productivity", - "created": 1728604800, - "description": "Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional...", - "context_length": 8000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000025", - "completion": "0.00001" - }, - "top_provider": { - "context_length": 8000, - "max_completion_tokens": 1024, - "is_moderated": false + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null }, - "per_request_limits": null, - "supported_parameters": ["max_tokens", "stop", "temperature", "top_p"], - "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-10-31", + "knowledge_cutoff": "2025-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/inflection/inflection-3-productivity/endpoints" + "details": "/api/v1/models/google/gemini-2.5-pro/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1134, + "win_rate": 50.6, + "rank": 74 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1171, + "win_rate": 57.5, + "rank": 64 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1244, + "win_rate": 68.2, + "rank": 34 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1150, + "win_rate": 54.2, + "rank": 71 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1168, + "win_rate": 57.5, + "rank": 66 + }, + { + "arena": "models", + "category": "website", + "elo": 1178, + "win_rate": 58.4, + "rank": 64 + } + ], + "artificial_analysis": { + "intelligence_index": 25.9, + "coding_index": 33.3, + "agentic_index": 7.2 + } + }, + "reasoning": { + "mandatory": true } }, { - "id": "kwaipilot/kat-coder-pro-v2", - "canonical_slug": "kwaipilot/kat-coder-pro-v2-20260327", + "id": "google/gemini-3-flash-preview", + "canonical_slug": "google/gemini-3-flash-preview-20251217", "hugging_face_id": "", - "name": "Kwaipilot: KAT-Coder-Pro V2", - "created": 1774649310, - "description": "KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...", - "context_length": 256000, + "name": "Google: Gemini 3 Flash Preview", + "created": 1765987078, + "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", - "input_cache_read": "0.00000006" + "prompt": "0.0000005", + "completion": "0.000003", + "image": "0.0000005", + "audio": "0.000001", + "input_audio_cache": "0.0000001", + "web_search": "0.014", + "internal_reasoning": "0.000003", + "input_cache_read": "0.00000005", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": 80000, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", "stop", @@ -8151,8 +8643,6 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -8167,152 +8657,352 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/kwaipilot/kat-coder-pro-v2-20260327/endpoints" + "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticslides", + "elo": 1073, + "win_rate": 39.3, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1075, + "win_rate": 39.3, + "rank": 9 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1086, + "win_rate": 48.1, + "rank": 31 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1099, + "win_rate": 47.1, + "rank": 27 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1161, + "win_rate": 50.6, + "rank": 14 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1144, + "win_rate": 46.6, + "rank": 30 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1022, + "win_rate": 38.3, + "rank": 21 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1161, + "win_rate": 49.6, + "rank": 27 + }, + { + "arena": "models", + "category": "3d", + "elo": 1238, + "win_rate": 62.7, + "rank": 40 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1208, + "win_rate": 57.6, + "rank": 45 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1204, + "win_rate": 58.3, + "rank": 50 + }, + { + "arena": "models", + "category": "website", + "elo": 1207, + "win_rate": 57, + "rank": 47 + } + ] + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "liquid/lfm-2-24b-a2b", - "canonical_slug": "liquid/lfm-2-24b-a2b-20260224", - "hugging_face_id": "LiquidAI/LFM2-24B-A2B", - "name": "LiquidAI: LFM2-24B-A2B", - "created": 1772048711, - "description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...", - "context_length": 128000, + "id": "google/gemini-3-flash-preview:batch", + "canonical_slug": "google/gemini-3-flash-preview-20251217", + "hugging_face_id": "", + "name": "Google: Gemini 3 Flash Preview (batch)", + "created": 1765987078, + "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "file", "audio", "video"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0.00000003", - "completion": "0.00000012" + "prompt": "0.00000025", + "completion": "0.0000015", + "image": "0.00000025", + "audio": "0.0000005", + "web_search": "0.014", + "internal_reasoning": "0.0000015" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", + "seed", "stop", + "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", "top_p" ], "default_parameters": { - "temperature": 0.1, + "temperature": null, "top_p": null, - "top_k": 50, + "top_k": null, "frequency_penalty": null, "presence_penalty": null, - "repetition_penalty": 1.05 + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/liquid/lfm-2-24b-a2b-20260224/endpoints" + "details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticslides", + "elo": 1073, + "win_rate": 39.3, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1075, + "win_rate": 39.3, + "rank": 9 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1086, + "win_rate": 48.1, + "rank": 31 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1099, + "win_rate": 47.1, + "rank": 27 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1161, + "win_rate": 50.6, + "rank": 14 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1144, + "win_rate": 46.6, + "rank": 30 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1022, + "win_rate": 38.3, + "rank": 21 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1161, + "win_rate": 49.6, + "rank": 27 + }, + { + "arena": "models", + "category": "3d", + "elo": 1238, + "win_rate": 62.7, + "rank": 40 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1208, + "win_rate": 57.6, + "rank": 45 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1204, + "win_rate": 58.3, + "rank": 50 + }, + { + "arena": "models", + "category": "website", + "elo": 1207, + "win_rate": 57, + "rank": 47 + } + ] + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "liquid/lfm-2.5-1.2b-instruct:free", - "canonical_slug": "liquid/lfm-2.5-1.2b-instruct-20260120", - "hugging_face_id": "LiquidAI/LFM2.5-1.2B-Instruct", - "name": "LiquidAI: LFM2.5-1.2B-Instruct (free)", - "created": 1768927521, - "description": "LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.", - "context_length": 32768, + "id": "google/gemini-3-pro-image", + "canonical_slug": "google/gemini-3-pro-image-20260528", + "hugging_face_id": null, + "name": "Google: Nano Banana Pro (Gemini 3 Pro Image)", + "created": 1781754054, + "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", + "context_length": 131072, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000002", + "completion": "0.000012", + "image": "0.000002", + "image_output": "0.00012", + "audio": "0.000002", + "input_audio_cache": "0.0000002", + "web_search": "0.014", + "internal_reasoning": "0.000012", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000000375" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, + "context_length": 65536, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "response_format", "seed", "stop", "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/liquid/lfm-2.5-1.2b-instruct-20260120/endpoints" + "details": "/api/v1/models/google/gemini-3-pro-image-20260528/endpoints" + }, + "reasoning": { + "mandatory": true } }, { - "id": "liquid/lfm-2.5-1.2b-thinking:free", - "canonical_slug": "liquid/lfm-2.5-1.2b-thinking-20260120", - "hugging_face_id": "LiquidAI/LFM2.5-1.2B-Thinking", - "name": "LiquidAI: LFM2.5-1.2B-Thinking (free)", - "created": 1768927527, - "description": "LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...", - "context_length": 32768, + "id": "google/gemini-3-pro-image-preview", + "canonical_slug": "google/gemini-3-pro-image-preview-20251120", + "hugging_face_id": "", + "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", + "created": 1763653797, + "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", + "context_length": 65536, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000002", + "completion": "0.000012", + "image": "0.000002", + "image_output": "0.00012", + "audio": "0.000002", + "input_audio_cache": "0.0000002", + "web_search": "0.014", + "internal_reasoning": "0.000012", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000000375" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, + "context_length": 65536, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", + "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", "top_p" ], "default_parameters": { @@ -8324,143 +9014,217 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/liquid/lfm-2.5-1.2b-thinking-20260120/endpoints" + "details": "/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "graphicdesign", + "elo": 1275, + "win_rate": 65.8, + "rank": 3 + }, + { + "arena": "models", + "category": "image", + "elo": 1263, + "win_rate": 62.1, + "rank": 3 + }, + { + "arena": "models", + "category": "logo", + "elo": 1253, + "win_rate": 61, + "rank": 4 + }, + { + "arena": "models", + "category": "imageediting", + "elo": 1270, + "win_rate": 65.4, + "rank": 2 + } + ] }, "reasoning": { "mandatory": true } }, { - "id": "mancer/weaver", - "canonical_slug": "mancer/weaver", + "id": "google/gemini-3.1-flash-image", + "canonical_slug": "google/gemini-3.1-flash-image-20260528", "hugging_face_id": null, - "name": "Mancer: Weaver (alpha)", - "created": 1690934400, - "description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.", - "context_length": 8000, + "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", + "created": 1781754065, + "description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...", + "context_length": 131072, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama2", - "instruct_type": "alpaca" + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.00000075", - "completion": "0.000001" + "prompt": "0.0000005", + "completion": "0.000003", + "image_output": "0.00006", + "web_search": "0.014" }, "top_provider": { - "context_length": 8000, - "max_completion_tokens": 2000, + "context_length": 131072, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", "temperature", - "top_a", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mancer/weaver/endpoints" + "details": "/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3-8b-instruct", - "canonical_slug": "meta-llama/llama-3-8b-instruct", - "hugging_face_id": "meta-llama/Meta-Llama-3-8B-Instruct", - "name": "Meta: Llama 3 8B Instruct", - "created": 1713398400, - "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...", - "context_length": 8192, + "id": "google/gemini-3.1-flash-image-preview", + "canonical_slug": "google/gemini-3.1-flash-image-preview-20260226", + "hugging_face_id": "", + "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", + "created": 1772119558, + "description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...", + "context_length": 65536, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.00000014", - "completion": "0.00000014" + "prompt": "0.0000005", + "completion": "0.000003", + "image_output": "0.00006", + "web_search": "0.014" }, "top_provider": { - "context_length": 8192, - "max_completion_tokens": null, + "context_length": 65536, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", - "stop", + "seed", "structured_outputs", "temperature", - "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3-8b-instruct/endpoints" + "details": "/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "graphicdesign", + "elo": 1285, + "win_rate": 66.3, + "rank": 2 + }, + { + "arena": "models", + "category": "image", + "elo": 1296, + "win_rate": 65.1, + "rank": 2 + }, + { + "arena": "models", + "category": "logo", + "elo": 1275, + "win_rate": 62.9, + "rank": 2 + } + ] + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3.1-70b-instruct", - "canonical_slug": "meta-llama/llama-3.1-70b-instruct", - "hugging_face_id": "meta-llama/Meta-Llama-3.1-70B-Instruct", - "name": "Meta: Llama 3.1 70B Instruct", - "created": 1721692800, - "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...", - "context_length": 131072, + "id": "google/gemini-3.1-flash-lite", + "canonical_slug": "google/gemini-3.1-flash-lite-20260507", + "hugging_face_id": null, + "name": "Google: Gemini 3.1 Flash Lite", + "created": 1778168828, + "description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000004" + "prompt": "0.00000025", + "completion": "0.0000015", + "image": "0.00000025", + "audio": "0.0000005", + "input_audio_cache": "0.00000005", + "web_search": "0.014", + "internal_reasoning": "0.0000015", + "input_cache_read": "0.000000025", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", "stop", @@ -8468,265 +9232,3668 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints" + "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3.1-8b-instruct", - "canonical_slug": "meta-llama/llama-3.1-8b-instruct", - "hugging_face_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", - "name": "Meta: Llama 3.1 8B Instruct", - "created": 1721692800, - "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", - "context_length": 131072, + "id": "google/gemini-3.1-flash-lite-image", + "canonical_slug": "google/gemini-3.1-flash-lite-image-20260630", + "hugging_face_id": null, + "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", + "created": 1782837225, + "description": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...", + "context_length": 65536, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "modality": "text+image->text+image", + "input_modalities": ["image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.00000002", - "completion": "0.00000003" + "prompt": "0.00000025", + "completion": "0.0000015", + "image_output": "0.00003", + "web_search": "0.014" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 65536, + "max_completion_tokens": 66000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", - "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2025-01-01", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints" + "details": "/api/v1/models/google/gemini-3.1-flash-lite-image-20260630/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 7.6, - "coding_index": 5.4, - "agentic_index": 0.5 - } + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3.2-11b-vision-instruct", - "canonical_slug": "meta-llama/llama-3.2-11b-vision-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-11B-Vision-Instruct", - "name": "Meta: Llama 3.2 11B Vision Instruct", - "created": 1727222400, - "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...", - "context_length": 131072, + "id": "google/gemini-3.1-flash-lite-preview", + "canonical_slug": "google/gemini-3.1-flash-lite-preview-20260303", + "hugging_face_id": "", + "name": "Google: Gemini 3.1 Flash Lite Preview", + "created": 1772512673, + "description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...", + "context_length": 1048576, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.000000345", - "completion": "0.000000345" + "prompt": "0.00000025", + "completion": "0.0000015", + "image": "0.00000025", + "audio": "0.0000005", + "input_audio_cache": "0.00000005", + "web_search": "0.014", + "internal_reasoning": "0.0000015", + "input_cache_read": "0.000000025", + "input_cache_write": "0.0000000833333333333333" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 16384, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", + "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-11b-vision-instruct/endpoints" - } - }, - { - "id": "meta-llama/llama-3.2-1b-instruct", - "canonical_slug": "meta-llama/llama-3.2-1b-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-1B-Instruct", - "name": "Meta: Llama 3.2 1B Instruct", - "created": 1727222400, - "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" - }, - "pricing": { - "prompt": "0.000000027", - "completion": "0.000000201" + "details": "/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints" }, - "top_provider": { - "context_length": 60000, - "max_completion_tokens": 60000, - "is_moderated": false + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1101, + "win_rate": 38.7, + "rank": 86 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1199, + "win_rate": 50.6, + "rank": 20 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1091, + "win_rate": 36.4, + "rank": 90 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1068, + "win_rate": 33.3, + "rank": 94 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1067, + "win_rate": 33.7, + "rank": 96 + }, + { + "arena": "models", + "category": "svg", + "elo": 1086, + "win_rate": 42.4, + "rank": 57 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1103, + "win_rate": 38.2, + "rank": 84 + }, + { + "arena": "models", + "category": "website", + "elo": 1094, + "win_rate": 36.5, + "rank": 94 + } + ], + "artificial_analysis": { + "intelligence_index": 25.6, + "coding_index": 34.7, + "agentic_index": 6.5 + } }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "seed", - "stop", - "temperature", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-12-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints" + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3.2-3b-instruct", - "canonical_slug": "meta-llama/llama-3.2-3b-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-3B-Instruct", - "name": "Meta: Llama 3.2 3B Instruct", - "created": 1727222400, - "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", - "context_length": 131072, + "id": "google/gemini-3.1-flash-lite:batch", + "canonical_slug": "google/gemini-3.1-flash-lite-20260507", + "hugging_face_id": null, + "name": "Google: Gemini 3.1 Flash Lite (batch)", + "created": 1778168828, + "description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000033" + "prompt": "0.000000125", + "completion": "0.00000075", + "image": "0.000000125", + "audio": "0.00000025", + "input_audio_cache": "0.000000025", + "web_search": "0.014", + "internal_reasoning": "0.00000075", + "input_cache_read": "0.0000000125" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "reasoning_effort", + "response_format", "seed", "stop", "structured_outputs", "temperature", - "top_k", - "top_logprobs", + "tool_choice", + "tools", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" + "details": "/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "minimal" } }, { - "id": "meta-llama/llama-3.2-3b-instruct:free", - "canonical_slug": "meta-llama/llama-3.2-3b-instruct", - "hugging_face_id": "meta-llama/Llama-3.2-3B-Instruct", - "name": "Meta: Llama 3.2 3B Instruct (free)", - "created": 1727222400, - "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", - "context_length": 131072, + "id": "google/gemini-3.1-pro-preview", + "canonical_slug": "google/gemini-3.1-pro-preview-20260219", + "hugging_face_id": "", + "name": "Google: Gemini 3.1 Pro Preview", + "created": 1771509627, + "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file+audio+video->text", + "input_modalities": ["audio", "file", "image", "text", "video"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Gemini", + "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000002", + "completion": "0.000012", + "image": "0.000002", + "audio": "0.000002", + "input_audio_cache": "0.0000002", + "web_search": "0.014", + "internal_reasoning": "0.000012", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000018", + "audio": "0.000004", + "input_audio_cache": "0.0000004", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 1048576, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "seed", "stop", + "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" - } - }, - { - "id": "meta-llama/llama-3.3-70b-instruct", - "canonical_slug": "meta-llama/llama-3.3-70b-instruct", + "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1120, + "win_rate": 44, + "rank": 17 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1226, + "win_rate": 55.8, + "rank": 5 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1112, + "win_rate": 33.8, + "rank": 8 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1219, + "win_rate": 54.4, + "rank": 5 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1107, + "win_rate": 33.9, + "rank": 8 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1084, + "win_rate": 41.4, + "rank": 32 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1105, + "win_rate": 42.5, + "rank": 26 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1236, + "win_rate": 60, + "rank": 6 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1195, + "win_rate": 50.9, + "rank": 9 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1145, + "win_rate": 44.5, + "rank": 29 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1110, + "win_rate": 34.1, + "rank": 8 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1109, + "win_rate": 31.9, + "rank": 18 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1172, + "win_rate": 46, + "rank": 23 + }, + { + "arena": "models", + "category": "3d", + "elo": 1287, + "win_rate": 59.3, + "rank": 25 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1304, + "win_rate": 63.6, + "rank": 4 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1264, + "win_rate": 64.4, + "rank": 28 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1262, + "win_rate": 61.9, + "rank": 24 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1240, + "win_rate": 53.7, + "rank": 38 + }, + { + "arena": "models", + "category": "svg", + "elo": 1321, + "win_rate": 68, + "rank": 4 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1307, + "win_rate": 69.3, + "rank": 14 + }, + { + "arena": "models", + "category": "website", + "elo": 1265, + "win_rate": 64.4, + "rank": 27 + } + ], + "artificial_analysis": { + "intelligence_index": 47.7, + "coding_index": 68.8, + "agentic_index": 23 + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.1-pro-preview-customtools", + "canonical_slug": "google/gemini-3.1-pro-preview-customtools-20260219", + "hugging_face_id": null, + "name": "Google: Gemini 3.1 Pro Preview Custom Tools", + "created": 1772045923, + "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "audio", "image", "video", "file"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000012", + "image": "0.000002", + "audio": "0.000002", + "input_audio_cache": "0.0000002", + "web_search": "0.014", + "internal_reasoning": "0.000012", + "input_cache_read": "0.0000002", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000018", + "audio": "0.000004", + "input_audio_cache": "0.0000004", + "input_cache_read": "0.0000004" + } + ] + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.1-pro-preview:batch", + "canonical_slug": "google/gemini-3.1-pro-preview-20260219", + "hugging_face_id": "", + "name": "Google: Gemini 3.1 Pro Preview (batch)", + "created": 1771509627, + "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["audio", "file", "image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000006", + "image": "0.000001", + "audio": "0.000001", + "web_search": "0.014", + "internal_reasoning": "0.000006", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000002", + "completion": "0.000009", + "audio": "0.000002" + } + ] + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1120, + "win_rate": 44, + "rank": 17 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1226, + "win_rate": 55.8, + "rank": 5 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1112, + "win_rate": 33.8, + "rank": 8 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1219, + "win_rate": 54.4, + "rank": 5 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1107, + "win_rate": 33.9, + "rank": 8 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1084, + "win_rate": 41.4, + "rank": 32 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1105, + "win_rate": 42.5, + "rank": 26 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1236, + "win_rate": 60, + "rank": 6 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1195, + "win_rate": 50.9, + "rank": 9 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1145, + "win_rate": 44.5, + "rank": 29 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1110, + "win_rate": 34.1, + "rank": 8 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1109, + "win_rate": 31.9, + "rank": 18 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1172, + "win_rate": 46, + "rank": 23 + }, + { + "arena": "models", + "category": "3d", + "elo": 1287, + "win_rate": 59.3, + "rank": 25 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1304, + "win_rate": 63.6, + "rank": 4 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1264, + "win_rate": 64.4, + "rank": 28 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1262, + "win_rate": 61.9, + "rank": 24 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1240, + "win_rate": 53.7, + "rank": 38 + }, + { + "arena": "models", + "category": "svg", + "elo": 1321, + "win_rate": 68, + "rank": 4 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1307, + "win_rate": 69.3, + "rank": 14 + }, + { + "arena": "models", + "category": "website", + "elo": 1265, + "win_rate": 64.4, + "rank": 27 + } + ], + "artificial_analysis": { + "intelligence_index": 47.7, + "coding_index": 68.8, + "agentic_index": 23 + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.5-flash", + "canonical_slug": "google/gemini-3.5-flash-20260519", + "hugging_face_id": null, + "name": "Google: Gemini 3.5 Flash", + "created": 1779193800, + "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000015", + "completion": "0.000009", + "image": "0.0000015", + "audio": "0.000003", + "input_audio_cache": "0.0000003", + "web_search": "0.014", + "internal_reasoning": "0.000009", + "input_cache_read": "0.00000015", + "input_cache_write": "0.0000000833333333333333" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2025-01-01", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1183, + "win_rate": 54, + "rank": 11 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1162, + "win_rate": 45.8, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1244, + "win_rate": 57.5, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1162, + "win_rate": 45.7, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1242, + "win_rate": 57.8, + "rank": 3 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1218, + "win_rate": 55.6, + "rank": 13 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1232, + "win_rate": 55.9, + "rank": 14 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1137, + "win_rate": 42.9, + "rank": 21 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1163, + "win_rate": 45.4, + "rank": 16 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1223, + "win_rate": 53.9, + "rank": 11 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1244, + "win_rate": 57.7, + "rank": 3 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1247, + "win_rate": 57.4, + "rank": 7 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1239, + "win_rate": 52.7, + "rank": 15 + }, + { + "arena": "models", + "category": "3d", + "elo": 1295, + "win_rate": 57.8, + "rank": 22 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1290, + "win_rate": 59.5, + "rank": 7 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1282, + "win_rate": 55.7, + "rank": 20 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1257, + "win_rate": 54.5, + "rank": 28 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1307, + "win_rate": 55.4, + "rank": 15 + }, + { + "arena": "models", + "category": "svg", + "elo": 1284, + "win_rate": 60.2, + "rank": 5 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1304, + "win_rate": 56, + "rank": 15 + }, + { + "arena": "models", + "category": "website", + "elo": 1272, + "win_rate": 55.1, + "rank": 24 + } + ], + "artificial_analysis": { + "intelligence_index": 52, + "coding_index": 70.1, + "agentic_index": 39.7 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.5-flash-lite", + "canonical_slug": "google/gemini-3.5-flash-lite-20260721", + "hugging_face_id": null, + "name": "Google: Gemini 3.5 Flash Lite", + "created": 1784646726, + "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000025", + "image": "0.0000003", + "audio": "0.0000003", + "input_audio_cache": "0.00000003", + "web_search": "0.014", + "internal_reasoning": "0.0000025", + "input_cache_read": "0.00000003", + "input_cache_write": "0.0000000833333333333333" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 37.4, + "coding_index": 49.3, + "agentic_index": 27.2 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "minimal" + } + }, + { + "id": "google/gemini-3.5-flash-lite:batch", + "canonical_slug": "google/gemini-3.5-flash-lite-20260721", + "hugging_face_id": null, + "name": "Google: Gemini 3.5 Flash Lite (batch)", + "created": 1784646726, + "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.00000125", + "image": "0.00000015", + "audio": "0.00000015", + "input_audio_cache": "0.000000015", + "web_search": "0.014", + "internal_reasoning": "0.00000125", + "input_cache_read": "0.000000015" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 37.4, + "coding_index": 49.3, + "agentic_index": 27.2 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "minimal" + } + }, + { + "id": "google/gemini-3.5-flash:batch", + "canonical_slug": "google/gemini-3.5-flash-20260519", + "hugging_face_id": null, + "name": "Google: Gemini 3.5 Flash (batch)", + "created": 1779193800, + "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000075", + "completion": "0.0000045", + "image": "0.00000075", + "audio": "0.0000015", + "input_audio_cache": "0.00000015", + "web_search": "0.014", + "internal_reasoning": "0.0000045", + "input_cache_read": "0.000000075" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2025-01-01", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1183, + "win_rate": 54, + "rank": 11 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1162, + "win_rate": 45.8, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1244, + "win_rate": 57.5, + "rank": 4 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1162, + "win_rate": 45.7, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1242, + "win_rate": 57.8, + "rank": 3 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1218, + "win_rate": 55.6, + "rank": 13 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1232, + "win_rate": 55.9, + "rank": 14 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1137, + "win_rate": 42.9, + "rank": 21 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1163, + "win_rate": 45.4, + "rank": 16 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1223, + "win_rate": 53.9, + "rank": 11 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1244, + "win_rate": 57.7, + "rank": 3 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1247, + "win_rate": 57.4, + "rank": 7 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1239, + "win_rate": 52.7, + "rank": 15 + }, + { + "arena": "models", + "category": "3d", + "elo": 1295, + "win_rate": 57.8, + "rank": 22 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1290, + "win_rate": 59.5, + "rank": 7 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1282, + "win_rate": 55.7, + "rank": 20 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1257, + "win_rate": 54.5, + "rank": 28 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1307, + "win_rate": 55.4, + "rank": 15 + }, + { + "arena": "models", + "category": "svg", + "elo": 1284, + "win_rate": 60.2, + "rank": 5 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1304, + "win_rate": 56, + "rank": 15 + }, + { + "arena": "models", + "category": "website", + "elo": 1272, + "win_rate": 55.1, + "rank": 24 + } + ], + "artificial_analysis": { + "intelligence_index": 52, + "coding_index": 70.1, + "agentic_index": 39.7 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.6-flash", + "canonical_slug": "google/gemini-3.6-flash-20260721", + "hugging_face_id": null, + "name": "Google: Gemini 3.6 Flash", + "created": 1784646733, + "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000075", + "completion": "0.00000375", + "image": "0.00000075", + "audio": "0.00000075", + "input_audio_cache": "0.000000075", + "web_search": "0.014", + "internal_reasoning": "0.00000375", + "input_cache_read": "0.000000075", + "input_cache_write": "0.0000000416666666666667" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1200, + "win_rate": 53.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1227, + "win_rate": 54.1, + "rank": 11 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1207, + "win_rate": 46.9, + "rank": 18 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1164, + "win_rate": 40.9, + "rank": 15 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1247, + "win_rate": 53.7, + "rank": 8 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1145, + "win_rate": 38.5, + "rank": 17 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1246, + "win_rate": 50, + "rank": 13 + }, + { + "arena": "models", + "category": "3d", + "elo": 1326, + "win_rate": 54.2, + "rank": 10 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1309, + "win_rate": 55.2, + "rank": 10 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1317, + "win_rate": 53.6, + "rank": 8 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1297, + "win_rate": 53.8, + "rank": 20 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1333, + "win_rate": 54.9, + "rank": 8 + }, + { + "arena": "models", + "category": "website", + "elo": 1314, + "win_rate": 57.4, + "rank": 7 + } + ], + "artificial_analysis": { + "intelligence_index": 51.6, + "coding_index": 69.2, + "agentic_index": 40.5 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.6-flash:batch", + "canonical_slug": "google/gemini-3.6-flash-20260721", + "hugging_face_id": null, + "name": "Google: Gemini 3.6 Flash (batch)", + "created": 1784646733, + "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000375", + "completion": "0.000001875", + "image": "0.000000375", + "audio": "0.000000375", + "input_audio_cache": "0.0000000375", + "web_search": "0.014", + "internal_reasoning": "0.000001875", + "input_cache_read": "0.0000000375", + "input_cache_write": "0.0000000416666666666667" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1200, + "win_rate": 53.9, + "rank": 6 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1227, + "win_rate": 54.1, + "rank": 11 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1207, + "win_rate": 46.9, + "rank": 18 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1164, + "win_rate": 40.9, + "rank": 15 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1247, + "win_rate": 53.7, + "rank": 8 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1145, + "win_rate": 38.5, + "rank": 17 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1246, + "win_rate": 50, + "rank": 13 + }, + { + "arena": "models", + "category": "3d", + "elo": 1326, + "win_rate": 54.2, + "rank": 10 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1309, + "win_rate": 55.2, + "rank": 10 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1317, + "win_rate": 53.6, + "rank": 8 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1297, + "win_rate": 53.8, + "rank": 20 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1333, + "win_rate": 54.9, + "rank": 8 + }, + { + "arena": "models", + "category": "website", + "elo": 1314, + "win_rate": 57.4, + "rank": 7 + } + ], + "artificial_analysis": { + "intelligence_index": 51.6, + "coding_index": 69.2, + "agentic_index": 40.5 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.7-flash", + "canonical_slug": "google/gemini-3.7-flash-20260813", + "hugging_face_id": null, + "name": "Google: Gemini 3.7 Flash", + "created": 1786640581, + "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000375", + "completion": "0.000001875", + "image": "0.000000375", + "audio": "0.000000375", + "input_audio_cache": "0.0000000375", + "web_search": "0.014", + "internal_reasoning": "0.000001875", + "input_cache_read": "0.0000000375", + "input_cache_write": "0.0000000208333333333333" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1253, + "win_rate": 56.8, + "rank": 6 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1309, + "win_rate": 52.6, + "rank": 13 + }, + { + "arena": "models", + "category": "website", + "elo": 1347, + "win_rate": 59.6, + "rank": 2 + } + ], + "artificial_analysis": { + "intelligence_index": 56, + "coding_index": 76.1, + "agentic_index": 45.1 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemini-3.7-flash:batch", + "canonical_slug": "google/gemini-3.7-flash-20260813", + "hugging_face_id": null, + "name": "Google: Gemini 3.7 Flash (batch)", + "created": 1786640581, + "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001875", + "completion": "0.0000009375", + "image": "0.0000001875", + "audio": "0.0000001875", + "input_audio_cache": "0.00000001875", + "web_search": "0.014", + "internal_reasoning": "0.0000009375", + "input_cache_read": "0.00000001875", + "input_cache_write": "0.0000000208333333333333" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1253, + "win_rate": 56.8, + "rank": 6 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1309, + "win_rate": 52.6, + "rank": 13 + }, + { + "arena": "models", + "category": "website", + "elo": 1347, + "win_rate": 59.6, + "rank": 2 + } + ], + "artificial_analysis": { + "intelligence_index": 56, + "coding_index": 76.1, + "agentic_index": 45.1 + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "google/gemma-2-27b-it", + "canonical_slug": "google/gemma-2-27b-it", + "hugging_face_id": "google/gemma-2-27b-it", + "name": "Google: Gemma 2 27B", + "created": 1720828800, + "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...", + "context_length": 8192, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "pricing": { + "prompt": "0.00000065", + "completion": "0.00000065" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-2-27b-it/endpoints" + } + }, + { + "id": "google/gemma-3-12b-it", + "canonical_slug": "google/gemma-3-12b-it", + "hugging_face_id": "google/gemma-3-12b-it", + "name": "Google: Gemma 3 12B", + "created": 1741902625, + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "context_length": 131072, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000015" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-3-12b-it/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 5.5, + "coding_index": 5.8, + "agentic_index": 0.3 + } + } + }, + { + "id": "google/gemma-3-27b-it", + "canonical_slug": "google/gemma-3-27b-it", + "hugging_face_id": "google/gemma-3-27b-it", + "name": "Google: Gemma 3 27B", + "created": 1741756359, + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "pricing": { + "prompt": "0.00000008", + "completion": "0.00000045", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-3-27b-it/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 7.4, + "coding_index": 10.1, + "agentic_index": 0.3 + } + } + }, + { + "id": "google/gemma-3-4b-it", + "canonical_slug": "google/gemma-3-4b-it", + "hugging_face_id": "google/gemma-3-4b-it", + "name": "Google: Gemma 3 4B", + "created": 1741905510, + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "context_length": 131072, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.0000001" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-3-4b-it/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 2.7, + "agentic_index": null + } + } + }, + { + "id": "google/gemma-3n-e4b-it", + "canonical_slug": "google/gemma-3n-e4b-it", + "hugging_face_id": "google/gemma-3n-E4B-it", + "name": "Google: Gemma 3n 4B", + "created": 1747776824, + "description": "Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...", + "context_length": 32768, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000006", + "completion": "0.00000012" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-3n-e4b-it/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 3.2, + "agentic_index": null + } + } + }, + { + "id": "google/gemma-4-26b-a4b-it", + "canonical_slug": "google/gemma-4-26b-a4b-it-20260403", + "hugging_face_id": "google/gemma-4-26B-A4B-it", + "name": "Google: Gemma 4 26B A4B ", + "created": 1775227989, + "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemma", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000012", + "completion": "0.0000004", + "input_cache_read": "0.00000005" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 64 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 26.1, + "coding_index": 39.3, + "agentic_index": 11 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, + { + "id": "google/gemma-4-26b-a4b-it:free", + "canonical_slug": "google/gemma-4-26b-a4b-it-20260403", + "hugging_face_id": "google/gemma-4-26B-A4B-it", + "name": "Google: Gemma 4 26B A4B (free)", + "created": 1775227989, + "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemma", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 64 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 26.1, + "coding_index": 39.3, + "agentic_index": 11 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, + { + "id": "google/gemma-4-31b-it", + "canonical_slug": "google/gemma-4-31b-it-20260402", + "hugging_face_id": "google/gemma-4-31B-it", + "name": "Google: Gemma 4 31B", + "created": 1775148486, + "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemma", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.00000034", + "input_cache_read": "0.0000001" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 64, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 29.7, + "coding_index": 43.4, + "agentic_index": 14.4 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, + { + "id": "google/gemma-4-31b-it:free", + "canonical_slug": "google/gemma-4-31b-it-20260402", + "hugging_face_id": "google/gemma-4-31B-it", + "name": "Google: Gemma 4 31B (free)", + "created": 1775148486, + "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], + "output_modalities": ["text"], + "tokenizer": "Gemma", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 64, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 29.7, + "coding_index": 43.4, + "agentic_index": 14.4 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false + } + }, + { + "id": "google/lyria-3-clip-preview", + "canonical_slug": "google/lyria-3-clip-preview-20260330", + "hugging_face_id": null, + "name": "Google: Lyria 3 Clip Preview", + "created": 1774907255, + "description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text+audio", + "input_modalities": ["text", "image"], + "output_modalities": ["text", "audio"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "temperature", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints" + } + }, + { + "id": "google/lyria-3-pro-preview", + "canonical_slug": "google/lyria-3-pro-preview-20260330", + "hugging_face_id": null, + "name": "Google: Lyria 3 Pro Preview", + "created": 1774907286, + "description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text+audio", + "input_modalities": ["text", "image"], + "output_modalities": ["text", "audio"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "temperature", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints" + } + }, + { + "id": "gryphe/mythomax-l2-13b", + "canonical_slug": "gryphe/mythomax-l2-13b", + "hugging_face_id": "Gryphe/MythoMax-L2-13b", + "name": "MythoMax 13B", + "created": 1688256000, + "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge", + "context_length": 8192, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama2", + "instruct_type": "alpaca" + }, + "pricing": { + "prompt": "0.00000006", + "completion": "0.00000006" + }, + "top_provider": { + "context_length": 4096, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/gryphe/mythomax-l2-13b/endpoints" + } + }, + { + "id": "ibm-granite/granite-4.0-h-micro", + "canonical_slug": "ibm-granite/granite-4.0-h-micro", + "hugging_face_id": "ibm-granite/granite-4.0-h-micro", + "name": "IBM: Granite 4.0 Micro", + "created": 1760927695, + "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...", + "context_length": 131000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000017", + "completion": "0.000000112" + }, + "top_provider": { + "context_length": 131000, + "max_completion_tokens": 131000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints" + } + }, + { + "id": "ibm-granite/granite-4.1-8b", + "canonical_slug": "ibm-granite/granite-4.1-8b-20260429", + "hugging_face_id": "ibm-granite/granite-4.1-8b", + "name": "IBM: Granite 4.1 8B", + "created": 1777577071, + "description": "Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.0000001", + "input_cache_read": "0.00000005" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/ibm-granite/granite-4.1-8b-20260429/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 9.5, + "agentic_index": null + } + } + }, + { + "id": "inception/mercury-2", + "canonical_slug": "inception/mercury-2-20260304", + "hugging_face_id": null, + "name": "Inception: Mercury 2", + "created": 1772636275, + "description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000025", + "completion": "0.00000075", + "input_cache_read": "0.000000025" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 50000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": 0.75, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/inception/mercury-2-20260304/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1036, + "win_rate": 23.6, + "rank": 97 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1045, + "win_rate": 28, + "rank": 55 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1018, + "win_rate": 20.8, + "rank": 106 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1016, + "win_rate": 21.9, + "rank": 100 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1008, + "win_rate": 19.7, + "rank": 107 + }, + { + "arena": "models", + "category": "svg", + "elo": 1009, + "win_rate": 24.4, + "rank": 75 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 994, + "win_rate": 18.4, + "rank": 99 + }, + { + "arena": "models", + "category": "website", + "elo": 1014, + "win_rate": 20.3, + "rank": 110 + } + ], + "artificial_analysis": { + "intelligence_index": 21.9, + "coding_index": 31.1, + "agentic_index": 9.5 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "inclusionai/ling-2.6-1t", + "canonical_slug": "inclusionai/ling-2.6-1t-20260423", + "hugging_face_id": null, + "name": "inclusionAI: Ling-2.6-1T", + "created": 1776948238, + "description": "Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000075", + "completion": "0.000000625", + "input_cache_read": "0.000000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/inclusionai/ling-2.6-1t-20260423/endpoints" + } + }, + { + "id": "inclusionai/ling-2.6-flash", + "canonical_slug": "inclusionai/ling-2.6-flash-20260421", + "hugging_face_id": "", + "name": "inclusionAI: Ling-2.6-flash", + "created": 1776795886, + "description": "Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000001", + "completion": "0.00000003", + "input_cache_read": "0.000000002" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/inclusionai/ling-2.6-flash-20260421/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 14.2, + "coding_index": 25.3, + "agentic_index": 2.3 + } + } + }, + { + "id": "inclusionai/ling-3.0-flash", + "canonical_slug": "inclusionai/ling-3.0-flash-20260723", + "hugging_face_id": "inclusionAI/Ling-3.0-flash", + "name": "Ling-3.0-flash", + "created": 1784818580, + "description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000021", + "completion": "0.000000063", + "input_cache_read": "0.0000000042" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 37.8, + "coding_index": 50.6, + "agentic_index": 29.3 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true + } + }, + { + "id": "inclusionai/ring-2.6-1t", + "canonical_slug": "inclusionai/ring-2.6-1t-20260508", + "hugging_face_id": null, + "name": "inclusionAI: Ring-2.6-1T", + "created": 1778247440, + "description": "Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000075", + "completion": "0.000000625", + "input_cache_read": "0.000000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/inclusionai/ring-2.6-1t-20260508/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 42.8, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high"], + "default_effort": "high" + } + }, + { + "id": "kwaipilot/kat-coder-air-v2.5", + "canonical_slug": "kwaipilot/kat-coder-air-v2.5-20260710", + "hugging_face_id": null, + "name": "Kwaipilot: KAT-Coder-Air V2.5", + "created": 1783714590, + "description": "KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...", + "context_length": 256000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 80000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/kwaipilot/kat-coder-air-v2.5-20260710/endpoints" + } + }, + { + "id": "kwaipilot/kat-coder-pro-v2", + "canonical_slug": "kwaipilot/kat-coder-pro-v2-20260327", + "hugging_face_id": "", + "name": "Kwaipilot: KAT-Coder-Pro V2", + "created": 1774649310, + "description": "KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000006" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 80000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/kwaipilot/kat-coder-pro-v2-20260327/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 59.5, + "agentic_index": null + } + } + }, + { + "id": "kwaipilot/kat-coder-pro-v2.5", + "canonical_slug": "kwaipilot/kat-coder-pro-v2.5-20260710", + "hugging_face_id": null, + "name": "Kwaipilot: KAT-Coder-Pro V2.5", + "created": 1783714589, + "description": "KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...", + "context_length": 256000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000074", + "completion": "0.00000296", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 80000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/kwaipilot/kat-coder-pro-v2.5-20260710/endpoints" + } + }, + { + "id": "liquid/lfm-2.5-2.6b:free", + "canonical_slug": "liquid/lfm-2.5-2.6b-20260811", + "hugging_face_id": "LiquidAI/LFM2.5-2.6B", + "name": "LiquidAI: LFM2.5-2.6B (free)", + "created": 1786470519, + "description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0", + "completion": "0" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_completion_tokens", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 0.1, + "top_k": 50, + "repetition_penalty": 1.1 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/liquid/lfm-2.5-2.6b-20260811/endpoints" + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "mancer/weaver", + "canonical_slug": "mancer/weaver", + "hugging_face_id": null, + "name": "Mancer: Weaver (alpha)", + "created": 1690934400, + "description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.", + "context_length": 8000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama2", + "instruct_type": "alpaca" + }, + "pricing": { + "prompt": "0.0000005", + "completion": "0.00000075" + }, + "top_provider": { + "context_length": 8000, + "max_completion_tokens": 6000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mancer/weaver/endpoints" + } + }, + { + "id": "meituan/longcat-2.0", + "canonical_slug": "meituan/longcat-2.0-20260720", + "hugging_face_id": "meituan-longcat/LongCat-2.0", + "name": "Meituan: LongCat 2.0", + "created": 1784554658, + "description": "LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...", + "context_length": 1048756, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.000000006" + }, + "top_provider": { + "context_length": 1048756, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meituan/longcat-2.0-20260720/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true + } + }, + { + "id": "meta-llama/llama-3.1-70b-instruct", + "canonical_slug": "meta-llama/llama-3.1-70b-instruct", + "hugging_face_id": "meta-llama/Meta-Llama-3.1-70B-Instruct", + "name": "Meta: Llama 3.1 70B Instruct", + "created": 1721692800, + "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.0000004" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints" + } + }, + { + "id": "meta-llama/llama-3.1-8b-instruct", + "canonical_slug": "meta-llama/llama-3.1-8b-instruct", + "hugging_face_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", + "name": "Meta: Llama 3.1 8B Instruct", + "created": 1721692800, + "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000008", + "input_cache_read": "0.000000025" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 5.4, + "agentic_index": null + } + } + }, + { + "id": "meta-llama/llama-3.2-1b-instruct", + "canonical_slug": "meta-llama/llama-3.2-1b-instruct", + "hugging_face_id": "meta-llama/Llama-3.2-1B-Instruct", + "name": "Meta: Llama 3.2 1B Instruct", + "created": 1727222400, + "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", + "context_length": 60000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.000000027", + "completion": "0.000000201" + }, + "top_provider": { + "context_length": 60000, + "max_completion_tokens": 60000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints" + } + }, + { + "id": "meta-llama/llama-3.2-3b-instruct", + "canonical_slug": "meta-llama/llama-3.2-3b-instruct", + "hugging_face_id": "meta-llama/Llama-3.2-3B-Instruct", + "name": "Meta: Llama 3.2 3B Instruct", + "created": 1727222400, + "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000033" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints" + } + }, + { + "id": "meta-llama/llama-3.3-70b-instruct", + "canonical_slug": "meta-llama/llama-3.3-70b-instruct", "hugging_face_id": "meta-llama/Llama-3.3-70B-Instruct", "name": "Meta: Llama 3.3 70B Instruct", "created": 1733506137, @@ -8736,15 +12903,2881 @@ "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.00000032" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 11.9, + "agentic_index": null + } + } + }, + { + "id": "meta-llama/llama-4-maverick", + "canonical_slug": "meta-llama/llama-4-maverick-17b-128e-instruct", + "hugging_face_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", + "name": "Meta: Llama 4 Maverick", + "created": 1743881822, + "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Llama4", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000008" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 954, + "win_rate": 40.2, + "rank": 104 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 899, + "win_rate": 35.8, + "rank": 116 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 903, + "win_rate": 38.4, + "rank": 114 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 876, + "win_rate": 33.7, + "rank": 118 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 928, + "win_rate": 40.8, + "rank": 109 + }, + { + "arena": "models", + "category": "website", + "elo": 882, + "win_rate": 34.4, + "rank": 121 + } + ], + "artificial_analysis": { + "intelligence_index": 14.5, + "coding_index": 16.3, + "agentic_index": 1.2 + } + } + }, + { + "id": "meta-llama/llama-4-scout", + "canonical_slug": "meta-llama/llama-4-scout-17b-16e-instruct", + "hugging_face_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", + "name": "Meta: Llama 4 Scout", + "created": 1743881519, + "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...", + "context_length": 1310720, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Llama4", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000003" + }, + "top_provider": { + "context_length": 327680, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 809, + "win_rate": 26.6, + "rank": 119 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 916, + "win_rate": 39.3, + "rank": 112 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 811, + "win_rate": 27.4, + "rank": 120 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 796, + "win_rate": 25.5, + "rank": 114 + }, + { + "arena": "models", + "category": "website", + "elo": 761, + "win_rate": 22.7, + "rank": 127 + } + ], + "artificial_analysis": { + "intelligence_index": 10.3, + "coding_index": 8.2, + "agentic_index": 1.1 + } + } + }, + { + "id": "meta-llama/llama-guard-4-12b", + "canonical_slug": "meta-llama/llama-guard-4-12b", + "hugging_face_id": "meta-llama/Llama-Guard-4-12B", + "name": "Meta: Llama Guard 4 12B", + "created": 1745975193, + "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...", + "context_length": 1048576, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["image", "text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000018", + "completion": "0.00000018" + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta-llama/llama-guard-4-12b/endpoints" + } + }, + { + "id": "meta/muse-glimmer-30b", + "canonical_slug": "meta/muse-glimmer-30b-20260810", + "hugging_face_id": "meta-models/Muse-Glimmer-30B", + "name": "Meta: Muse Glimmer 30B", + "created": 1786302394, + "description": "Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...", + "context_length": 131072, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000035", + "completion": "0.0000015", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": 64 + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-glimmer-30b-20260810/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "meta/muse-spark-1.1", + "canonical_slug": "meta/muse-spark-1.1-20260709", + "hugging_face_id": null, + "name": "Meta: Muse Spark 1.1", + "created": 1784215741, + "description": "Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000125", + "completion": "0.00000425", + "web_search": "0.0025", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": null, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-spark-1.1-20260709/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1188, + "win_rate": 48.2, + "rank": 8 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1217, + "win_rate": 50.3, + "rank": 14 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1244, + "win_rate": 49.6, + "rank": 13 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 39.4, + "rank": 17 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1212, + "win_rate": 51.7, + "rank": 8 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1210, + "win_rate": 47.2, + "rank": 16 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1177, + "win_rate": 44.2, + "rank": 13 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1241, + "win_rate": 50.3, + "rank": 14 + }, + { + "arena": "models", + "category": "3d", + "elo": 1306, + "win_rate": 53.4, + "rank": 16 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1329, + "win_rate": 62, + "rank": 2 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1298, + "win_rate": 53.5, + "rank": 12 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1305, + "win_rate": 52.5, + "rank": 11 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1320, + "win_rate": 52.2, + "rank": 11 + }, + { + "arena": "models", + "category": "svg", + "elo": 1257, + "win_rate": 48.2, + "rank": 9 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1322, + "win_rate": 53.4, + "rank": 10 + }, + { + "arena": "models", + "category": "website", + "elo": 1283, + "win_rate": 53.2, + "rank": 20 + } + ], + "artificial_analysis": { + "intelligence_index": 53.2, + "coding_index": 71.3, + "agentic_index": 39.7 + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "meta/muse-spark-1.2", + "canonical_slug": "meta/muse-spark-1.2-20260805", + "hugging_face_id": null, + "name": "Meta: Muse Spark 1.2", + "created": 1785959287, + "description": "Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": ["text", "image", "video", "file", "audio"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000125", + "completion": "0.00000425", + "web_search": "0.0025", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": null, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/meta/muse-spark-1.2-20260805/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1237, + "win_rate": 53.9, + "rank": 9 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1247, + "win_rate": 50.2, + "rank": 12 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1052, + "win_rate": 28.2, + "rank": 20 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1208, + "win_rate": 47.3, + "rank": 17 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1087, + "win_rate": 32.2, + "rank": 19 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1264, + "win_rate": 52.2, + "rank": 8 + }, + { + "arena": "models", + "category": "3d", + "elo": 1355, + "win_rate": 62.3, + "rank": 6 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1340, + "win_rate": 59.4, + "rank": 3 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1366, + "win_rate": 63.5, + "rank": 4 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1358, + "win_rate": 60.7, + "rank": 4 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1345, + "win_rate": 58.4, + "rank": 5 + }, + { + "arena": "models", + "category": "website", + "elo": 1328, + "win_rate": 57.9, + "rank": 4 + } + ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low", "minimal"], + "default_effort": "medium" + } + }, + { + "id": "microsoft/phi-4", + "canonical_slug": "microsoft/phi-4", + "hugging_face_id": "microsoft/phi-4", + "name": "Microsoft: Phi 4", + "created": 1736489872, + "description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...", + "context_length": 16384, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000007", + "completion": "0.00000014" + }, + "top_provider": { + "context_length": 16384, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/microsoft/phi-4/endpoints" + } + }, + { + "id": "microsoft/wizardlm-2-8x22b", + "canonical_slug": "microsoft/wizardlm-2-8x22b", + "hugging_face_id": "microsoft/WizardLM-2-8x22B", + "name": "WizardLM-2 8x22B", + "created": 1713225600, + "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...", + "context_length": 65535, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": "vicuna" + }, + "pricing": { + "prompt": "0.00000062", + "completion": "0.00000062" + }, + "top_provider": { + "context_length": 65535, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-04-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints" + } + }, + { + "id": "minimax/minimax-01", + "canonical_slug": "minimax/minimax-01", + "hugging_face_id": "MiniMaxAI/MiniMax-Text-01", + "name": "MiniMax: MiniMax-01", + "created": 1736915462, + "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...", + "context_length": 1000192, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000011" + }, + "top_provider": { + "context_length": 1000192, + "max_completion_tokens": 1000192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": ["max_tokens", "temperature", "top_p"], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2024-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-01/endpoints" + } + }, + { + "id": "minimax/minimax-m1", + "canonical_slug": "minimax/minimax-m1", + "hugging_face_id": "", + "name": "MiniMax: MiniMax M1", + "created": 1750200414, + "description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.0000022" + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 40000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m1/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "minimax/minimax-m2", + "canonical_slug": "minimax/minimax-m2", + "hugging_face_id": "MiniMaxAI/MiniMax-M2", + "name": "MiniMax: MiniMax M2", + "created": 1761252093, + "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...", + "context_length": 204800, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000255", + "completion": "0.00000102" + }, + "top_provider": { + "context_length": 204800, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m2/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1151, + "win_rate": 48.6, + "rank": 67 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1153, + "win_rate": 48.1, + "rank": 73 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1164, + "win_rate": 49.8, + "rank": 67 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1155, + "win_rate": 48.3, + "rank": 69 + }, + { + "arena": "models", + "category": "svg", + "elo": 1132, + "win_rate": 54, + "rank": 48 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1165, + "win_rate": 49.7, + "rank": 67 + }, + { + "arena": "models", + "category": "website", + "elo": 1153, + "win_rate": 47.9, + "rank": 76 + } + ] + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "minimax/minimax-m2-her", + "canonical_slug": "minimax/minimax-m2-her-20260123", + "hugging_face_id": "", + "name": "MiniMax: MiniMax M2-her", + "created": 1769177239, + "description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...", + "context_length": 65536, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": ["max_tokens", "temperature", "top_p"], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m2-her-20260123/endpoints" + } + }, + { + "id": "minimax/minimax-m2.1", + "canonical_slug": "minimax/minimax-m2.1", + "hugging_face_id": "MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax: MiniMax M2.1", + "created": 1766454997, + "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...", + "context_length": 204800, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 204800, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.9, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m2.1/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1219, + "win_rate": 57.6, + "rank": 44 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1210, + "win_rate": 55.3, + "rank": 44 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1230, + "win_rate": 56.5, + "rank": 40 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1172, + "win_rate": 50.5, + "rank": 64 + }, + { + "arena": "models", + "category": "svg", + "elo": 1164, + "win_rate": 54.2, + "rank": 41 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1253, + "win_rate": 61.2, + "rank": 35 + }, + { + "arena": "models", + "category": "website", + "elo": 1213, + "win_rate": 55.4, + "rank": 45 + } + ] + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "minimax/minimax-m2.5", + "canonical_slug": "minimax/minimax-m2.5-20260211", + "hugging_face_id": "MiniMaxAI/MiniMax-M2.5", + "name": "MiniMax: MiniMax M2.5", + "created": 1770908502, + "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", + "context_length": 204800, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000022", + "completion": "0.0000009", + "input_cache_read": "0.00000005" + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": 196608, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m2.5-20260211/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1223, + "win_rate": 57.5, + "rank": 43 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1226, + "win_rate": 56.7, + "rank": 41 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1195, + "win_rate": 51, + "rank": 52 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1215, + "win_rate": 55.6, + "rank": 45 + }, + { + "arena": "models", + "category": "svg", + "elo": 1185, + "win_rate": 54.6, + "rank": 31 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1201, + "win_rate": 53.3, + "rank": 50 + }, + { + "arena": "models", + "category": "website", + "elo": 1233, + "win_rate": 57.4, + "rank": 41 + } + ] + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "minimax/minimax-m2.7", + "canonical_slug": "minimax/minimax-m2.7-20260318", + "hugging_face_id": "MiniMaxAI/MiniMax-M2.7", + "name": "MiniMax: MiniMax M2.7", + "created": 1773836697, + "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...", + "context_length": 204800, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000006" + }, + "top_provider": { + "context_length": 204800, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m2.7-20260318/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1247, + "win_rate": 50.8, + "rank": 36 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1171, + "win_rate": 47.6, + "rank": 35 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1254, + "win_rate": 52.6, + "rank": 32 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1254, + "win_rate": 52.8, + "rank": 30 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1245, + "win_rate": 52.2, + "rank": 35 + }, + { + "arena": "models", + "category": "svg", + "elo": 1172, + "win_rate": 49.8, + "rank": 37 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1240, + "win_rate": 49.7, + "rank": 39 + }, + { + "arena": "models", + "category": "website", + "elo": 1258, + "win_rate": 53.3, + "rank": 32 + } + ], + "artificial_analysis": { + "intelligence_index": 38.9, + "coding_index": 52.6, + "agentic_index": 25.9 + } + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "minimax/minimax-m3", + "canonical_slug": "minimax/minimax-m3-20260531", + "hugging_face_id": "MiniMaxAI/Minimax-M3", + "name": "MiniMax: MiniMax M3", + "created": 1780245374, + "description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000012", + "input_cache_read": "0.00000006" + }, + "top_provider": { + "context_length": 524288, + "max_completion_tokens": 512000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1194, + "win_rate": 52, + "rank": 7 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1176, + "win_rate": 46.4, + "rank": 25 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1224, + "win_rate": 50, + "rank": 15 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1175, + "win_rate": 43, + "rank": 14 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1222, + "win_rate": 50.5, + "rank": 12 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1223, + "win_rate": 49.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1236, + "win_rate": 49.7, + "rank": 16 + }, + { + "arena": "models", + "category": "3d", + "elo": 1270, + "win_rate": 53.3, + "rank": 29 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1189, + "win_rate": 47.2, + "rank": 25 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1271, + "win_rate": 53.4, + "rank": 25 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1256, + "win_rate": 52.1, + "rank": 29 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1253, + "win_rate": 48.9, + "rank": 33 + }, + { + "arena": "models", + "category": "svg", + "elo": 1204, + "win_rate": 50, + "rank": 26 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1274, + "win_rate": 52.7, + "rank": 26 + }, + { + "arena": "models", + "category": "website", + "elo": 1272, + "win_rate": 53.9, + "rank": 25 + } + ], + "artificial_analysis": { + "intelligence_index": 45.4, + "coding_index": 58.6, + "agentic_index": 36.1 + } + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "minimax/minimax-m3:batch", + "canonical_slug": "minimax/minimax-m3-20260531", + "hugging_face_id": "MiniMaxAI/Minimax-M3", + "name": "MiniMax: MiniMax M3 (batch)", + "created": 1780245374, + "description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...", + "context_length": 524288, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 524288, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1194, + "win_rate": 52, + "rank": 7 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1176, + "win_rate": 46.4, + "rank": 25 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1224, + "win_rate": 50, + "rank": 15 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1175, + "win_rate": 43, + "rank": 14 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1222, + "win_rate": 50.5, + "rank": 12 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1223, + "win_rate": 49.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1236, + "win_rate": 49.7, + "rank": 16 + }, + { + "arena": "models", + "category": "3d", + "elo": 1270, + "win_rate": 53.3, + "rank": 29 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1189, + "win_rate": 47.2, + "rank": 25 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1271, + "win_rate": 53.4, + "rank": 25 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1256, + "win_rate": 52.1, + "rank": 29 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1253, + "win_rate": 48.9, + "rank": 33 + }, + { + "arena": "models", + "category": "svg", + "elo": 1204, + "win_rate": 50, + "rank": 26 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1274, + "win_rate": 52.7, + "rank": 26 + }, + { + "arena": "models", + "category": "website", + "elo": 1272, + "win_rate": 53.9, + "rank": 25 + } + ], + "artificial_analysis": { + "intelligence_index": 45.4, + "coding_index": 58.6, + "agentic_index": 36.1 + } + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "mistralai/codestral-2508", + "canonical_slug": "mistralai/codestral-2508", + "hugging_face_id": "", + "name": "Mistral: Codestral 2508", + "created": 1754079630, + "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)", + "context_length": 256000, + "architecture": { + "modality": "text+file->text", + "input_modalities": ["text", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000009", + "input_cache_read": "0.00000003" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "prediction", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/codestral-2508/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1026, + "win_rate": 38.5, + "rank": 103 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1040, + "win_rate": 41.1, + "rank": 97 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1006, + "win_rate": 36.3, + "rank": 108 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1045, + "win_rate": 46.7, + "rank": 92 + }, + { + "arena": "models", + "category": "website", + "elo": 1024, + "win_rate": 37.8, + "rank": 108 + }, + { + "arena": "models", + "category": "3d", + "elo": 1074, + "win_rate": 45.4, + "rank": 90 + } + ] + } + }, + { + "id": "mistralai/ministral-14b-2512", + "canonical_slug": "mistralai/ministral-14b-2512", + "hugging_face_id": "mistralai/Ministral-3-14B-Instruct-2512", + "name": "Mistral: Ministral 3 14B 2512", + "created": 1764681735, + "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000002", + "input_cache_read": "0.00000002" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/ministral-14b-2512/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1044, + "win_rate": 39.6, + "rank": 95 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1084, + "win_rate": 44, + "rank": 92 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1076, + "win_rate": 43.6, + "rank": 93 + }, + { + "arena": "models", + "category": "website", + "elo": 1092, + "win_rate": 44.8, + "rank": 95 + } + ], + "artificial_analysis": { + "intelligence_index": 11.2, + "coding_index": 14.4, + "agentic_index": 2.2 + } + } + }, + { + "id": "mistralai/ministral-3b-2512", + "canonical_slug": "mistralai/ministral-3b-2512", + "hugging_face_id": "mistralai/Ministral-3-3B-Instruct-2512", + "name": "Mistral: Ministral 3 3B 2512", + "created": 1764681560, + "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", + "context_length": 131072, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000001", + "input_cache_read": "0.00000001" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/ministral-3b-2512/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1016, + "win_rate": 35.9, + "rank": 101 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1029, + "win_rate": 37.3, + "rank": 102 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 987, + "win_rate": 33, + "rank": 111 + }, + { + "arena": "models", + "category": "website", + "elo": 1039, + "win_rate": 38.2, + "rank": 106 + } + ], + "artificial_analysis": { + "intelligence_index": 7.1, + "coding_index": 4.8, + "agentic_index": 1.6 + } + } + }, + { + "id": "mistralai/ministral-8b-2512", + "canonical_slug": "mistralai/ministral-8b-2512", + "hugging_face_id": "mistralai/Ministral-3-8B-Instruct-2512", + "name": "Mistral: Ministral 3 8B 2512", + "created": 1764681654, + "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.00000015", + "input_cache_read": "0.000000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/ministral-8b-2512/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1085, + "win_rate": 46.2, + "rank": 88 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1072, + "win_rate": 42.9, + "rank": 93 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1028, + "win_rate": 38.7, + "rank": 103 + }, + { + "arena": "models", + "category": "website", + "elo": 1076, + "win_rate": 42.9, + "rank": 97 + } + ], + "artificial_analysis": { + "intelligence_index": 9, + "coding_index": 9.7, + "agentic_index": 1.2 + } + } + }, + { + "id": "mistralai/mistral-large", + "canonical_slug": "mistralai/mistral-large", + "hugging_face_id": null, + "name": "Mistral Large", + "created": 1708905600, + "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", + "context_length": 128000, + "architecture": { + "modality": "text+file->text", + "input_modalities": ["text", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000006", + "input_cache_read": "0.0000002" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2024-11-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-large/endpoints" + } + }, + { + "id": "mistralai/mistral-large-2407", + "canonical_slug": "mistralai/mistral-large-2407", + "hugging_face_id": "", + "name": "Mistral Large 2407", + "created": 1731978415, + "description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", + "context_length": 131072, + "architecture": { + "modality": "text+file->text", + "input_modalities": ["text", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000006", + "input_cache_read": "0.0000002" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2024-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-large-2407/endpoints" + } + }, + { + "id": "mistralai/mistral-large-2512", + "canonical_slug": "mistralai/mistral-large-2512", + "hugging_face_id": "", + "name": "Mistral: Mistral Large 3 2512", + "created": 1764624472, + "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", + "context_length": 262144, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000005", + "completion": "0.0000015", + "input_cache_read": "0.00000005" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.0645, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-large-2512/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1153, + "win_rate": 47, + "rank": 66 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1102, + "win_rate": 40.3, + "rank": 52 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1161, + "win_rate": 47.6, + "rank": 68 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1160, + "win_rate": 45.8, + "rank": 68 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1118, + "win_rate": 41.6, + "rank": 83 + }, + { + "arena": "models", + "category": "svg", + "elo": 1026, + "win_rate": 37.7, + "rank": 72 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1130, + "win_rate": 43.3, + "rank": 75 + }, + { + "arena": "models", + "category": "website", + "elo": 1173, + "win_rate": 49.4, + "rank": 68 + } + ], + "artificial_analysis": { + "intelligence_index": 15.9, + "coding_index": 20.1, + "agentic_index": 5.5 + } + } + }, + { + "id": "mistralai/mistral-medium-3", + "canonical_slug": "mistralai/mistral-medium-3", + "hugging_face_id": "", + "name": "Mistral: Mistral Medium 3", + "created": 1746627341, + "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...", + "context_length": 131072, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.000002", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-medium-3/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1137, + "win_rate": 54.7, + "rank": 71 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1088, + "win_rate": 48.1, + "rank": 91 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1056, + "win_rate": 46, + "rank": 95 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1056, + "win_rate": 45.2, + "rank": 97 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1053, + "win_rate": 49.6, + "rank": 91 + }, + { + "arena": "models", + "category": "website", + "elo": 1090, + "win_rate": 47.6, + "rank": 96 + } + ] + } + }, + { + "id": "mistralai/mistral-medium-3-5", + "canonical_slug": "mistralai/mistral-medium-3.5-20260430", + "hugging_face_id": null, + "name": "Mistral: Mistral Medium 3.5", + "created": 1777570439, + "description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...", + "context_length": 262144, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000015", + "completion": "0.0000075" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 30.4, + "coding_index": 46.9, + "agentic_index": 19.2 + } + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["high", "none"], + "default_effort": "high" + } + }, + { + "id": "mistralai/mistral-medium-3.1", + "canonical_slug": "mistralai/mistral-medium-3.1", + "hugging_face_id": "", + "name": "Mistral: Mistral Medium 3.1", + "created": 1755095639, + "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...", + "context_length": 131072, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.000002", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2025-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-medium-3.1/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1135, + "win_rate": 44.6, + "rank": 72 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1030, + "win_rate": 30.8, + "rank": 56 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1139, + "win_rate": 45, + "rank": 77 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1167, + "win_rate": 47.3, + "rank": 66 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1112, + "win_rate": 40.8, + "rank": 86 + }, + { + "arena": "models", + "category": "svg", + "elo": 1025, + "win_rate": 37.5, + "rank": 73 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1127, + "win_rate": 43.5, + "rank": 77 + }, + { + "arena": "models", + "category": "website", + "elo": 1143, + "win_rate": 45.9, + "rank": 79 + } + ], + "artificial_analysis": { + "intelligence_index": 14.7, + "coding_index": 20.5, + "agentic_index": 6.1 + } + } + }, + { + "id": "mistralai/mistral-nemo", + "canonical_slug": "mistralai/mistral-nemo", + "hugging_face_id": "mistralai/Mistral-Nemo-Instruct-2407", + "name": "Mistral: Mistral Nemo", + "created": 1721347200, + "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "pricing": { + "prompt": "0.000000019", + "completion": "0.00000003" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2024-04-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-nemo/endpoints" + } + }, + { + "id": "mistralai/mistral-saba", + "canonical_slug": "mistralai/mistral-saba-2502", + "hugging_face_id": "", + "name": "Mistral: Saba", + "created": 1739803239, + "description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...", + "context_length": 32768, + "architecture": { + "modality": "text+file->text", + "input_modalities": ["text", "file"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000006", + "input_cache_read": "0.00000002" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2024-09-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-saba-2502/endpoints" + } + }, + { + "id": "mistralai/mistral-small-24b-instruct-2501", + "canonical_slug": "mistralai/mistral-small-24b-instruct-2501", + "hugging_face_id": "mistralai/Mistral-Small-24B-Instruct-2501", + "name": "Mistral: Mistral Small 3", + "created": 1738255409, + "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...", + "context_length": 32768, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000005", + "completion": "0.00000008" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": 0.3, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2023-10-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints" + } + }, + { + "id": "mistralai/mistral-small-2603", + "canonical_slug": "mistralai/mistral-small-2603", + "hugging_face_id": "mistralai/Mistral-Small-4-119B-2603", + "name": "Mistral: Mistral Small 4", + "created": 1773695685, + "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...", + "context_length": 262144, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-small-2603/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 19.7, + "coding_index": 26.6, + "agentic_index": 4.6 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["high", "none"], + "default_effort": "high" + } + }, + { + "id": "mistralai/mistral-small-3.1-24b-instruct", + "canonical_slug": "mistralai/mistral-small-3.1-24b-instruct-2503", + "hugging_face_id": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", + "name": "Mistral: Mistral Small 3.1 24B", + "created": 1742238937, + "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...", + "context_length": 128000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000351", + "completion": "0.000000555" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 0.3 + }, + "supported_voices": null, + "knowledge_cutoff": "2023-10-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints" + } + }, + { + "id": "mistralai/mistral-small-3.2-24b-instruct", + "canonical_slug": "mistralai/mistral-small-3.2-24b-instruct-2506", + "hugging_face_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", + "name": "Mistral: Mistral Small 3.2 24B", + "created": 1750443016, + "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...", + "context_length": 256000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["image", "text"], + "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.00000032" + "prompt": "0.00000009375", + "completion": "0.00000025" }, "top_provider": { - "context_length": 131072, + "context_length": 256000, "max_completion_tokens": 16384, "is_moderated": false }, @@ -8768,40 +15801,74 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 0.3 + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" + "details": "/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 9.4, - "coding_index": 11.9, - "agentic_index": 0.3 - } + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 926, + "win_rate": 39.8, + "rank": 114 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 950, + "win_rate": 43.3, + "rank": 107 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 926, + "win_rate": 39.4, + "rank": 117 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 935, + "win_rate": 40.5, + "rank": 108 + }, + { + "arena": "models", + "category": "website", + "elo": 906, + "win_rate": 38.3, + "rank": 119 + } + ] } }, { - "id": "meta-llama/llama-3.3-70b-instruct:free", - "canonical_slug": "meta-llama/llama-3.3-70b-instruct", - "hugging_face_id": "meta-llama/Llama-3.3-70B-Instruct", - "name": "Meta: Llama 3.3 70B Instruct (free)", - "created": 1733506137, - "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", - "context_length": 131072, + "id": "mistralai/mixtral-8x22b-instruct", + "canonical_slug": "mistralai/mixtral-8x22b-instruct", + "hugging_face_id": "mistralai/Mixtral-8x22B-Instruct-v0.1", + "name": "Mistral: Mixtral 8x22B Instruct", + "created": 1713312000, + "description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...", + "context_length": 65536, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+file->text", + "input_modalities": ["text", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Mistral", + "instruct_type": "mistral" }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000002", + "completion": "0.000006", + "input_cache_read": "0.0000002" }, "top_provider": { "context_length": 65536, @@ -8813,62 +15880,56 @@ "frequency_penalty", "max_tokens", "presence_penalty", + "response_format", + "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 0.3 + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2024-01-31", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 9.4, - "coding_index": 11.9, - "agentic_index": 0.3 - } + "details": "/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints" } }, { - "id": "meta-llama/llama-4-maverick", - "canonical_slug": "meta-llama/llama-4-maverick-17b-128e-instruct", - "hugging_face_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", - "name": "Meta: Llama 4 Maverick", - "created": 1743881822, - "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...", - "context_length": 1048576, + "id": "mistralai/voxtral-small-24b-2507", + "canonical_slug": "mistralai/voxtral-small-24b-2507", + "hugging_face_id": "mistralai/Voxtral-Small-24B-2507", + "name": "Mistral: Voxtral Small 24B 2507", + "created": 1761835144, + "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...", + "context_length": 32000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+file+audio->text", + "input_modalities": ["text", "audio", "file"], "output_modalities": ["text"], - "tokenizer": "Llama4", + "tokenizer": "Mistral", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006" + "prompt": "0.0000001", + "completion": "0.0000003", + "audio": "0.0001", + "input_cache_read": "0.00000001" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 16384, + "context_length": 32000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", - "logprobs", "max_tokens", - "min_p", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", @@ -8876,99 +15937,133 @@ "temperature", "tool_choice", "tools", + "top_p" + ], + "default_parameters": { + "temperature": 0.2, + "top_p": 0.95, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints" + } + }, + { + "id": "moonshotai/kimi-k2", + "canonical_slug": "moonshotai/kimi-k2", + "hugging_face_id": "moonshotai/Kimi-K2-Instruct", + "name": "MoonshotAI: Kimi K2 0711", + "created": 1752263252, + "description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000057", + "completion": "0.0000023" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 100352, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": "2024-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 977, - "win_rate": 40.2, - "rank": 92 - }, { "arena": "models", "category": "codecategories", - "elo": 929, - "win_rate": 35.8, - "rank": 103 + "elo": 1052, + "win_rate": 51.7, + "rank": 97 }, { "arena": "models", "category": "dataviz", - "elo": 926, - "win_rate": 38.4, - "rank": 101 + "elo": 1039, + "win_rate": 49.4, + "rank": 98 }, { "arena": "models", "category": "gamedev", - "elo": 903, - "win_rate": 33.7, - "rank": 104 + "elo": 1012, + "win_rate": 46.4, + "rank": 105 }, { "arena": "models", "category": "uicomponent", - "elo": 954, - "win_rate": 40.8, - "rank": 95 + "elo": 1059, + "win_rate": 55.1, + "rank": 89 }, { "arena": "models", "category": "website", - "elo": 914, - "win_rate": 34.4, - "rank": 106 + "elo": 1061, + "win_rate": 53.1, + "rank": 101 } - ], - "artificial_analysis": { - "intelligence_index": 14.3, - "coding_index": 16.3, - "agentic_index": 1.3 - } + ] } }, { - "id": "meta-llama/llama-4-scout", - "canonical_slug": "meta-llama/llama-4-scout-17b-16e-instruct", - "hugging_face_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", - "name": "Meta: Llama 4 Scout", - "created": 1743881519, - "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...", - "context_length": 10000000, + "id": "moonshotai/kimi-k2-0905", + "canonical_slug": "moonshotai/kimi-k2-0905", + "hugging_face_id": "moonshotai/Kimi-K2-Instruct-0905", + "name": "MoonshotAI: Kimi K2 0905", + "created": 1757021147, + "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Llama4", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000003" + "prompt": "0.0000006", + "completion": "0.0000025" }, "top_provider": { - "context_length": 327680, - "max_completion_tokens": 16384, + "context_length": 262144, + "max_completion_tokens": 100352, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", "max_tokens", - "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -8983,558 +16078,1048 @@ ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": "2024-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2-0905/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "codecategories", - "elo": 839, - "win_rate": 26.6, - "rank": 107 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 939, - "win_rate": 39.3, - "rank": 97 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 838, - "win_rate": 27.4, - "rank": 106 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 822, - "win_rate": 25.5, - "rank": 101 + "elo": 1117, + "win_rate": 48.5, + "rank": 85 }, { "arena": "models", "category": "website", - "elo": 793, - "win_rate": 22.7, - "rank": 113 + "elo": 1118, + "win_rate": 48.3, + "rank": 89 } - ], - "artificial_analysis": { - "intelligence_index": 10, - "coding_index": 8.2, - "agentic_index": 1.1 - } + ] } }, { - "id": "meta-llama/llama-guard-4-12b", - "canonical_slug": "meta-llama/llama-guard-4-12b", - "hugging_face_id": "meta-llama/Llama-Guard-4-12B", - "name": "Meta: Llama Guard 4 12B", - "created": 1745975193, - "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...", - "context_length": 163840, + "id": "moonshotai/kimi-k2-thinking", + "canonical_slug": "moonshotai/kimi-k2-thinking-20251106", + "hugging_face_id": "moonshotai/Kimi-K2-Thinking", + "name": "MoonshotAI: Kimi K2 Thinking", + "created": 1762440622, + "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000018", - "completion": "0.00000018" + "prompt": "0.0000006", + "completion": "0.0000025", + "input_cache_read": "0.00000015" }, "top_provider": { - "context_length": 163840, - "max_completion_tokens": 16384, + "context_length": 262144, + "max_completion_tokens": 100352, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", + "include_reasoning", + "logprobs", "max_tokens", - "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/meta-llama/llama-guard-4-12b/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "website", + "elo": 1124, + "win_rate": 48.8, + "rank": 87 + } + ], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 21, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": true, + "default_enabled": true } }, { - "id": "microsoft/phi-4", - "canonical_slug": "microsoft/phi-4", - "hugging_face_id": "microsoft/phi-4", - "name": "Microsoft: Phi 4", - "created": 1736489872, - "description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...", - "context_length": 16384, + "id": "moonshotai/kimi-k2.5", + "canonical_slug": "moonshotai/kimi-k2.5-0127", + "hugging_face_id": "moonshotai/Kimi-K2.5", + "name": "MoonshotAI: Kimi K2.5", + "created": 1769487076, + "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000007", - "completion": "0.00000014" + "prompt": "0.00000057", + "completion": "0.00000285", + "input_cache_read": "0.000000095" }, "top_provider": { - "context_length": 16384, - "max_completion_tokens": 16384, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/microsoft/phi-4/endpoints" - } - }, - { - "id": "microsoft/wizardlm-2-8x22b", - "canonical_slug": "microsoft/wizardlm-2-8x22b", - "hugging_face_id": "microsoft/WizardLM-2-8x22B", - "name": "WizardLM-2 8x22B", - "created": 1713225600, - "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...", - "context_length": 65536, + "details": "/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1154, + "win_rate": 57.9, + "rank": 26 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1152, + "win_rate": 54.2, + "rank": 24 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1219, + "win_rate": 59.8, + "rank": 9 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1198, + "win_rate": 54.2, + "rank": 21 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1169, + "win_rate": 50.1, + "rank": 25 + }, + { + "arena": "models", + "category": "3d", + "elo": 1259, + "win_rate": 53.1, + "rank": 33 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1203, + "win_rate": 46.5, + "rank": 19 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1256, + "win_rate": 54.1, + "rank": 31 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1243, + "win_rate": 51.3, + "rank": 36 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1244, + "win_rate": 53.5, + "rank": 37 + }, + { + "arena": "models", + "category": "svg", + "elo": 1183, + "win_rate": 48.3, + "rank": 35 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1266, + "win_rate": 53.7, + "rank": 30 + }, + { + "arena": "models", + "category": "website", + "elo": 1261, + "win_rate": 55.3, + "rank": 29 + } + ], + "artificial_analysis": { + "intelligence_index": 36, + "coding_index": 46.8, + "agentic_index": 21.7 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true + } + }, + { + "id": "moonshotai/kimi-k2.6", + "canonical_slug": "moonshotai/kimi-k2.6-20260420", + "hugging_face_id": "moonshotai/Kimi-K2.6", + "name": "MoonshotAI: Kimi K2.6", + "created": 1776699402, + "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": "vicuna" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000062", - "completion": "0.00000062" + "prompt": "0.0000005415", + "completion": "0.00000228", + "input_cache_read": "0.0000000912" }, "top_provider": { - "context_length": 65535, - "max_completion_tokens": 8000, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", + "parallel_tool_calls", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2024-04-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints" - } - }, - { - "id": "minimax/minimax-01", - "canonical_slug": "minimax/minimax-01", - "hugging_face_id": "MiniMaxAI/MiniMax-Text-01", - "name": "MiniMax: MiniMax-01", - "created": 1736915462, - "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...", - "context_length": 1000192, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000002", - "completion": "0.0000011" - }, - "top_provider": { - "context_length": 1000192, - "max_completion_tokens": 1000192, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": ["max_tokens", "temperature", "top_p"], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-01/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1146, + "win_rate": 47.9, + "rank": 15 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1248, + "win_rate": 59, + "rank": 2 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1187, + "win_rate": 45.8, + "rank": 5 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1252, + "win_rate": 59.2, + "rank": 2 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1186, + "win_rate": 45.5, + "rank": 5 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1195, + "win_rate": 51.3, + "rank": 20 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1193, + "win_rate": 53.9, + "rank": 21 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1161, + "win_rate": 47.1, + "rank": 15 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1219, + "win_rate": 53.6, + "rank": 6 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1216, + "win_rate": 53.6, + "rank": 13 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1181, + "win_rate": 44.3, + "rank": 5 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1180, + "win_rate": 42.1, + "rank": 12 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1268, + "win_rate": 59.3, + "rank": 7 + }, + { + "arena": "models", + "category": "3d", + "elo": 1326, + "win_rate": 59.6, + "rank": 11 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1191, + "win_rate": 47.2, + "rank": 23 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1295, + "win_rate": 56.2, + "rank": 16 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1280, + "win_rate": 55.8, + "rank": 18 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1291, + "win_rate": 55.9, + "rank": 22 + }, + { + "arena": "models", + "category": "svg", + "elo": 1215, + "win_rate": 51.8, + "rank": 22 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1296, + "win_rate": 56, + "rank": 19 + }, + { + "arena": "models", + "category": "website", + "elo": 1284, + "win_rate": 54.9, + "rank": 18 + } + ], + "artificial_analysis": { + "intelligence_index": 45.1, + "coding_index": 61.8, + "agentic_index": 31.2 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true } }, { - "id": "minimax/minimax-m1", - "canonical_slug": "minimax/minimax-m1", - "hugging_face_id": "", - "name": "MiniMax: MiniMax M1", - "created": 1750200414, - "description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...", - "context_length": 1000000, + "id": "moonshotai/kimi-k2.7-code", + "canonical_slug": "moonshotai/kimi-k2.7-code-20260612", + "hugging_face_id": "moonshotai/Kimi-K2.7-Code", + "name": "MoonshotAI: Kimi K2.7 Code", + "created": 1781266361, + "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, - "pricing": { - "prompt": "0.0000004", - "completion": "0.0000022" + "pricing": { + "prompt": "0.00000071", + "completion": "0.0000035", + "input_cache_read": "0.00000015" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 40000, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", + "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", + "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-m1/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1135, + "win_rate": 42.9, + "rank": 16 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1177, + "win_rate": 48, + "rank": 23 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1212, + "win_rate": 53.4, + "rank": 17 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1185, + "win_rate": 49.3, + "rank": 12 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1218, + "win_rate": 53.6, + "rank": 7 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1204, + "win_rate": 50.5, + "rank": 20 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1161, + "win_rate": 44, + "rank": 15 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1216, + "win_rate": 48.3, + "rank": 20 + }, + { + "arena": "models", + "category": "3d", + "elo": 1296, + "win_rate": 52.2, + "rank": 21 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1245, + "win_rate": 51.9, + "rank": 13 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1278, + "win_rate": 52.3, + "rank": 24 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1248, + "win_rate": 50.9, + "rank": 33 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1251, + "win_rate": 49.7, + "rank": 34 + }, + { + "arena": "models", + "category": "svg", + "elo": 1210, + "win_rate": 49.3, + "rank": 24 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1290, + "win_rate": 53, + "rank": 22 + }, + { + "arena": "models", + "category": "website", + "elo": 1284, + "win_rate": 53.8, + "rank": 19 + } + ], + "artificial_analysis": { + "intelligence_index": 43, + "coding_index": 60.8, + "agentic_index": 30.3 + } }, "reasoning": { - "mandatory": false + "mandatory": true, + "default_enabled": true } }, { - "id": "minimax/minimax-m2", - "canonical_slug": "minimax/minimax-m2", - "hugging_face_id": "MiniMaxAI/MiniMax-M2", - "name": "MiniMax: MiniMax M2", - "created": 1761252093, - "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...", - "context_length": 204800, + "id": "moonshotai/kimi-k2.7-code:batch", + "canonical_slug": "moonshotai/kimi-k2.7-code-20260612", + "hugging_face_id": "moonshotai/Kimi-K2.7-Code", + "name": "MoonshotAI: Kimi K2.7 Code (batch)", + "created": 1781266361, + "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000000255", - "completion": "0.00000102" + "prompt": "0.000000475", + "completion": "0.000002", + "input_cache_read": "0.000000095" }, "top_provider": { - "context_length": 204800, - "max_completion_tokens": 131072, + "context_length": 262144, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logprobs", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "frequency_penalty": null + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-m2/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1135, + "win_rate": 42.9, + "rank": 16 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1177, + "win_rate": 48, + "rank": 23 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1212, + "win_rate": 53.4, + "rank": 17 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1185, + "win_rate": 49.3, + "rank": 12 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1218, + "win_rate": 53.6, + "rank": 7 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1204, + "win_rate": 50.5, + "rank": 20 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1161, + "win_rate": 44, + "rank": 15 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1216, + "win_rate": 48.3, + "rank": 20 + }, { "arena": "models", "category": "3d", - "elo": 1175, - "win_rate": 48.3, - "rank": 53 + "elo": 1296, + "win_rate": 52.2, + "rank": 21 }, { "arena": "models", - "category": "codecategories", - "elo": 1184, - "win_rate": 48.1, - "rank": 60 + "category": "asciiart", + "elo": 1245, + "win_rate": 51.9, + "rank": 13 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1278, + "win_rate": 52.3, + "rank": 24 }, { "arena": "models", "category": "dataviz", - "elo": 1184, - "win_rate": 50, - "rank": 55 + "elo": 1248, + "win_rate": 50.9, + "rank": 33 }, { "arena": "models", "category": "gamedev", - "elo": 1183, - "win_rate": 48.1, - "rank": 56 + "elo": 1251, + "win_rate": 49.7, + "rank": 34 }, { "arena": "models", "category": "svg", - "elo": 1158, - "win_rate": 55.3, - "rank": 42 + "elo": 1210, + "win_rate": 49.3, + "rank": 24 }, { "arena": "models", "category": "uicomponent", - "elo": 1190, - "win_rate": 49.2, - "rank": 53 + "elo": 1290, + "win_rate": 53, + "rank": 22 }, { "arena": "models", "category": "website", - "elo": 1185, - "win_rate": 48, - "rank": 60 + "elo": 1284, + "win_rate": 53.8, + "rank": 19 } - ] + ], + "artificial_analysis": { + "intelligence_index": 43, + "coding_index": 60.8, + "agentic_index": 30.3 + } }, "reasoning": { - "mandatory": true - } - }, - { - "id": "minimax/minimax-m2-her", - "canonical_slug": "minimax/minimax-m2-her-20260123", - "hugging_face_id": "", - "name": "MiniMax: MiniMax M2-her", - "created": 1769177239, - "description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...", - "context_length": 65536, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", - "input_cache_read": "0.00000003" - }, - "top_provider": { - "context_length": 65536, - "max_completion_tokens": 2048, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": ["max_tokens", "temperature", "top_p"], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/minimax/minimax-m2-her-20260123/endpoints" + "mandatory": true, + "default_enabled": true } }, { - "id": "minimax/minimax-m2.1", - "canonical_slug": "minimax/minimax-m2.1", - "hugging_face_id": "MiniMaxAI/MiniMax-M2.1", - "name": "MiniMax: MiniMax M2.1", - "created": 1766454997, - "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...", - "context_length": 204800, + "id": "moonshotai/kimi-k3", + "canonical_slug": "moonshotai/kimi-k3-20260715", + "hugging_face_id": "moonshotai/Kimi-K3", + "name": "MoonshotAI: Kimi K3", + "created": 1784215858, + "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...", + "context_length": 1048576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", - "input_cache_read": "0.00000003" + "prompt": "0.000003", + "completion": "0.000015", + "input_cache_read": "0.0000003" }, "top_provider": { - "context_length": 204800, - "max_completion_tokens": 131072, + "context_length": 1048576, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.9, - "frequency_penalty": null + "temperature": null, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-m2.1/endpoints" + "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1227, + "win_rate": 52.6, + "rank": 12 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1354, + "win_rate": 67, + "rank": 2 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1199, + "win_rate": 48.5, + "rank": 11 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1301, + "win_rate": 59.9, + "rank": 1 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1377, + "win_rate": 70.2, + "rank": 1 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1322, + "win_rate": 62.3, + "rank": 1 + }, { "arena": "models", "category": "3d", - "elo": 1243, - "win_rate": 57.5, - "rank": 33 + "elo": 1451, + "win_rate": 69.1, + "rank": 1 }, { "arena": "models", "category": "codecategories", - "elo": 1240, - "win_rate": 55.3, - "rank": 33 + "elo": 1404, + "win_rate": 65.9, + "rank": 1 }, { "arena": "models", "category": "dataviz", - "elo": 1250, - "win_rate": 57, - "rank": 29 + "elo": 1374, + "win_rate": 63.5, + "rank": 1 }, { "arena": "models", "category": "gamedev", - "elo": 1200, - "win_rate": 50.4, - "rank": 50 + "elo": 1432, + "win_rate": 65, + "rank": 1 }, { "arena": "models", "category": "svg", - "elo": 1189, - "win_rate": 55.4, - "rank": 36 + "elo": 1339, + "win_rate": 64.1, + "rank": 3 }, { "arena": "models", "category": "uicomponent", - "elo": 1276, - "win_rate": 60.9, - "rank": 24 + "elo": 1385, + "win_rate": 63.1, + "rank": 1 }, { "arena": "models", "category": "website", - "elo": 1244, - "win_rate": 55.4, - "rank": 32 + "elo": 1370, + "win_rate": 63.2, + "rank": 1 } - ] + ], + "artificial_analysis": { + "intelligence_index": 59.7, + "coding_index": 76.2, + "agentic_index": 54.3 + } }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "high", "low"], + "default_effort": "max" } }, { - "id": "minimax/minimax-m2.5", - "canonical_slug": "minimax/minimax-m2.5-20260211", - "hugging_face_id": "MiniMaxAI/MiniMax-M2.5", - "name": "MiniMax: MiniMax M2.5", - "created": 1770908502, - "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", - "context_length": 204800, + "id": "morph/morph-v3-fast", + "canonical_slug": "morph/morph-v3-fast", + "hugging_face_id": "", + "name": "Morph: Morph V3 Fast", + "created": 1751910002, + "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}...", + "context_length": 81920, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -9543,149 +17128,106 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000012", - "completion": "0.00000048" + "prompt": "0.0000008", + "completion": "0.0000012" + }, + "top_provider": { + "context_length": 81920, + "max_completion_tokens": 38000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": ["max_tokens", "stop", "temperature"], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/morph/morph-v3-fast/endpoints" + } + }, + { + "id": "morph/morph-v3-large", + "canonical_slug": "morph/morph-v3-large", + "hugging_face_id": "", + "name": "Morph: Morph V3 Large", + "created": 1751910858, + "description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}...", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000009", + "completion": "0.0000019" }, "top_provider": { - "context_length": 196608, - "max_completion_tokens": 196608, + "context_length": 262144, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", - "parallel_tool_calls", - "presence_penalty", - "reasoning", - "reasoning_effort", - "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" + "top_logprobs" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-m2.5-20260211/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1247, - "win_rate": 57.6, - "rank": 32 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1256, - "win_rate": 56.8, - "rank": 30 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1215, - "win_rate": 51.2, - "rank": 41 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1242, - "win_rate": 55.5, - "rank": 34 - }, - { - "arena": "models", - "category": "svg", - "elo": 1208, - "win_rate": 54.5, - "rank": 27 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1226, - "win_rate": 53.4, - "rank": 38 - }, - { - "arena": "models", - "category": "website", - "elo": 1264, - "win_rate": 57.5, - "rank": 27 - } - ] - }, - "reasoning": { - "mandatory": true + "details": "/api/v1/models/morph/morph-v3-large/endpoints" } }, { - "id": "minimax/minimax-m2.7", - "canonical_slug": "minimax/minimax-m2.7-20260318", - "hugging_face_id": "MiniMaxAI/MiniMax-M2.7", - "name": "MiniMax: MiniMax M2.7", - "created": 1773836697, - "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...", - "context_length": 204800, + "id": "nex-agi/nex-n2-mini", + "canonical_slug": "nex-agi/nex-n2-mini", + "hugging_face_id": "nex-agi/Nex-N2-Mini", + "name": "Nex AGI: Nex-N2-Mini", + "created": 1782312964, + "description": "Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000012", - "input_cache_read": "0.00000006", - "input_cache_write": "0.000000375" + "prompt": "0.000000025", + "completion": "0.0000001", + "input_cache_read": "0.0000000025" }, "top_provider": { - "context_length": 204800, - "max_completion_tokens": 196608, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", - "stop", "structured_outputs", "temperature", "tool_choice", @@ -9695,9 +17237,9 @@ "top_p" ], "default_parameters": { - "temperature": 1, + "temperature": 0.7, "top_p": 0.95, - "top_k": null, + "top_k": 40, "frequency_penalty": null, "presence_penalty": null, "repetition_penalty": null @@ -9706,117 +17248,44 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/minimax/minimax-m2.7-20260318/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1267, - "win_rate": 51, - "rank": 27 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1186, - "win_rate": 48, - "rank": 31 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1281, - "win_rate": 53.3, - "rank": 23 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1271, - "win_rate": 53.2, - "rank": 20 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1273, - "win_rate": 53.3, - "rank": 23 - }, - { - "arena": "models", - "category": "svg", - "elo": 1195, - "win_rate": 50.5, - "rank": 34 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1260, - "win_rate": 49.8, - "rank": 28 - }, - { - "arena": "models", - "category": "website", - "elo": 1287, - "win_rate": 54.3, - "rank": 21 - } - ], - "artificial_analysis": { - "intelligence_index": 38.1, - "coding_index": 52.6, - "agentic_index": 25.6 - } + "details": "/api/v1/models/nex-agi/nex-n2-mini/endpoints" }, "reasoning": { - "mandatory": true + "mandatory": false } }, { - "id": "minimax/minimax-m3", - "canonical_slug": "minimax/minimax-m3-20260531", - "hugging_face_id": "MiniMaxAI/Minimax-M3", - "name": "MiniMax: MiniMax M3", - "created": 1780245374, - "description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...", - "context_length": 1000000, + "id": "nex-agi/nex-n2-pro", + "canonical_slug": "nex-agi/nex-n2-pro", + "hugging_face_id": "nex-agi/Nex-N2-Pro", + "name": "Nex AGI: Nex-N2-Pro", + "created": 1780937140, + "description": "Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...", + "context_length": 262144, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.0000024", - "input_cache_read": "0.00000012" + "prompt": "0.00000025", + "completion": "0.000001", + "input_cache_read": "0.000000025" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 512000, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -9825,96 +17294,82 @@ "top_p" ], "default_parameters": { - "temperature": 1, + "temperature": 0.7, "top_p": 0.95, - "top_k": null, + "top_k": 40, "frequency_penalty": null, "presence_penalty": null, "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "androidnative", - "elo": 1045, - "win_rate": 25.4, - "rank": 26 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1267, - "win_rate": 58, - "rank": 2 - }, + "expiration_date": null, + "links": { + "details": "/api/v1/models/nex-agi/nex-n2-pro/endpoints" + }, + "benchmarks": { + "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1305, - "win_rate": 56.5, - "rank": 18 + "elo": 1304, + "win_rate": 53, + "rank": 19 }, { "arena": "models", "category": "asciiart", - "elo": 1221, - "win_rate": 49.8, - "rank": 15 + "elo": 1133, + "win_rate": 37.7, + "rank": 48 }, { "arena": "models", "category": "codecategories", - "elo": 1305, - "win_rate": 55.6, - "rank": 14 + "elo": 1253, + "win_rate": 48.8, + "rank": 35 }, { "arena": "models", "category": "dataviz", - "elo": 1291, - "win_rate": 56.7, - "rank": 11 + "elo": 1259, + "win_rate": 50.1, + "rank": 26 }, { "arena": "models", "category": "gamedev", - "elo": 1288, - "win_rate": 51.7, - "rank": 20 + "elo": 1258, + "win_rate": 49.2, + "rank": 30 }, { "arena": "models", "category": "svg", - "elo": 1244, - "win_rate": 54.4, + "elo": 1231, + "win_rate": 51.2, "rank": 16 }, { "arena": "models", "category": "uicomponent", - "elo": 1295, - "win_rate": 54.1, - "rank": 17 + "elo": 1250, + "win_rate": 47.9, + "rank": 37 }, { "arena": "models", "category": "website", - "elo": 1303, - "win_rate": 55.6, - "rank": 13 + "elo": 1234, + "win_rate": 46.7, + "rank": 40 } ], "artificial_analysis": { - "intelligence_index": 44.4, - "coding_index": 58.6, - "agentic_index": 35.4 + "intelligence_index": null, + "coding_index": 59.1, + "agentic_index": null } }, "reasoning": { @@ -9922,281 +17377,232 @@ } }, { - "id": "mistralai/codestral-2508", - "canonical_slug": "mistralai/codestral-2508", - "hugging_face_id": "", - "name": "Mistral: Codestral 2508", - "created": 1754079630, - "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)", - "context_length": 256000, + "id": "nousresearch/hermes-3-llama-3.1-405b", + "canonical_slug": "nousresearch/hermes-3-llama-3.1-405b", + "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-405B", + "name": "Nous: Hermes 3 405B Instruct", + "created": 1723766400, + "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", + "context_length": 131072, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null + "tokenizer": "Llama3", + "instruct_type": "chatml" }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000009", - "input_cache_read": "0.00000003" + "prompt": "0.000001", + "completion": "0.000001" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": null, + "context_length": 131072, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", + "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": 0.3 - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": "2023-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/codestral-2508/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1056, - "win_rate": 38.5, - "rank": 90 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1061, - "win_rate": 41.7, - "rank": 85 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1032, - "win_rate": 36.2, - "rank": 92 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1071, - "win_rate": 46.9, - "rank": 79 - }, - { - "arena": "models", - "category": "website", - "elo": 1055, - "win_rate": 37.8, - "rank": 93 - }, - { - "arena": "models", - "category": "3d", - "elo": 1098, - "win_rate": 45.5, - "rank": 77 - } - ] + "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" } }, { - "id": "mistralai/devstral-2512", - "canonical_slug": "mistralai/devstral-2512", - "hugging_face_id": "mistralai/Devstral-2-123B-Instruct-2512", - "name": "Mistral: Devstral 2 2512", - "created": 1765285419, - "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...", - "context_length": 262144, + "id": "nousresearch/hermes-3-llama-3.1-70b", + "canonical_slug": "nousresearch/hermes-3-llama-3.1-70b", + "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-70B", + "name": "Nous: Hermes 3 70B Instruct", + "created": 1723939200, + "description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", + "context_length": 131072, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": null + "tokenizer": "Llama3", + "instruct_type": "chatml" }, "pricing": { - "prompt": "0.0000004", - "completion": "0.000002", - "input_cache_read": "0.00000004" + "prompt": "0.0000007", + "completion": "0.0000007" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, + "context_length": 131072, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", + "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": 0.3, - "top_p": null, - "frequency_penalty": null + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints" + } + }, + { + "id": "nousresearch/hermes-4-405b", + "canonical_slug": "nousresearch/hermes-4-405b", + "hugging_face_id": "NousResearch/Hermes-4-405B", + "name": "Nous: Hermes 4 405B", + "created": 1756235463, + "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000003" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "temperature", + "top_k", + "top_p" + ], + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/devstral-2512/endpoints" + "details": "/api/v1/models/nousresearch/hermes-4-405b/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 19.2, - "coding_index": 31.3, - "agentic_index": 10.6 - } + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/ministral-14b-2512", - "canonical_slug": "mistralai/ministral-14b-2512", - "hugging_face_id": "mistralai/Ministral-3-14B-Instruct-2512", - "name": "Mistral: Ministral 3 14B 2512", - "created": 1764681735, - "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...", - "context_length": 262144, + "id": "nousresearch/hermes-4-70b", + "canonical_slug": "nousresearch/hermes-4-70b", + "hugging_face_id": "NousResearch/Hermes-4-70B", + "name": "Nous: Hermes 4 70B", + "created": 1756236182, + "description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...", + "context_length": 131072, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Llama3", "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.0000002", - "input_cache_read": "0.00000002" + "prompt": "0.00000013", + "completion": "0.0000004" }, "top_provider": { - "context_length": 262144, + "context_length": 131072, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", - "seed", - "stop", - "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_logprobs", + "top_k", "top_p" ], - "default_parameters": { - "temperature": 0.3, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/ministral-14b-2512/endpoints" + "details": "/api/v1/models/nousresearch/hermes-4-70b/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1068, - "win_rate": 39.6, - "rank": 82 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1114, - "win_rate": 44, - "rank": 79 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1104, - "win_rate": 43.6, - "rank": 78 - }, - { - "arena": "models", - "category": "website", - "elo": 1124, - "win_rate": 44.8, - "rank": 80 - } - ], - "artificial_analysis": { - "intelligence_index": 11.1, - "coding_index": 14.4, - "agentic_index": 2.2 - } + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/ministral-3b-2512", - "canonical_slug": "mistralai/ministral-3b-2512", - "hugging_face_id": "mistralai/Ministral-3-3B-Instruct-2512", - "name": "Mistral: Ministral 3 3B 2512", - "created": 1764681560, - "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", - "context_length": 131072, + "id": "nvidia/nemotron-3-nano-30b-a3b", + "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", + "name": "NVIDIA: Nemotron 3 Nano 30B A3B", + "created": 1765731275, + "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000001", - "input_cache_read": "0.00000001" + "prompt": "0.00000005", + "completion": "0.0000002", + "input_cache_read": "0.000000025" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 262144, + "max_completion_tokens": 228000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", @@ -10205,11 +17611,12 @@ "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.3, + "temperature": null, "top_p": null, "frequency_penalty": null }, @@ -10217,90 +17624,57 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/ministral-3b-2512/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1040, - "win_rate": 35.9, - "rank": 88 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1059, - "win_rate": 37.3, - "rank": 89 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1014, - "win_rate": 33, - "rank": 97 - }, - { - "arena": "models", - "category": "website", - "elo": 1070, - "win_rate": 38.2, - "rank": 90 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 6.8, - "coding_index": 4.8, - "agentic_index": 1.6 + "intelligence_index": 14.5, + "coding_index": 14.4, + "agentic_index": 2 } + }, + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/ministral-8b-2512", - "canonical_slug": "mistralai/ministral-8b-2512", - "hugging_face_id": "mistralai/Ministral-3-8B-Instruct-2512", - "name": "Mistral: Ministral 3 8B 2512", - "created": 1764681654, - "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", - "context_length": 262144, + "id": "nvidia/nemotron-3-nano-30b-a3b:free", + "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", + "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", + "created": 1765731275, + "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", + "context_length": 256000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.00000015", - "input_cache_read": "0.000000015" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 262144, + "context_length": 256000, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", - "repetition_penalty", - "response_format", + "reasoning", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.3, + "temperature": null, "top_p": null, "frequency_penalty": null }, @@ -10308,125 +17682,119 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/ministral-8b-2512/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1109, - "win_rate": 46.2, - "rank": 76 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1102, - "win_rate": 42.9, - "rank": 81 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1056, - "win_rate": 38.7, - "rank": 86 - }, - { - "arena": "models", - "category": "website", - "elo": 1108, - "win_rate": 42.9, - "rank": 82 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 9, - "coding_index": 9.7, - "agentic_index": 1.2 + "intelligence_index": 14.5, + "coding_index": 14.4, + "agentic_index": 2 } + }, + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/mistral-large", - "canonical_slug": "mistralai/mistral-large", - "hugging_face_id": null, - "name": "Mistral Large", - "created": 1708905600, - "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", - "context_length": 128000, + "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", + "canonical_slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428", + "hugging_face_id": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", + "name": "NVIDIA: Nemotron 3 Nano Omni (free)", + "created": 1777393095, + "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...", + "context_length": 256000, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text+image+audio+video->text", + "input_modalities": ["text", "audio", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000006", - "input_cache_read": "0.0000002" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": null, + "context_length": 256000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", - "response_format", + "reasoning", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": 0.6, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-11-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-large/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 13.8, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true } }, { - "id": "mistralai/mistral-large-2407", - "canonical_slug": "mistralai/mistral-large-2407", - "hugging_face_id": "", - "name": "Mistral Large 2407", - "created": 1731978415, - "description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", - "context_length": 131072, + "id": "nvidia/nemotron-3-super-120b-a12b", + "canonical_slug": "nvidia/nemotron-3-super-120b-a12b-20230311", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", + "name": "NVIDIA: Nemotron 3 Super", + "created": 1773245239, + "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", + "context_length": 1000000, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000006", - "input_cache_read": "0.0000002" + "prompt": "0.000000085", + "completion": "0.0000004" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 262144, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", "seed", "stop", @@ -10434,51 +17802,72 @@ "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-large-2407/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 25.7, + "coding_index": 37.7, + "agentic_index": 8.8 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true, + "supported_efforts": ["medium", "low"], + "default_effort": "medium" } }, { - "id": "mistralai/mistral-large-2512", - "canonical_slug": "mistralai/mistral-large-2512", - "hugging_face_id": "", - "name": "Mistral: Mistral Large 3 2512", - "created": 1764624472, - "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", + "id": "nvidia/nemotron-3-super-120b-a12b:free", + "canonical_slug": "nvidia/nemotron-3-super-120b-a12b-20230311", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", + "name": "NVIDIA: Nemotron 3 Super (free)", + "created": 1773245239, + "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", "context_length": 262144, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.0000015", - "input_cache_read": "0.00000005" + "prompt": "0", + "completion": "0" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": null, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", "temperature", "tool_choice", @@ -10486,112 +17875,71 @@ "top_p" ], "default_parameters": { - "temperature": 0.0645, - "top_p": null, - "frequency_penalty": null + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-large-2512/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1177, - "win_rate": 46.9, - "rank": 52 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1115, - "win_rate": 40.3, - "rank": 44 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1191, - "win_rate": 47.6, - "rank": 57 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1180, - "win_rate": 45.8, - "rank": 56 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1146, - "win_rate": 41.5, - "rank": 66 - }, - { - "arena": "models", - "category": "svg", - "elo": 1050, - "win_rate": 38, - "rank": 64 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1155, - "win_rate": 43.1, - "rank": 60 - }, - { - "arena": "models", - "category": "website", - "elo": 1204, - "win_rate": 49.4, - "rank": 55 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 15.9, - "coding_index": 20.1, - "agentic_index": 5.5 + "intelligence_index": 25.7, + "coding_index": 37.7, + "agentic_index": 8.8 } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true, + "supported_efforts": ["medium", "low"], + "default_effort": "medium" } }, { - "id": "mistralai/mistral-medium-3", - "canonical_slug": "mistralai/mistral-medium-3", - "hugging_face_id": "", - "name": "Mistral: Mistral Medium 3", - "created": 1746627341, - "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...", - "context_length": 131072, + "id": "nvidia/nemotron-3-ultra-550b-a55b", + "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "name": "NVIDIA: Nemotron 3 Ultra", + "created": 1780551208, + "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", + "context_length": 512288, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.000002", - "input_cache_read": "0.00000004" + "prompt": "0.0000006", + "completion": "0.0000036", + "input_cache_read": "0.0000002" }, "top_provider": { - "context_length": 131072, + "context_length": 512288, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", "seed", "stop", @@ -10599,85 +17947,118 @@ "temperature", "tool_choice", "tools", + "top_k", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-medium-3/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1160, - "win_rate": 54.6, - "rank": 58 + "elo": 1186, + "win_rate": 41.1, + "rank": 55 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1108, + "win_rate": 36.8, + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1118, - "win_rate": 48.1, - "rank": 78 + "elo": 1149, + "win_rate": 36, + "rank": 75 }, { "arena": "models", "category": "dataviz", - "elo": 1075, - "win_rate": 45.7, - "rank": 82 + "elo": 1151, + "win_rate": 37.4, + "rank": 72 }, { "arena": "models", "category": "gamedev", - "elo": 1084, - "win_rate": 45.3, - "rank": 82 + "elo": 1160, + "win_rate": 37, + "rank": 68 + }, + { + "arena": "models", + "category": "svg", + "elo": 1114, + "win_rate": 37.4, + "rank": 52 }, { "arena": "models", "category": "uicomponent", - "elo": 1081, - "win_rate": 50, - "rank": 77 + "elo": 1170, + "win_rate": 38.3, + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1122, - "win_rate": 47.7, - "rank": 81 + "elo": 1129, + "win_rate": 33.5, + "rank": 85 } - ] + ], + "artificial_analysis": { + "intelligence_index": 38.3, + "coding_index": 49.3, + "agentic_index": 27.5 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true, + "supported_efforts": ["high", "medium"], + "default_effort": "high" } }, { - "id": "mistralai/mistral-medium-3-5", - "canonical_slug": "mistralai/mistral-medium-3.5-20260430", - "hugging_face_id": null, - "name": "Mistral: Mistral Medium 3.5", - "created": 1777570439, - "description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...", - "context_length": 262144, + "id": "nvidia/nemotron-3-ultra-550b-a55b:batch", + "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "name": "NVIDIA: Nemotron 3 Ultra (batch)", + "created": 1780551208, + "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", + "context_length": 512288, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000015", - "completion": "0.0000075" + "prompt": "0.0000003", + "completion": "0.0000018", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 262144, + "context_length": 512288, "max_completion_tokens": null, "is_moderated": false }, @@ -10685,21 +18066,25 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, + "temperature": 1, + "top_p": 0.95, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -10709,220 +18094,292 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1186, + "win_rate": 41.1, + "rank": 55 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1108, + "win_rate": 36.8, + "rank": 51 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1149, + "win_rate": 36, + "rank": 75 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1151, + "win_rate": 37.4, + "rank": 72 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1160, + "win_rate": 37, + "rank": 68 + }, + { + "arena": "models", + "category": "svg", + "elo": 1114, + "win_rate": 37.4, + "rank": 52 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1170, + "win_rate": 38.3, + "rank": 65 + }, + { + "arena": "models", + "category": "website", + "elo": 1129, + "win_rate": 33.5, + "rank": 85 + } + ], "artificial_analysis": { - "intelligence_index": 29.9, - "coding_index": 46.9, - "agentic_index": 19 + "intelligence_index": 38.3, + "coding_index": 49.3, + "agentic_index": 27.5 } }, "reasoning": { "mandatory": false, - "supported_efforts": ["high", "none"], + "default_enabled": true, + "supports_max_tokens": true, + "supported_efforts": ["high", "medium"], "default_effort": "high" } }, { - "id": "mistralai/mistral-medium-3.1", - "canonical_slug": "mistralai/mistral-medium-3.1", - "hugging_face_id": "", - "name": "Mistral: Mistral Medium 3.1", - "created": 1755095639, - "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...", - "context_length": 131072, + "id": "nvidia/nemotron-3-ultra-550b-a55b:free", + "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "name": "NVIDIA: Nemotron 3 Ultra (free)", + "created": 1780551208, + "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", + "context_length": 1000000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.000002", - "input_cache_read": "0.00000004" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", + "include_reasoning", "max_tokens", - "presence_penalty", - "response_format", + "reasoning", + "reasoning_effort", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-medium-3.1/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1159, - "win_rate": 44.7, - "rank": 59 + "elo": 1186, + "win_rate": 41.1, + "rank": 55 }, { "arena": "models", "category": "asciiart", - "elo": 1044, - "win_rate": 30.8, - "rank": 48 + "elo": 1108, + "win_rate": 36.8, + "rank": 51 }, { "arena": "models", "category": "codecategories", - "elo": 1170, - "win_rate": 45.1, - "rank": 62 + "elo": 1149, + "win_rate": 36, + "rank": 75 }, { "arena": "models", "category": "dataviz", - "elo": 1191, - "win_rate": 47.6, - "rank": 53 + "elo": 1151, + "win_rate": 37.4, + "rank": 72 }, { "arena": "models", "category": "gamedev", - "elo": 1139, - "win_rate": 40.7, - "rank": 70 + "elo": 1160, + "win_rate": 37, + "rank": 68 }, { "arena": "models", "category": "svg", - "elo": 1050, - "win_rate": 38.2, - "rank": 65 + "elo": 1114, + "win_rate": 37.4, + "rank": 52 }, { "arena": "models", "category": "uicomponent", - "elo": 1152, - "win_rate": 43.5, - "rank": 62 + "elo": 1170, + "win_rate": 38.3, + "rank": 65 }, { "arena": "models", "category": "website", - "elo": 1175, - "win_rate": 46, - "rank": 62 + "elo": 1129, + "win_rate": 33.5, + "rank": 85 } ], "artificial_analysis": { - "intelligence_index": 14.7, - "coding_index": 20.5, - "agentic_index": 6.2 + "intelligence_index": 38.3, + "coding_index": 49.3, + "agentic_index": 27.5 } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supports_max_tokens": true, + "supported_efforts": ["high", "medium"], + "default_effort": "high" } }, { - "id": "mistralai/mistral-nemo", - "canonical_slug": "mistralai/mistral-nemo", - "hugging_face_id": "mistralai/Mistral-Nemo-Instruct-2407", - "name": "Mistral: Mistral Nemo", - "created": 1721347200, - "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...", - "context_length": 131072, + "id": "nvidia/nemotron-3.5-content-safety:free", + "canonical_slug": "nvidia/nemotron-3.5-content-safety-20260604", + "hugging_face_id": "nvidia/Nemotron-3.5-Content-Safety", + "name": "NVIDIA: Nemotron 3.5 Content Safety (free)", + "created": 1780581864, + "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": "mistral" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000002", - "completion": "0.00000003" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 128000, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", + "reasoning", "seed", - "stop", - "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-04-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-nemo/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true } }, { - "id": "mistralai/mistral-saba", - "canonical_slug": "mistralai/mistral-saba-2502", - "hugging_face_id": "", - "name": "Mistral: Saba", - "created": 1739803239, - "description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...", - "context_length": 32768, + "id": "nvidia/nemotron-3.5-lightning", + "canonical_slug": "nvidia/nemotron-3.5-lightning-20260807", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "name": "NVIDIA: Nemotron 3.5 Lightning", + "created": 1786452751, + "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...", + "context_length": 1000000, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.0000006", - "input_cache_read": "0.00000002" + "prompt": "0.0000001", + "completion": "0.00000025", + "input_cache_read": "0.00000005" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": null, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", + "repetition_penalty", "response_format", "seed", "stop", @@ -10930,214 +18387,208 @@ "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.3 - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-09-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-saba-2502/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 23.6, + "coding_index": 26.8, + "agentic_index": 13.8 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/mistral-small-24b-instruct-2501", - "canonical_slug": "mistralai/mistral-small-24b-instruct-2501", - "hugging_face_id": "mistralai/Mistral-Small-24B-Instruct-2501", - "name": "Mistral: Mistral Small 3", - "created": 1738255409, - "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...", - "context_length": 32768, + "id": "nvidia/nemotron-3.5-lightning:free", + "canonical_slug": "nvidia/nemotron-3.5-lightning-20260807", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "name": "NVIDIA: Nemotron 3.5 Lightning (free)", + "created": 1786452751, + "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...", + "context_length": 1000000, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.00000008" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": 16384, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", - "response_format", + "reasoning", "seed", - "stop", - "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", "top_p" ], - "default_parameters": { - "temperature": 0.3, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints" + "details": "/api/v1/models/nvidia/nemotron-3.5-lightning-20260807/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 23.6, + "coding_index": 26.8, + "agentic_index": 13.8 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "mistralai/mistral-small-2603", - "canonical_slug": "mistralai/mistral-small-2603", - "hugging_face_id": "mistralai/Mistral-Small-4-119B-2603", - "name": "Mistral: Mistral Small 4", - "created": 1773695685, - "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...", - "context_length": 262144, + "id": "nvidia/nemotron-nano-12b-v2-vl:free", + "canonical_slug": "nvidia/nemotron-nano-12b-v2-vl", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", + "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)", + "created": 1761675565, + "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...", + "context_length": 128000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["image", "text", "video"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000015" + "prompt": "0", + "completion": "0" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, + "context_length": 128000, + "max_completion_tokens": 128000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", "max_tokens", - "presence_penalty", "reasoning", - "response_format", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-small-2603/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 19.6, - "coding_index": 26.6, - "agentic_index": 4.7 - } + "details": "/api/v1/models/nvidia/nemotron-nano-12b-v2-vl/endpoints" }, "reasoning": { - "mandatory": false, - "default_enabled": false, - "supported_efforts": ["high", "none"], - "default_effort": "high" + "mandatory": false } }, { - "id": "mistralai/mistral-small-3.1-24b-instruct", - "canonical_slug": "mistralai/mistral-small-3.1-24b-instruct-2503", - "hugging_face_id": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", - "name": "Mistral: Mistral Small 3.1 24B", - "created": 1742238937, - "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...", + "id": "nvidia/nemotron-nano-9b-v2:free", + "canonical_slug": "nvidia/nemotron-nano-9b-v2", + "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", + "name": "NVIDIA: Nemotron Nano 9B V2 (free)", + "created": 1757106807, + "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", "context_length": 128000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000000351", - "completion": "0.000000555" + "prompt": "0", + "completion": "0" }, "top_provider": { "context_length": 128000, - "max_completion_tokens": 128000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", + "response_format", "seed", - "stop", + "structured_outputs", "temperature", - "top_k", - "top_logprobs", + "tool_choice", + "tools", "top_p" ], "default_parameters": { - "temperature": 0.3 + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints" - } - }, - { - "id": "mistralai/mistral-small-3.2-24b-instruct", - "canonical_slug": "mistralai/mistral-small-3.2-24b-instruct-2506", - "hugging_face_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", - "name": "Mistral: Mistral Small 3.2 24B", - "created": 1750443016, - "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...", - "context_length": 128000, + "details": "/api/v1/models/nvidia/nemotron-nano-9b-v2/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "openai/gpt-3.5-turbo", + "canonical_slug": "openai/gpt-3.5-turbo", + "hugging_face_id": null, + "name": "OpenAI: GPT-3.5 Turbo", + "created": 1685232000, + "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", + "context_length": 16385, "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000000075", - "completion": "0.0000002" + "prompt": "0.0000005", + "completion": "0.0000015" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 16385, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -11145,9 +18596,7 @@ "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", @@ -11155,88 +18604,55 @@ "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.3 - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints" + "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 956, - "win_rate": 39.8, - "rank": 102 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 971, - "win_rate": 43.3, - "rank": 94 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 954, - "win_rate": 39.4, - "rank": 101 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 961, - "win_rate": 40.5, - "rank": 94 - }, - { - "arena": "models", - "category": "website", - "elo": 938, - "win_rate": 38.3, - "rank": 105 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 10.7, + "agentic_index": null + } } }, { - "id": "mistralai/mixtral-8x22b-instruct", - "canonical_slug": "mistralai/mixtral-8x22b-instruct", - "hugging_face_id": "mistralai/Mixtral-8x22B-Instruct-v0.1", - "name": "Mistral: Mixtral 8x22B Instruct", - "created": 1713312000, - "description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...", - "context_length": 65536, + "id": "openai/gpt-3.5-turbo-0613", + "canonical_slug": "openai/gpt-3.5-turbo-0613", + "hugging_face_id": null, + "name": "OpenAI: GPT-3.5 Turbo (older v0613)", + "created": 1706140800, + "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", + "context_length": 4095, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": "mistral" + "tokenizer": "GPT", + "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000006", - "input_cache_read": "0.0000002" + "prompt": "0.000001", + "completion": "0.000002" }, "top_provider": { - "context_length": 65536, - "max_completion_tokens": null, + "context_length": 4095, + "max_completion_tokens": 4096, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "max_tokens", + "logit_bias", + "logprobs", + "max_completion_tokens", "presence_penalty", "response_format", "seed", @@ -11245,47 +18661,47 @@ "temperature", "tool_choice", "tools", + "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.3 - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-01-31", + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints" + "details": "/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints" } }, { - "id": "mistralai/voxtral-small-24b-2507", - "canonical_slug": "mistralai/voxtral-small-24b-2507", - "hugging_face_id": "mistralai/Voxtral-Small-24B-2507", - "name": "Mistral: Voxtral Small 24B 2507", - "created": 1761835144, - "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...", - "context_length": 32000, + "id": "openai/gpt-3.5-turbo-16k", + "canonical_slug": "openai/gpt-3.5-turbo-16k", + "hugging_face_id": null, + "name": "OpenAI: GPT-3.5 Turbo 16k", + "created": 1693180800, + "description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...", + "context_length": 16385, "architecture": { - "modality": "text+file+audio->text", - "input_modalities": ["text", "audio", "file"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000003", - "audio": "0.0001", - "input_cache_read": "0.00000001" + "prompt": "0.000003", + "completion": "0.000004" }, "top_provider": { - "context_length": 32000, - "max_completion_tokens": null, + "context_length": 16385, + "max_completion_tokens": 4096, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", @@ -11295,135 +18711,96 @@ "temperature", "tool_choice", "tools", + "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.2, - "top_p": 0.95, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints" + "details": "/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints" } }, { - "id": "moonshotai/kimi-k2", - "canonical_slug": "moonshotai/kimi-k2", - "hugging_face_id": "moonshotai/Kimi-K2-Instruct", - "name": "MoonshotAI: Kimi K2 0711", - "created": 1752263252, - "description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...", - "context_length": 131072, + "id": "openai/gpt-3.5-turbo-instruct", + "canonical_slug": "openai/gpt-3.5-turbo-instruct", + "hugging_face_id": null, + "name": "OpenAI: GPT-3.5 Turbo Instruct", + "created": 1695859200, + "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.", + "context_length": 4095, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null + "tokenizer": "GPT", + "instruct_type": "chatml" }, "pricing": { - "prompt": "0.00000057", - "completion": "0.0000023" + "prompt": "0.0000015", + "completion": "0.000002" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 100352, - "is_moderated": false + "context_length": 4095, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", "presence_penalty", - "repetition_penalty", + "response_format", "seed", "stop", + "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-12-31", + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/moonshotai/kimi-k2/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1083, - "win_rate": 51.7, - "rank": 83 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1062, - "win_rate": 49.4, - "rank": 84 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1040, - "win_rate": 46.4, - "rank": 90 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1085, - "win_rate": 55.1, - "rank": 76 - }, - { - "arena": "models", - "category": "website", - "elo": 1093, - "win_rate": 53.1, - "rank": 86 - } - ] - } - }, - { - "id": "moonshotai/kimi-k2-0905", - "canonical_slug": "moonshotai/kimi-k2-0905", - "hugging_face_id": "moonshotai/Kimi-K2-Instruct-0905", - "name": "MoonshotAI: Kimi K2 0905", - "created": 1757021147, - "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...", - "context_length": 262144, + "details": "/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints" + } + }, + { + "id": "openai/gpt-3.5-turbo:batch", + "canonical_slug": "openai/gpt-3.5-turbo", + "hugging_face_id": null, + "name": "OpenAI: GPT-3.5 Turbo (batch)", + "created": 1685232000, + "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", + "context_length": 16385, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.0000025" + "prompt": "0.00000025", + "completion": "0.00000075", + "web_search": "0.01" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 100352, - "is_moderated": false + "context_length": 16385, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", @@ -11431,69 +18808,57 @@ "temperature", "tool_choice", "tools", - "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-12-31", + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/moonshotai/kimi-k2-0905/endpoints" + "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1147, - "win_rate": 48.5, - "rank": 72 - }, - { - "arena": "models", - "category": "website", - "elo": 1150, - "win_rate": 48.3, - "rank": 73 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 10.7, + "agentic_index": null + } } }, { - "id": "moonshotai/kimi-k2-thinking", - "canonical_slug": "moonshotai/kimi-k2-thinking-20251106", - "hugging_face_id": "moonshotai/Kimi-K2-Thinking", - "name": "MoonshotAI: Kimi K2 Thinking", - "created": 1762440622, - "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...", - "context_length": 262144, + "id": "openai/gpt-4", + "canonical_slug": "openai/gpt-4", + "hugging_face_id": null, + "name": "OpenAI: GPT-4", + "created": 1685232000, + "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...", + "context_length": 8191, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.0000025", - "input_cache_read": "0.00000015" + "prompt": "0.00003", + "completion": "0.00006" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 100352, - "is_moderated": false + "context_length": 8191, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", + "logit_bias", "logprobs", + "max_completion_tokens", "max_tokens", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -11501,77 +18866,56 @@ "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2021-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints" + "details": "/api/v1/models/openai/gpt-4/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "website", - "elo": 1156, - "win_rate": 48.8, - "rank": 71 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 17.3, - "coding_index": 21, - "agentic_index": 1.8 + "intelligence_index": null, + "coding_index": 13.1, + "agentic_index": null } - }, - "reasoning": { - "mandatory": true } }, { - "id": "moonshotai/kimi-k2.5", - "canonical_slug": "moonshotai/kimi-k2.5-0127", - "hugging_face_id": "moonshotai/Kimi-K2.5", - "name": "MoonshotAI: Kimi K2.5", - "created": 1769487076, - "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...", - "context_length": 262144, + "id": "openai/gpt-4-turbo", + "canonical_slug": "openai/gpt-4-turbo", + "hugging_face_id": null, + "name": "OpenAI: GPT-4 Turbo", + "created": 1712620800, + "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", + "context_length": 128000, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000000375", - "completion": "0.000002025", - "input_cache_read": "0.000000203" + "prompt": "0.00001", + "completion": "0.00003" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -11579,161 +18923,106 @@ "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "androidnative", - "elo": 1131, - "win_rate": 57.9, - "rank": 17 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1180, - "win_rate": 54.2, - "rank": 14 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1256, - "win_rate": 59.5, - "rank": 2 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1182, - "win_rate": 49.3, - "rank": 21 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1196, - "win_rate": 50.3, - "rank": 14 - }, - { - "arena": "models", - "category": "3d", - "elo": 1285, - "win_rate": 53.9, - "rank": 23 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1212, - "win_rate": 46.9, - "rank": 20 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1286, - "win_rate": 54.7, - "rank": 21 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1270, - "win_rate": 52.9, - "rank": 22 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1272, - "win_rate": 53.6, - "rank": 24 - }, - { - "arena": "models", - "category": "svg", - "elo": 1206, - "win_rate": 49.4, - "rank": 29 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1290, - "win_rate": 54.3, - "rank": 20 - }, - { - "arena": "models", - "category": "website", - "elo": 1292, - "win_rate": 55.9, - "rank": 17 - } - ] + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" }, - "reasoning": { - "mandatory": false, - "default_enabled": true + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 21.5, + "agentic_index": null + } } }, { - "id": "moonshotai/kimi-k2.6", - "canonical_slug": "moonshotai/kimi-k2.6-20260420", - "hugging_face_id": "moonshotai/Kimi-K2.6", - "name": "MoonshotAI: Kimi K2.6", - "created": 1776699402, - "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...", - "context_length": 262144, + "id": "openai/gpt-4-turbo-preview", + "canonical_slug": "openai/gpt-4-turbo-preview", + "hugging_face_id": null, + "name": "OpenAI: GPT-4 Turbo Preview", + "created": 1706140800, + "description": "The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...", + "context_length": 128000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00001", + "completion": "0.00003" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-4-turbo-preview/endpoints" + } + }, + { + "id": "openai/gpt-4-turbo:batch", + "canonical_slug": "openai/gpt-4-turbo", + "hugging_face_id": null, + "name": "OpenAI: GPT-4 Turbo (batch)", + "created": 1712620800, + "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", + "context_length": 128000, "architecture": { "modality": "text+image->text", "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000066", - "completion": "0.00000341", - "input_cache_read": "0.00000014" + "prompt": "0.000005", + "completion": "0.000015", + "web_search": "0.01" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logit_bias", "logprobs", "max_tokens", - "min_p", - "parallel_tool_calls", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -11741,935 +19030,1005 @@ "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2023-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints" + "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1176, - "win_rate": 50.2, - "rank": 7 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1248, - "win_rate": 59, - "rank": 2 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1187, - "win_rate": 45.8, - "rank": 5 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1252, - "win_rate": 59.2, - "rank": 2 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1186, - "win_rate": 45.5, - "rank": 5 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1213, - "win_rate": 50.5, - "rank": 12 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1221, - "win_rate": 56.1, - "rank": 10 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1216, - "win_rate": 53.1, - "rank": 9 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1247, - "win_rate": 58.5, - "rank": 2 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1225, - "win_rate": 53.4, - "rank": 9 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1181, - "win_rate": 44.3, - "rank": 5 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1180, - "win_rate": 42.1, - "rank": 7 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1260, - "win_rate": 58.1, - "rank": 7 - }, + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 21.5, + "agentic_index": null + } + } + }, + { + "id": "openai/gpt-4.1", + "canonical_slug": "openai/gpt-4.1-2025-04-14", + "hugging_face_id": "", + "name": "OpenAI: GPT-4.1", + "created": 1744651385, + "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...", + "context_length": 1047576, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000008", + "web_search": "0.01", + "input_cache_read": "0.0000005" + }, + "top_provider": { + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" + }, + "benchmarks": { + "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1353, - "win_rate": 62.3, - "rank": 4 + "elo": 903, + "win_rate": 30.9, + "rank": 108 }, { "arena": "models", "category": "codecategories", - "elo": 1327, - "win_rate": 58, - "rank": 6 + "elo": 1044, + "win_rate": 50.9, + "rank": 100 }, { "arena": "models", "category": "dataviz", - "elo": 1302, - "win_rate": 56.7, - "rank": 8 + "elo": 1125, + "win_rate": 59.5, + "rank": 80 }, { "arena": "models", "category": "gamedev", - "elo": 1316, - "win_rate": 58.1, - "rank": 13 - }, - { - "arena": "models", - "category": "svg", - "elo": 1235, - "win_rate": 52.5, - "rank": 19 + "elo": 1117, + "win_rate": 59.1, + "rank": 84 }, { "arena": "models", "category": "uicomponent", - "elo": 1319, - "win_rate": 57, - "rank": 11 + "elo": 1028, + "win_rate": 49.7, + "rank": 97 }, { "arena": "models", "category": "website", - "elo": 1318, - "win_rate": 56.4, - "rank": 8 + "elo": 1049, + "win_rate": 52.3, + "rank": 103 } - ], - "artificial_analysis": { - "intelligence_index": 44.2, - "coding_index": 61.8, - "agentic_index": 30.3 - } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true + ] } }, { - "id": "moonshotai/kimi-k2.7-code", - "canonical_slug": "moonshotai/kimi-k2.7-code-20260612", - "hugging_face_id": "moonshotai/Kimi-K2.7-Code", - "name": "MoonshotAI: Kimi K2.7 Code", - "created": 1781266361, - "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...", - "context_length": 262144, + "id": "openai/gpt-4.1-mini", + "canonical_slug": "openai/gpt-4.1-mini-2025-04-14", + "hugging_face_id": "", + "name": "OpenAI: GPT-4.1 Mini", + "created": 1744651381, + "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...", + "context_length": 1047576, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000074", - "completion": "0.0000035", - "input_cache_read": "0.00000015" + "prompt": "0.0000004", + "completion": "0.0000016", + "web_search": "0.01", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logit_bias", - "logprobs", + "max_completion_tokens", "max_tokens", - "min_p", - "parallel_tool_calls", - "presence_penalty", - "reasoning", - "reasoning_effort", - "repetition_penalty", "response_format", "seed", - "stop", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints" + "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1171, - "win_rate": 47.4, - "rank": 8 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1220, - "win_rate": 51.5, - "rank": 10 + "arena": "models", + "category": "3d", + "elo": 890, + "win_rate": 30.5, + "rank": 109 }, { - "arena": "agents", - "category": "fullstack", - "elo": 1245, - "win_rate": 56, - "rank": 7 + "arena": "models", + "category": "codecategories", + "elo": 1012, + "win_rate": 47.5, + "rank": 107 }, { - "arena": "agents", - "category": "htmlslides", - "elo": 1209, - "win_rate": 53, - "rank": 5 + "arena": "models", + "category": "dataviz", + "elo": 1055, + "win_rate": 49.2, + "rank": 96 }, { - "arena": "agents", - "category": "mobileapps", - "elo": 1221, - "win_rate": 50.7, - "rank": 10 + "arena": "models", + "category": "gamedev", + "elo": 1109, + "win_rate": 58.5, + "rank": 87 }, { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1194, - "win_rate": 46.8, - "rank": 6 + "arena": "models", + "category": "uicomponent", + "elo": 989, + "win_rate": 45.4, + "rank": 101 }, { - "arena": "agents", - "category": "webapps", - "elo": 1248, - "win_rate": 50.8, - "rank": 9 - }, + "arena": "models", + "category": "website", + "elo": 1008, + "win_rate": 47.8, + "rank": 111 + } + ], + "artificial_analysis": { + "intelligence_index": 14.8, + "coding_index": 20.2, + "agentic_index": 1.8 + } + } + }, + { + "id": "openai/gpt-4.1-mini:batch", + "canonical_slug": "openai/gpt-4.1-mini-2025-04-14", + "hugging_face_id": "", + "name": "OpenAI: GPT-4.1 Mini (batch)", + "created": 1744651381, + "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...", + "context_length": 1047576, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000008", + "web_search": "0.01", + "input_cache_read": "0.00000005" + }, + "top_provider": { + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" + }, + "benchmarks": { + "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1321, - "win_rate": 56.2, - "rank": 11 + "elo": 890, + "win_rate": 30.5, + "rank": 109 }, { "arena": "models", "category": "codecategories", - "elo": 1307, - "win_rate": 55.1, - "rank": 12 + "elo": 1012, + "win_rate": 47.5, + "rank": 107 }, { "arena": "models", "category": "dataviz", - "elo": 1258, - "win_rate": 51.4, - "rank": 26 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1281, - "win_rate": 51.5, - "rank": 22 + "elo": 1055, + "win_rate": 49.2, + "rank": 96 }, { "arena": "models", - "category": "svg", - "elo": 1254, - "win_rate": 52.6, - "rank": 13 + "category": "gamedev", + "elo": 1109, + "win_rate": 58.5, + "rank": 87 }, { "arena": "models", "category": "uicomponent", - "elo": 1301, - "win_rate": 54.8, - "rank": 14 + "elo": 989, + "win_rate": 45.4, + "rank": 101 }, { "arena": "models", "category": "website", - "elo": 1316, - "win_rate": 56.9, - "rank": 9 + "elo": 1008, + "win_rate": 47.8, + "rank": 111 } ], "artificial_analysis": { - "intelligence_index": 41.9, - "coding_index": 60.8, - "agentic_index": 29.6 + "intelligence_index": 14.8, + "coding_index": 20.2, + "agentic_index": 1.8 } - }, - "reasoning": { - "mandatory": true, - "default_enabled": true - } - }, - { - "id": "morph/morph-v3-fast", - "canonical_slug": "morph/morph-v3-fast", - "hugging_face_id": "", - "name": "Morph: Morph V3 Fast", - "created": 1751910002, - "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}...", - "context_length": 81920, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000008", - "completion": "0.0000012" - }, - "top_provider": { - "context_length": 81920, - "max_completion_tokens": 38000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": ["max_tokens", "stop", "temperature"], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/morph/morph-v3-fast/endpoints" } }, { - "id": "morph/morph-v3-large", - "canonical_slug": "morph/morph-v3-large", + "id": "openai/gpt-4.1-nano", + "canonical_slug": "openai/gpt-4.1-nano-2025-04-14", "hugging_face_id": "", - "name": "Morph: Morph V3 Large", - "created": 1751910858, - "description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}...", - "context_length": 262144, + "name": "OpenAI: GPT-4.1 Nano", + "created": 1744651369, + "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...", + "context_length": 1047576, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000009", - "completion": "0.0000019" + "prompt": "0.0000001", + "completion": "0.0000004", + "web_search": "0.01", + "input_cache_read": "0.000000025" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 131072, - "is_moderated": false + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "logprobs", + "max_completion_tokens", "max_tokens", "response_format", - "stop", + "seed", "structured_outputs", "temperature", - "top_logprobs" + "tool_choice", + "tools", + "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/morph/morph-v3-large/endpoints" + "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 978, + "win_rate": 46, + "rank": 102 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 982, + "win_rate": 47.3, + "rank": 109 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 913, + "win_rate": 41.1, + "rank": 113 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1008, + "win_rate": 49.6, + "rank": 106 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 944, + "win_rate": 43.9, + "rank": 106 + }, + { + "arena": "models", + "category": "website", + "elo": 984, + "win_rate": 48.1, + "rank": 113 + } + ], + "artificial_analysis": { + "intelligence_index": 9.6, + "coding_index": 11.1, + "agentic_index": 1.2 + } } }, { - "id": "nex-agi/nex-n2-mini", - "canonical_slug": "nex-agi/nex-n2-mini", - "hugging_face_id": "nex-agi/Nex-N2-Mini", - "name": "Nex AGI: Nex-N2-Mini", - "created": 1782312964, - "description": "Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...", - "context_length": 262144, + "id": "openai/gpt-4.1-nano:batch", + "canonical_slug": "openai/gpt-4.1-nano-2025-04-14", + "hugging_face_id": "", + "name": "OpenAI: GPT-4.1 Nano (batch)", + "created": 1744651369, + "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...", + "context_length": 1047576, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000000025", - "completion": "0.0000001", - "input_cache_read": "0.0000000025" + "prompt": "0.00000005", + "completion": "0.0000002", + "web_search": "0.01", + "input_cache_read": "0.0000000125" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, - "is_moderated": false + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", - "logprobs", "max_tokens", - "reasoning", "response_format", + "seed", "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.95, - "top_k": 40, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/nex-agi/nex-n2-mini/endpoints" + "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" }, - "reasoning": { - "mandatory": false + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 978, + "win_rate": 46, + "rank": 102 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 982, + "win_rate": 47.3, + "rank": 109 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 913, + "win_rate": 41.1, + "rank": 113 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1008, + "win_rate": 49.6, + "rank": 106 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 944, + "win_rate": 43.9, + "rank": 106 + }, + { + "arena": "models", + "category": "website", + "elo": 984, + "win_rate": 48.1, + "rank": 113 + } + ], + "artificial_analysis": { + "intelligence_index": 9.6, + "coding_index": 11.1, + "agentic_index": 1.2 + } } }, { - "id": "nex-agi/nex-n2-pro", - "canonical_slug": "nex-agi/nex-n2-pro", - "hugging_face_id": "nex-agi/Nex-N2-Pro", - "name": "Nex AGI: Nex-N2-Pro", - "created": 1780937140, - "description": "Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...", - "context_length": 262144, + "id": "openai/gpt-4.1:batch", + "canonical_slug": "openai/gpt-4.1-2025-04-14", + "hugging_face_id": "", + "name": "OpenAI: GPT-4.1 (batch)", + "created": 1744651385, + "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...", + "context_length": 1047576, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.000001", - "input_cache_read": "0.000000025" + "prompt": "0.000001", + "completion": "0.000004", + "web_search": "0.01", + "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, - "is_moderated": false + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "include_reasoning", - "logprobs", "max_tokens", - "reasoning", + "response_format", + "seed", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.95, - "top_k": 40, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/nex-agi/nex-n2-pro/endpoints" + "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1308, - "win_rate": 53.4, - "rank": 16 + "elo": 903, + "win_rate": 30.9, + "rank": 108 }, { "arena": "models", "category": "codecategories", - "elo": 1274, - "win_rate": 49.6, - "rank": 25 + "elo": 1044, + "win_rate": 50.9, + "rank": 100 }, { "arena": "models", "category": "dataviz", - "elo": 1254, - "win_rate": 49.4, - "rank": 27 + "elo": 1125, + "win_rate": 59.5, + "rank": 80 }, { "arena": "models", "category": "gamedev", - "elo": 1269, - "win_rate": 48.7, - "rank": 26 - }, - { - "arena": "models", - "category": "svg", - "elo": 1265, - "win_rate": 55, - "rank": 10 + "elo": 1117, + "win_rate": 59.1, + "rank": 84 }, { "arena": "models", "category": "uicomponent", - "elo": 1258, - "win_rate": 47.6, - "rank": 29 + "elo": 1028, + "win_rate": 49.7, + "rank": 97 }, { "arena": "models", "category": "website", - "elo": 1254, - "win_rate": 47.6, - "rank": 30 + "elo": 1049, + "win_rate": 52.3, + "rank": 103 } ] - }, - "reasoning": { - "mandatory": false } }, { - "id": "nousresearch/hermes-3-llama-3.1-405b", - "canonical_slug": "nousresearch/hermes-3-llama-3.1-405b", - "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-405B", - "name": "Nous: Hermes 3 405B Instruct", - "created": 1723766400, - "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, + "id": "openai/gpt-4o", + "canonical_slug": "openai/gpt-4o", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o", + "created": 1715558400, + "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "chatml" + "tokenizer": "GPT", + "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000001" + "prompt": "0.0000025", + "completion": "0.00001", + "input_cache_read": "0.00000125" }, "top_provider": { - "context_length": 131072, + "context_length": 128000, "max_completion_tokens": 16384, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", - "min_p", + "prediction", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" + "details": "/api/v1/models/openai/gpt-4o/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 922, + "win_rate": 39.2, + "rank": 105 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 880, + "win_rate": 34.8, + "rank": 117 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 878, + "win_rate": 36, + "rank": 115 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 944, + "win_rate": 42.3, + "rank": 114 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 914, + "win_rate": 38.1, + "rank": 110 + }, + { + "arena": "models", + "category": "website", + "elo": 842, + "win_rate": 31.5, + "rank": 125 + } + ] } }, { - "id": "nousresearch/hermes-3-llama-3.1-405b:free", - "canonical_slug": "nousresearch/hermes-3-llama-3.1-405b", - "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-405B", - "name": "Nous: Hermes 3 405B Instruct (free)", - "created": 1723766400, - "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, + "id": "openai/gpt-4o-2024-05-13", + "canonical_slug": "openai/gpt-4o-2024-05-13", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o (2024-05-13)", + "created": 1715558400, + "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "chatml" + "tokenizer": "GPT", + "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000005", + "completion": "0.000015" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 128000, + "max_completion_tokens": 4096, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", + "prediction", "presence_penalty", + "response_format", + "seed", "stop", + "structured_outputs", "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints" + "details": "/api/v1/models/openai/gpt-4o-2024-05-13/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 24.2, + "agentic_index": null + } } }, { - "id": "nousresearch/hermes-3-llama-3.1-70b", - "canonical_slug": "nousresearch/hermes-3-llama-3.1-70b", - "hugging_face_id": "NousResearch/Hermes-3-Llama-3.1-70B", - "name": "Nous: Hermes 3 70B Instruct", - "created": 1723939200, - "description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, + "id": "openai/gpt-4o-2024-08-06", + "canonical_slug": "openai/gpt-4o-2024-08-06", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o (2024-08-06)", + "created": 1722902400, + "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "chatml" + "tokenizer": "GPT", + "instruct_type": null }, "pricing": { - "prompt": "0.0000007", - "completion": "0.0000007" + "prompt": "0.0000025", + "completion": "0.00001", + "input_cache_read": "0.00000125" }, "top_provider": { - "context_length": 131072, + "context_length": 128000, "max_completion_tokens": 16384, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", - "min_p", + "prediction", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints" + "details": "/api/v1/models/openai/gpt-4o-2024-08-06/endpoints" } }, { - "id": "nousresearch/hermes-4-405b", - "canonical_slug": "nousresearch/hermes-4-405b", - "hugging_face_id": "NousResearch/Hermes-4-405B", - "name": "Nous: Hermes 4 405B", - "created": 1756235463, - "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...", - "context_length": 131072, + "id": "openai/gpt-4o-2024-11-20", + "canonical_slug": "openai/gpt-4o-2024-11-20", + "hugging_face_id": "", + "name": "OpenAI: GPT-4o (2024-11-20)", + "created": 1732127594, + "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000001", - "completion": "0.000003" + "prompt": "0.0000025", + "completion": "0.00001", + "input_cache_read": "0.00000125" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "prediction", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", + "seed", + "stop", + "structured_outputs", "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nousresearch/hermes-4-405b/endpoints" - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/openai/gpt-4o-2024-11-20/endpoints" } }, { - "id": "nousresearch/hermes-4-70b", - "canonical_slug": "nousresearch/hermes-4-70b", - "hugging_face_id": "NousResearch/Hermes-4-70B", - "name": "Nous: Hermes 4 70B", - "created": 1756236182, - "description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...", - "context_length": 131072, + "id": "openai/gpt-4o-mini", + "canonical_slug": "openai/gpt-4o-mini", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o-mini", + "created": 1721260800, + "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000013", - "completion": "0.0000004" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000075" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", + "logit_bias", + "logprobs", + "max_completion_tokens", "max_tokens", + "prediction", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", + "seed", + "stop", + "structured_outputs", "temperature", - "top_k", - "top_p" + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-08-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nousresearch/hermes-4-70b/endpoints" + "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" }, - "reasoning": { - "mandatory": false + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 11.4, + "agentic_index": 1 + } } }, { - "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5", - "canonical_slug": "nvidia/llama-3.3-nemotron-super-49b-v1.5", - "hugging_face_id": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", - "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", - "created": 1760101395, - "description": "Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...", - "context_length": 131072, + "id": "openai/gpt-4o-mini-2024-07-18", + "canonical_slug": "openai/gpt-4o-mini-2024-07-18", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o-mini (2024-07-18)", + "created": 1721260800, + "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama3", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000004" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000075" }, "top_provider": { - "context_length": 131072, + "context_length": 128000, "max_completion_tokens": 16384, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logit_bias", + "logprobs", "max_tokens", - "min_p", + "prediction", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_p" + "top_logprobs", + "top_p", + "web_search_options" ], - "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-03-31", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/llama-3.3-nemotron-super-49b-v1.5/endpoints" - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints" } }, { - "id": "nvidia/nemotron-3-nano-30b-a3b", - "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", - "name": "NVIDIA: Nemotron 3 Nano 30B A3B", - "created": 1765731275, - "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", - "context_length": 262144, + "id": "openai/gpt-4o-mini:batch", + "canonical_slug": "openai/gpt-4o-mini", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o-mini (batch)", + "created": 1721260800, + "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000002" + "prompt": "0.000000075", + "completion": "0.0000003", + "web_search": "0.01", + "input_cache_read": "0.0000000375" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 228000, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logit_bias", "logprobs", "max_tokens", - "min_p", + "prediction", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -12677,575 +20036,641 @@ "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", - "top_p" + "top_p", + "web_search_options" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" + "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 14.2, - "coding_index": 14.4, - "agentic_index": 2 + "intelligence_index": null, + "coding_index": 11.4, + "agentic_index": 1 } - }, - "reasoning": { - "mandatory": false } }, { - "id": "nvidia/nemotron-3-nano-30b-a3b:free", - "canonical_slug": "nvidia/nemotron-3-nano-30b-a3b", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", - "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", - "created": 1765731275, - "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", - "context_length": 256000, + "id": "openai/gpt-4o:batch", + "canonical_slug": "openai/gpt-4o", + "hugging_face_id": null, + "name": "OpenAI: GPT-4o (batch)", + "created": 1715558400, + "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00000125", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.000000625" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", - "reasoning", + "prediction", + "presence_penalty", + "response_format", "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", "tools", - "top_p" + "top_logprobs", + "top_p", + "web_search_options" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints" + "details": "/api/v1/models/openai/gpt-4o/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 14.2, - "coding_index": 14.4, - "agentic_index": 2 - } - }, - "reasoning": { - "mandatory": false + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 922, + "win_rate": 39.2, + "rank": 105 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 880, + "win_rate": 34.8, + "rank": 117 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 878, + "win_rate": 36, + "rank": 115 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 944, + "win_rate": 42.3, + "rank": 114 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 914, + "win_rate": 38.1, + "rank": 110 + }, + { + "arena": "models", + "category": "website", + "elo": 842, + "win_rate": 31.5, + "rank": 125 + } + ] } }, { - "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", - "canonical_slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428", - "hugging_face_id": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", - "name": "NVIDIA: Nemotron 3 Nano Omni (free)", - "created": 1777393095, - "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...", - "context_length": 256000, + "id": "openai/gpt-5", + "canonical_slug": "openai/gpt-5-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5", + "created": 1754587413, + "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...", + "context_length": 400000, "architecture": { - "modality": "text+image+audio+video->text", - "input_modalities": ["text", "audio", "image", "video"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00000125", + "completion": "0.00001", + "web_search": "0.01", + "input_cache_read": "0.000000125" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": 65536, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", + "response_format", "seed", - "temperature", + "structured_outputs", "tool_choice", - "tools", - "top_p" + "tools" ], "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints" + "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1109, + "win_rate": 41.5, + "rank": 85 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1173, + "win_rate": 49, + "rank": 34 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1187, + "win_rate": 54.4, + "rank": 58 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1244, + "win_rate": 60.6, + "rank": 35 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1223, + "win_rate": 59.4, + "rank": 43 + }, + { + "arena": "models", + "category": "svg", + "elo": 1218, + "win_rate": 62.3, + "rank": 19 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1208, + "win_rate": 57.3, + "rank": 47 + }, + { + "arena": "models", + "category": "website", + "elo": 1195, + "win_rate": 53.5, + "rank": 57 + } + ], + "artificial_analysis": { + "intelligence_index": 35.3, + "coding_index": 37.8, + "agentic_index": 26.5 + } }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "nvidia/nemotron-3-super-120b-a12b", - "canonical_slug": "nvidia/nemotron-3-super-120b-a12b-20230311", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", - "name": "NVIDIA: Nemotron 3 Super", - "created": 1773245239, - "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", - "context_length": 1000000, + "id": "openai/gpt-5-codex:batch", + "canonical_slug": "openai/gpt-5-codex", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Codex (batch)", + "created": 1758643403, + "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000008", - "completion": "0.00000045" + "prompt": "0.000000625", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.0000000625" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_k", - "top_logprobs", - "top_p" + "tools" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" + "details": "/api/v1/models/openai/gpt-5-codex/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 25.4, - "coding_index": 37.7, - "agentic_index": 8.7 - } + "design_arena": [ + { + "arena": "agents", + "category": "webapps", + "elo": 1111, + "win_rate": 51, + "rank": 30 + } + ] }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true, - "supported_efforts": ["medium", "low"], - "default_effort": "medium" + "mandatory": true } }, { - "id": "nvidia/nemotron-3-super-120b-a12b:free", - "canonical_slug": "nvidia/nemotron-3-super-120b-a12b-20230311", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", - "name": "NVIDIA: Nemotron 3 Super (free)", - "created": 1773245239, - "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", - "context_length": 1000000, + "id": "openai/gpt-5-image", + "canonical_slug": "openai/gpt-5-image", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Image", + "created": 1760447986, + "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", + "modality": "text+image+file->text+image", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["image", "text"], + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00001", + "completion": "0.00001", + "image_output": "0.00004", + "web_search": "0.01", + "input_cache_read": "0.00000125" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "presence_penalty", "reasoning", "response_format", "seed", + "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints" + "details": "/api/v1/models/openai/gpt-5-image/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 25.4, - "coding_index": 37.7, - "agentic_index": 8.7 - } + "design_arena": [ + { + "arena": "models", + "category": "graphicdesign", + "elo": 1197, + "win_rate": 48.9, + "rank": 7 + }, + { + "arena": "models", + "category": "image", + "elo": 1211, + "win_rate": 53.9, + "rank": 7 + }, + { + "arena": "models", + "category": "logo", + "elo": 1214, + "win_rate": 52.7, + "rank": 7 + } + ] }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true, - "supported_efforts": ["medium", "low"], - "default_effort": "medium" + "mandatory": true } }, { - "id": "nvidia/nemotron-3-ultra-550b-a55b", - "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "name": "NVIDIA: Nemotron 3 Ultra", - "created": 1780551208, - "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", - "context_length": 1000000, + "id": "openai/gpt-5-image-mini", + "canonical_slug": "openai/gpt-5-image-mini", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Image Mini", + "created": 1760624583, + "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", + "modality": "text+image+file->text+image", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["image", "text"], + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.0000022", - "input_cache_read": "0.0000001" + "prompt": "0.0000025", + "completion": "0.000002", + "image_output": "0.000008", + "web_search": "0.01", + "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", "logit_bias", + "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_k", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" + "details": "/api/v1/models/openai/gpt-5-image-mini/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", - "category": "3d", - "elo": 1216, - "win_rate": 43.9, - "rank": 41 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1112, - "win_rate": 38.4, - "rank": 45 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1173, - "win_rate": 36.9, - "rank": 61 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1151, - "win_rate": 36.6, - "rank": 64 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1195, - "win_rate": 39.3, - "rank": 54 - }, - { - "arena": "models", - "category": "svg", - "elo": 1140, - "win_rate": 38.4, - "rank": 47 + "category": "graphicdesign", + "elo": 1190, + "win_rate": 47.7, + "rank": 9 }, { "arena": "models", - "category": "uicomponent", - "elo": 1171, - "win_rate": 37.4, - "rank": 56 + "category": "image", + "elo": 1203, + "win_rate": 51, + "rank": 9 }, { "arena": "models", - "category": "website", - "elo": 1141, - "win_rate": 32.7, - "rank": 77 + "category": "logo", + "elo": 1221, + "win_rate": 51.4, + "rank": 6 } - ], - "artificial_analysis": { - "intelligence_index": 37.8, - "coding_index": 49.3, - "agentic_index": 27.4 - } + ] }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true, - "supported_efforts": ["high", "medium"], - "default_effort": "high" + "mandatory": true } }, { - "id": "nvidia/nemotron-3-ultra-550b-a55b:free", - "canonical_slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "name": "NVIDIA: Nemotron 3 Ultra (free)", - "created": 1780551208, - "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...", - "context_length": 1000000, + "id": "openai/gpt-5-mini", + "canonical_slug": "openai/gpt-5-mini-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Mini", + "created": 1754587407, + "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.00000025", + "completion": "0.000002", + "web_search": "0.01", + "input_cache_read": "0.000000025" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 65536, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", + "response_format", "seed", - "temperature", - "tool_choice", - "tools", - "top_p" + "structured_outputs", + "tool_choice", + "tools" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-05-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints" + "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1216, - "win_rate": 43.9, - "rank": 41 + "elo": 1091, + "win_rate": 36.9, + "rank": 87 }, { "arena": "models", "category": "asciiart", - "elo": 1112, - "win_rate": 38.4, - "rank": 45 + "elo": 1155, + "win_rate": 44.5, + "rank": 40 }, { "arena": "models", "category": "codecategories", - "elo": 1173, - "win_rate": 36.9, - "rank": 61 + "elo": 1134, + "win_rate": 43.4, + "rank": 80 }, { "arena": "models", "category": "dataviz", - "elo": 1151, - "win_rate": 36.6, - "rank": 64 + "elo": 1153, + "win_rate": 43.8, + "rank": 71 }, { "arena": "models", "category": "gamedev", - "elo": 1195, - "win_rate": 39.3, - "rank": 54 + "elo": 1167, + "win_rate": 46.5, + "rank": 67 }, { "arena": "models", "category": "svg", - "elo": 1140, - "win_rate": 38.4, - "rank": 47 + "elo": 1121, + "win_rate": 45, + "rank": 50 }, { "arena": "models", "category": "uicomponent", - "elo": 1171, - "win_rate": 37.4, - "rank": 56 + "elo": 1135, + "win_rate": 42, + "rank": 71 }, { "arena": "models", "category": "website", - "elo": 1141, - "win_rate": 32.7, - "rank": 77 + "elo": 1136, + "win_rate": 44.2, + "rank": 80 } ], "artificial_analysis": { - "intelligence_index": 37.8, - "coding_index": 49.3, - "agentic_index": 27.4 + "intelligence_index": 25.8, + "coding_index": 15.6, + "agentic_index": 19.6 } }, "reasoning": { - "mandatory": false, - "default_enabled": true, - "supports_max_tokens": true, - "supported_efforts": ["high", "medium"], - "default_effort": "high" + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "nvidia/nemotron-3.5-content-safety:free", - "canonical_slug": "nvidia/nemotron-3.5-content-safety-20260604", - "hugging_face_id": "nvidia/Nemotron-3.5-Content-Safety", - "name": "NVIDIA: Nemotron 3.5 Content Safety (free)", - "created": 1780581864, - "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...", - "context_length": 128000, + "id": "openai/gpt-5-mini:batch", + "canonical_slug": "openai/gpt-5-mini-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Mini (batch)", + "created": 1754587407, + "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....", + "context_length": 400000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.000000125", + "completion": "0.000001", + "web_search": "0.01", + "input_cache_read": "0.0000000125" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 8192, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", + "response_format", "seed", - "temperature", - "top_p" + "structured_outputs", + "tool_choice", + "tools" ], "default_parameters": { "temperature": null, @@ -13256,682 +20681,956 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "nvidia/nemotron-nano-12b-v2-vl:free", - "canonical_slug": "nvidia/nemotron-nano-12b-v2-vl", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", - "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)", - "created": 1761675565, - "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...", - "context_length": 128000, - "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["image", "text", "video"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 128000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "seed", - "temperature", - "tool_choice", - "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-05-31", "expiration_date": null, "links": { - "details": "/api/v1/models/nvidia/nemotron-nano-12b-v2-vl/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "nvidia/nemotron-nano-9b-v2:free", - "canonical_slug": "nvidia/nemotron-nano-9b-v2", - "hugging_face_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", - "name": "NVIDIA: Nemotron Nano 9B V2 (free)", - "created": 1757106807, - "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": null, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null + "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" }, - "supported_voices": null, - "knowledge_cutoff": "2025-03-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/nvidia/nemotron-nano-9b-v2/endpoints" + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1091, + "win_rate": 36.9, + "rank": 87 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1155, + "win_rate": 44.5, + "rank": 40 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1134, + "win_rate": 43.4, + "rank": 80 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1153, + "win_rate": 43.8, + "rank": 71 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1167, + "win_rate": 46.5, + "rank": 67 + }, + { + "arena": "models", + "category": "svg", + "elo": 1121, + "win_rate": 45, + "rank": 50 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1135, + "win_rate": 42, + "rank": 71 + }, + { + "arena": "models", + "category": "website", + "elo": 1136, + "win_rate": 44.2, + "rank": 80 + } + ], + "artificial_analysis": { + "intelligence_index": 25.8, + "coding_index": 15.6, + "agentic_index": 19.6 + } }, "reasoning": { - "mandatory": false + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "openai/gpt-3.5-turbo", - "canonical_slug": "openai/gpt-3.5-turbo", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo", - "created": 1685232000, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 16385, + "id": "openai/gpt-5-nano", + "canonical_slug": "openai/gpt-5-nano-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Nano", + "created": 1754587402, + "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000005", - "completion": "0.0000015" + "prompt": "0.00000005", + "completion": "0.0000004", + "web_search": "0.01", + "input_cache_read": "0.000000005" }, "top_provider": { - "context_length": 16385, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", + "max_completion_tokens", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2021-09-30", + "knowledge_cutoff": "2024-05-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints" + "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 10.7, - "agentic_index": null - } - } - }, - { - "id": "openai/gpt-3.5-turbo-0613", - "canonical_slug": "openai/gpt-3.5-turbo-0613", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo (older v0613)", - "created": 1706140800, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 4095, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.000001", - "completion": "0.000002" - }, - "top_provider": { - "context_length": 4095, - "max_completion_tokens": 4096, - "is_moderated": false + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1019, + "win_rate": 36.3, + "rank": 100 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1103, + "win_rate": 48, + "rank": 87 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1078, + "win_rate": 46.2, + "rank": 91 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1083, + "win_rate": 46.5, + "rank": 92 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1095, + "win_rate": 51.9, + "rank": 85 + }, + { + "arena": "models", + "category": "website", + "elo": 1112, + "win_rate": 48.9, + "rank": 90 + } + ] }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_completion_tokens", - "presence_penalty", - "response_format", - "seed", - "stop", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2021-09-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints" + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "openai/gpt-3.5-turbo-16k", - "canonical_slug": "openai/gpt-3.5-turbo-16k", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo 16k", - "created": 1693180800, - "description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...", - "context_length": 16385, + "id": "openai/gpt-5-nano:batch", + "canonical_slug": "openai/gpt-5-nano-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Nano (batch)", + "created": 1754587402, + "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000003", - "completion": "0.000004" + "prompt": "0.000000025", + "completion": "0.0000002", + "web_search": "0.01", + "input_cache_read": "0.0000000025" }, "top_provider": { - "context_length": 16385, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_completion_tokens", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2021-09-30", + "knowledge_cutoff": "2024-05-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints" + "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1019, + "win_rate": 36.3, + "rank": 100 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1103, + "win_rate": 48, + "rank": 87 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1078, + "win_rate": 46.2, + "rank": 91 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1083, + "win_rate": 46.5, + "rank": 92 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1095, + "win_rate": 51.9, + "rank": 85 + }, + { + "arena": "models", + "category": "website", + "elo": 1112, + "win_rate": 48.9, + "rank": 90 + } + ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "openai/gpt-3.5-turbo-instruct", - "canonical_slug": "openai/gpt-3.5-turbo-instruct", - "hugging_face_id": null, - "name": "OpenAI: GPT-3.5 Turbo Instruct", - "created": 1695859200, - "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.", - "context_length": 4095, + "id": "openai/gpt-5-pro", + "canonical_slug": "openai/gpt-5-pro-2025-10-06", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Pro", + "created": 1759776663, + "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", - "instruct_type": "chatml" + "instruct_type": null }, "pricing": { - "prompt": "0.0000015", - "completion": "0.000002" + "prompt": "0.000015", + "completion": "0.00012", + "web_search": "0.01" }, "top_provider": { - "context_length": 4095, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", - "top_logprobs", - "top_p" + "tool_choice", + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2021-09-30", + "knowledge_cutoff": "2024-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints" + "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high"], + "default_effort": "high" } }, { - "id": "openai/gpt-4", - "canonical_slug": "openai/gpt-4", - "hugging_face_id": null, - "name": "OpenAI: GPT-4", - "created": 1685232000, - "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...", - "context_length": 8191, + "id": "openai/gpt-5-pro:batch", + "canonical_slug": "openai/gpt-5-pro-2025-10-06", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 Pro (batch)", + "created": 1759776663, + "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00003", - "completion": "0.00006" + "prompt": "0.0000075", + "completion": "0.00006", + "web_search": "0.01" }, "top_provider": { - "context_length": 8191, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_completion_tokens", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2021-09-30", + "knowledge_cutoff": "2024-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4/endpoints" + "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 13.1, - "agentic_index": null - } + "reasoning": { + "mandatory": true, + "supported_efforts": ["high"], + "default_effort": "high" } }, { - "id": "openai/gpt-4-turbo", - "canonical_slug": "openai/gpt-4-turbo", - "hugging_face_id": null, - "name": "OpenAI: GPT-4 Turbo", - "created": 1712620800, - "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", - "context_length": 128000, + "id": "openai/gpt-5:batch", + "canonical_slug": "openai/gpt-5-2025-08-07", + "hugging_face_id": "", + "name": "OpenAI: GPT-5 (batch)", + "created": 1754587413, + "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...", + "context_length": 400000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00003" + "prompt": "0.000000625", + "completion": "0.000005", + "web_search": "0.01", + "input_cache_read": "0.0000000625" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2024-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4-turbo/endpoints" + "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1109, + "win_rate": 41.5, + "rank": 85 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1173, + "win_rate": 49, + "rank": 34 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1187, + "win_rate": 54.4, + "rank": 58 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1244, + "win_rate": 60.6, + "rank": 35 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1223, + "win_rate": 59.4, + "rank": 43 + }, + { + "arena": "models", + "category": "svg", + "elo": 1218, + "win_rate": 62.3, + "rank": 19 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1208, + "win_rate": 57.3, + "rank": 47 + }, + { + "arena": "models", + "category": "website", + "elo": 1195, + "win_rate": 53.5, + "rank": 57 + } + ], "artificial_analysis": { - "intelligence_index": null, - "coding_index": 21.5, - "agentic_index": null + "intelligence_index": 35.3, + "coding_index": 37.8, + "agentic_index": 26.5 } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low", "minimal"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4-turbo-preview", - "canonical_slug": "openai/gpt-4-turbo-preview", - "hugging_face_id": null, - "name": "OpenAI: GPT-4 Turbo Preview", - "created": 1706140800, - "description": "The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...", - "context_length": 128000, + "id": "openai/gpt-5.1", + "canonical_slug": "openai/gpt-5.1-20251113", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.1", + "created": 1763060305, + "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...", + "context_length": 400000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00003" + "prompt": "0.00000125", + "completion": "0.00001", + "web_search": "0.01", + "input_cache_read": "0.000000125" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 4096, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", + "max_completion_tokens", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4-turbo-preview/endpoints" + "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "webapps", + "elo": 1032, + "win_rate": 39.9, + "rank": 36 + }, + { + "arena": "models", + "category": "3d", + "elo": 1114, + "win_rate": 43.7, + "rank": 83 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1151, + "win_rate": 48.6, + "rank": 43 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1190, + "win_rate": 52.9, + "rank": 56 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1228, + "win_rate": 58.1, + "rank": 41 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1217, + "win_rate": 55.9, + "rank": 44 + }, + { + "arena": "models", + "category": "svg", + "elo": 1184, + "win_rate": 56.3, + "rank": 34 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1196, + "win_rate": 53.4, + "rank": 53 + }, + { + "arena": "models", + "category": "website", + "elo": 1198, + "win_rate": 53.9, + "rank": 56 + } + ], + "artificial_analysis": { + "intelligence_index": 37.5, + "coding_index": 49.4, + "agentic_index": 21.6 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "none"], + "default_effort": "none" } }, { - "id": "openai/gpt-4.1", - "canonical_slug": "openai/gpt-4.1-2025-04-14", + "id": "openai/gpt-5.1-codex", + "canonical_slug": "openai/gpt-5.1-codex-20251113", "hugging_face_id": "", - "name": "OpenAI: GPT-4.1", - "created": 1744651385, - "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...", - "context_length": 1047576, + "name": "OpenAI: GPT-5.1-Codex", + "created": 1763060298, + "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "context_length": 400000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000008", + "prompt": "0.00000125", + "completion": "0.00001", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.00000013" }, "top_provider": { - "context_length": 1047576, - "max_completion_tokens": null, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "include_reasoning", "max_completion_tokens", - "max_tokens", + "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints" + "details": "/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "models", - "category": "3d", - "elo": 927, - "win_rate": 30.9, - "rank": 96 + "arena": "agents", + "category": "fullstack", + "elo": 1086, + "win_rate": 44.5, + "rank": 31 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1191, + "win_rate": 53.4, + "rank": 22 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1060, + "win_rate": 41.5, + "rank": 35 }, { "arena": "models", "category": "codecategories", - "elo": 1075, - "win_rate": 50.9, - "rank": 85 + "elo": 1171, + "win_rate": 54.6, + "rank": 65 }, { "arena": "models", "category": "dataviz", - "elo": 1147, - "win_rate": 59.5, - "rank": 66 + "elo": 1236, + "win_rate": 55.9, + "rank": 38 }, { "arena": "models", "category": "gamedev", - "elo": 1145, - "win_rate": 59.1, - "rank": 67 + "elo": 1176, + "win_rate": 50.5, + "rank": 61 }, { "arena": "models", "category": "uicomponent", - "elo": 1055, - "win_rate": 49.7, - "rank": 81 + "elo": 1265, + "win_rate": 60, + "rank": 32 }, { "arena": "models", "category": "website", - "elo": 1081, - "win_rate": 52.3, - "rank": 87 + "elo": 1173, + "win_rate": 56.1, + "rank": 67 } ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.1-codex-max", + "canonical_slug": "openai/gpt-5.1-codex-max-20251204", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.1-Codex-Max", + "created": 1764878934, + "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...", + "context_length": 400000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000125", + "completion": "0.00001", + "web_search": "0.01", + "input_cache_read": "0.000000125" + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4.1-mini", - "canonical_slug": "openai/gpt-4.1-mini-2025-04-14", + "id": "openai/gpt-5.1-codex-mini", + "canonical_slug": "openai/gpt-5.1-codex-mini-20251113", "hugging_face_id": "", - "name": "OpenAI: GPT-4.1 Mini", - "created": 1744651381, - "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...", - "context_length": 1047576, + "name": "OpenAI: GPT-5.1-Codex-Mini", + "created": 1763057820, + "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", + "context_length": 400000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "modality": "text+image->text", + "input_modalities": ["image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000016", + "prompt": "0.00000025", + "completion": "0.000002", "web_search": "0.01", - "input_cache_read": "0.0000001" + "input_cache_read": "0.00000003" }, "top_provider": { - "context_length": 1047576, - "max_completion_tokens": 32768, - "is_moderated": true + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "include_reasoning", "max_completion_tokens", - "max_tokens", + "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints" + "details": "/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 914, - "win_rate": 30.5, - "rank": 97 + "elo": 1042, + "win_rate": 32.8, + "rank": 96 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1137, + "win_rate": 43, + "rank": 47 }, { "arena": "models", "category": "codecategories", - "elo": 1043, - "win_rate": 47.5, - "rank": 93 + "elo": 1113, + "win_rate": 41.5, + "rank": 86 }, { "arena": "models", "category": "dataviz", - "elo": 1076, - "win_rate": 49.2, - "rank": 80 + "elo": 1120, + "win_rate": 40.5, + "rank": 85 }, { "arena": "models", "category": "gamedev", - "elo": 1136, - "win_rate": 58.5, - "rank": 71 + "elo": 1131, + "win_rate": 43.5, + "rank": 80 + }, + { + "arena": "models", + "category": "svg", + "elo": 1011, + "win_rate": 35, + "rank": 74 }, { "arena": "models", "category": "uicomponent", - "elo": 1016, - "win_rate": 45.4, - "rank": 88 + "elo": 1108, + "win_rate": 40.9, + "rank": 81 }, { "arena": "models", "category": "website", - "elo": 1040, - "win_rate": 47.8, - "rank": 94 + "elo": 1122, + "win_rate": 42.8, + "rank": 88 } - ], - "artificial_analysis": { - "intelligence_index": 14.8, - "coding_index": 20.2, - "agentic_index": 1.7 - } + ] + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4.1-nano", - "canonical_slug": "openai/gpt-4.1-nano-2025-04-14", + "id": "openai/gpt-5.1:batch", + "canonical_slug": "openai/gpt-5.1-20251113", "hugging_face_id": "", - "name": "OpenAI: GPT-4.1 Nano", - "created": 1744651369, - "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...", - "context_length": 1047576, + "name": "OpenAI: GPT-5.1 (batch)", + "created": 1763060305, + "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["image", "text", "file"], @@ -13940,414 +21639,685 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000004", + "prompt": "0.000000625", + "completion": "0.000005", "web_search": "0.01", - "input_cache_read": "0.000000025" + "input_cache_read": "0.0000000625" }, "top_provider": { - "context_length": 1047576, - "max_completion_tokens": 32768, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "max_completion_tokens", + "include_reasoning", "max_tokens", + "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_p" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints" + "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "webapps", + "elo": 1032, + "win_rate": 39.9, + "rank": 36 + }, { "arena": "models", "category": "3d", - "elo": 1002, - "win_rate": 46, - "rank": 90 + "elo": 1114, + "win_rate": 43.7, + "rank": 83 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1151, + "win_rate": 48.6, + "rank": 43 }, { "arena": "models", "category": "codecategories", - "elo": 1012, - "win_rate": 47.3, - "rank": 97 + "elo": 1190, + "win_rate": 52.9, + "rank": 56 }, { "arena": "models", "category": "dataviz", - "elo": 935, - "win_rate": 41.1, - "rank": 99 + "elo": 1228, + "win_rate": 58.1, + "rank": 41 }, { "arena": "models", "category": "gamedev", - "elo": 1036, - "win_rate": 49.6, - "rank": 91 + "elo": 1217, + "win_rate": 55.9, + "rank": 44 + }, + { + "arena": "models", + "category": "svg", + "elo": 1184, + "win_rate": 56.3, + "rank": 34 }, { "arena": "models", "category": "uicomponent", - "elo": 970, - "win_rate": 43.9, - "rank": 93 + "elo": 1196, + "win_rate": 53.4, + "rank": 53 }, { "arena": "models", "category": "website", - "elo": 1015, - "win_rate": 48.1, - "rank": 99 + "elo": 1198, + "win_rate": 53.9, + "rank": 56 } ], "artificial_analysis": { - "intelligence_index": 9.6, - "coding_index": 11.1, - "agentic_index": 1.2 + "intelligence_index": 37.5, + "coding_index": 49.4, + "agentic_index": 21.6 } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "none"], + "default_effort": "none" } }, { - "id": "openai/gpt-4o", - "canonical_slug": "openai/gpt-4o", - "hugging_face_id": null, - "name": "OpenAI: GPT-4o", - "created": 1715558400, - "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", - "context_length": 128000, + "id": "openai/gpt-5.2", + "canonical_slug": "openai/gpt-5.2-20251211", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.2", + "created": 1765389775, + "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.00001" + "prompt": "0.00000175", + "completion": "0.000014", + "web_search": "0.01", + "input_cache_read": "0.000000175" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_completion_tokens", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o/endpoints" + "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "models", + "category": "website", + "elo": 1206, + "win_rate": 54.4, + "rank": 48 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1095, + "win_rate": 49.2, + "rank": 30 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1079, + "win_rate": 44.1, + "rank": 32 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 48.1, + "rank": 19 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1147, + "win_rate": 46.6, + "rank": 28 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1116, + "win_rate": 43.8, + "rank": 29 + }, { "arena": "models", "category": "3d", - "elo": 946, - "win_rate": 39.2, - "rank": 93 + "elo": 1132, + "win_rate": 41.5, + "rank": 77 }, { "arena": "models", "category": "codecategories", - "elo": 910, - "win_rate": 34.8, - "rank": 105 + "elo": 1189, + "win_rate": 49.5, + "rank": 57 }, { "arena": "models", "category": "dataviz", - "elo": 900, - "win_rate": 36, - "rank": 102 + "elo": 1224, + "win_rate": 56.1, + "rank": 43 }, { "arena": "models", "category": "gamedev", - "elo": 972, - "win_rate": 42.3, - "rank": 99 + "elo": 1233, + "win_rate": 56, + "rank": 41 }, { "arena": "models", "category": "uicomponent", - "elo": 940, - "win_rate": 38.1, - "rank": 97 + "elo": 1217, + "win_rate": 51.3, + "rank": 44 }, { "arena": "models", - "category": "website", - "elo": 874, - "win_rate": 31.5, - "rank": 110 + "category": "asciiart", + "elo": 1185, + "win_rate": 50.7, + "rank": 27 + }, + { + "arena": "models", + "category": "svg", + "elo": 1170, + "win_rate": 52.6, + "rank": 39 } ] + }, + "reasoning": { + "mandatory": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4o-2024-05-13", - "canonical_slug": "openai/gpt-4o-2024-05-13", - "hugging_face_id": null, - "name": "OpenAI: GPT-4o (2024-05-13)", - "created": 1715558400, - "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "id": "openai/gpt-5.2-chat", + "canonical_slug": "openai/gpt-5.2-chat-20251211", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.2 Chat", + "created": 1765389783, + "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", "context_length": 128000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.000015" + "prompt": "0.00000175", + "completion": "0.000014", + "web_search": "0.01", + "input_cache_read": "0.000000175" }, "top_provider": { "context_length": 128000, - "max_completion_tokens": 4096, + "max_completion_tokens": 32000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", "max_completion_tokens", - "max_tokens", - "presence_penalty", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o-2024-05-13/endpoints" + "details": "/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints" + } + }, + { + "id": "openai/gpt-5.2-codex", + "canonical_slug": "openai/gpt-5.2-codex-20260114", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.2-Codex", + "created": 1768409315, + "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "context_length": 400000, + "architecture": { + "modality": "text+image->text", + "input_modalities": ["text", "image"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000175", + "completion": "0.000014", + "web_search": "0.01", + "input_cache_read": "0.000000175" + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints" }, "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 24.2, - "agentic_index": null - } + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1176, + "win_rate": 47.5, + "rank": 24 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1028, + "win_rate": 37, + "rank": 37 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 47.8, + "rank": 20 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1143, + "win_rate": 46.4, + "rank": 31 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1091, + "win_rate": 39.6, + "rank": 33 + } + ] + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4o-2024-08-06", - "canonical_slug": "openai/gpt-4o-2024-08-06", - "hugging_face_id": null, - "name": "OpenAI: GPT-4o (2024-08-06)", - "created": 1722902400, - "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...", - "context_length": 128000, + "id": "openai/gpt-5.2-pro", + "canonical_slug": "openai/gpt-5.2-pro-20251211", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.2 Pro", + "created": 1765389780, + "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.00001", - "input_cache_read": "0.00000125" + "prompt": "0.000021", + "completion": "0.000168", + "web_search": "0.01" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_completion_tokens", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o-2024-08-06/endpoints" + "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4o-2024-11-20", - "canonical_slug": "openai/gpt-4o-2024-11-20", + "id": "openai/gpt-5.2-pro:batch", + "canonical_slug": "openai/gpt-5.2-pro-20251211", "hugging_face_id": "", - "name": "OpenAI: GPT-4o (2024-11-20)", - "created": 1732127594, - "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...", - "context_length": 128000, + "name": "OpenAI: GPT-5.2 Pro (batch)", + "created": 1765389780, + "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.00001", - "input_cache_read": "0.00000125" + "prompt": "0.0000105", + "completion": "0.000084", + "web_search": "0.01" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o-2024-11-20/endpoints" + "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4o-mini", - "canonical_slug": "openai/gpt-4o-mini", - "hugging_face_id": null, - "name": "OpenAI: GPT-4o-mini", - "created": 1721260800, - "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", - "context_length": 128000, + "id": "openai/gpt-5.2:batch", + "canonical_slug": "openai/gpt-5.2-20251211", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.2 (batch)", + "created": 1765389775, + "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000075" + "prompt": "0.000000875", + "completion": "0.000007", + "web_search": "0.01", + "input_cache_read": "0.0000000875" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": false + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", - "max_completion_tokens", + "include_reasoning", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o-mini/endpoints" + "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "website", + "elo": 1206, + "win_rate": 54.4, + "rank": 48 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1095, + "win_rate": 49.2, + "rank": 30 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1079, + "win_rate": 44.1, + "rank": 32 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 48.1, + "rank": 19 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1147, + "win_rate": 46.6, + "rank": 28 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1116, + "win_rate": 43.8, + "rank": 29 + }, + { + "arena": "models", + "category": "3d", + "elo": 1132, + "win_rate": 41.5, + "rank": 77 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1189, + "win_rate": 49.5, + "rank": 57 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1224, + "win_rate": 56.1, + "rank": 43 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1233, + "win_rate": 56, + "rank": 41 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1217, + "win_rate": 51.3, + "rank": 44 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1185, + "win_rate": 50.7, + "rank": 27 + }, + { + "arena": "models", + "category": "svg", + "elo": 1170, + "win_rate": 52.6, + "rank": 39 + } + ] }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": null, - "coding_index": 11.4, - "agentic_index": 1 - } + "reasoning": { + "mandatory": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-4o-mini-2024-07-18", - "canonical_slug": "openai/gpt-4o-mini-2024-07-18", - "hugging_face_id": null, - "name": "OpenAI: GPT-4o-mini (2024-07-18)", - "created": 1721260800, - "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", - "context_length": 128000, + "id": "openai/gpt-5.3-codex", + "canonical_slug": "openai/gpt-5.3-codex-20260224", + "hugging_face_id": "", + "name": "OpenAI: GPT-5.3-Codex", + "created": 1771959164, + "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...", + "context_length": 400000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -14356,129 +22326,152 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000075" + "prompt": "0.00000175", + "completion": "0.000014", + "web_search": "0.01", + "input_cache_read": "0.000000175" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, + "context_length": 400000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", + "max_completion_tokens", "max_tokens", - "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p", - "web_search_options" + "tools" ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints" - } - }, - { - "id": "openai/gpt-4o-mini-search-preview", - "canonical_slug": "openai/gpt-4o-mini-search-preview-2025-03-11", - "hugging_face_id": "", - "name": "OpenAI: GPT-4o-mini Search Preview", - "created": 1741818122, - "description": "GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "web_search": "0.0275" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": true + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, - "per_request_limits": null, - "supported_parameters": [ - "max_tokens", - "response_format", - "structured_outputs", - "web_search_options" - ], - "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-4o-mini-search-preview-2025-03-11/endpoints" - } - }, - { - "id": "openai/gpt-4o-search-preview", - "canonical_slug": "openai/gpt-4o-search-preview-2025-03-11", - "hugging_face_id": "", - "name": "OpenAI: GPT-4o Search Preview", - "created": 1741817949, - "description": "GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", - "context_length": 128000, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000025", - "completion": "0.00001", - "web_search": "0.035" + "details": "/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints" }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": true + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1084, + "win_rate": 35.2, + "rank": 33 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1020, + "win_rate": 36.4, + "rank": 38 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1124, + "win_rate": 45.1, + "rank": 24 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1107, + "win_rate": 41.4, + "rank": 36 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1076, + "win_rate": 36.1, + "rank": 34 + }, + { + "arena": "models", + "category": "3d", + "elo": 1062, + "win_rate": 35.3, + "rank": 91 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1184, + "win_rate": 51.2, + "rank": 28 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1164, + "win_rate": 47.3, + "rank": 66 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1187, + "win_rate": 50.6, + "rank": 57 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1199, + "win_rate": 51.3, + "rank": 52 + }, + { + "arena": "models", + "category": "svg", + "elo": 1163, + "win_rate": 53.9, + "rank": 42 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1172, + "win_rate": 48.3, + "rank": 64 + }, + { + "arena": "models", + "category": "website", + "elo": 1174, + "win_rate": 48.5, + "rank": 66 + } + ] }, - "per_request_limits": null, - "supported_parameters": [ - "max_tokens", - "response_format", - "structured_outputs", - "web_search_options" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2023-10-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-4o-search-preview-2025-03-11/endpoints" + "reasoning": { + "mandatory": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5", - "canonical_slug": "openai/gpt-5-2025-08-07", + "id": "openai/gpt-5.4", + "canonical_slug": "openai/gpt-5.4-20260305", "hugging_face_id": "", - "name": "OpenAI: GPT-5", - "created": 1754587413, - "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...", - "context_length": 400000, + "name": "OpenAI: GPT-5.4", + "created": 1772734352, + "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -14487,15 +22480,23 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", + "prompt": "0.0000025", + "completion": "0.000015", "web_search": "0.01", - "input_cache_read": "0.000000125" + "input_cache_read": "0.00000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000005", + "completion": "0.0000225", + "input_cache_read": "0.0000005" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -14503,6 +22504,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -14518,143 +22520,202 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-09-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "3d", - "elo": 1133, - "win_rate": 41.4, - "rank": 69 + "elo": 1156, + "win_rate": 42.4, + "rank": 65 }, { "arena": "models", "category": "asciiart", - "elo": 1187, - "win_rate": 49, - "rank": 28 + "elo": 1233, + "win_rate": 55.5, + "rank": 16 }, { "arena": "models", "category": "codecategories", - "elo": 1218, - "win_rate": 54.7, - "rank": 43 + "elo": 1231, + "win_rate": 52.5, + "rank": 39 }, { "arena": "models", "category": "dataviz", - "elo": 1282, - "win_rate": 63.3, - "rank": 16 + "elo": 1258, + "win_rate": 56.6, + "rank": 27 }, { "arena": "models", "category": "gamedev", - "elo": 1252, - "win_rate": 59.5, - "rank": 32 + "elo": 1276, + "win_rate": 57.6, + "rank": 26 }, { "arena": "models", "category": "svg", - "elo": 1246, - "win_rate": 64.1, - "rank": 15 + "elo": 1229, + "win_rate": 57.9, + "rank": 17 }, { "arena": "models", "category": "uicomponent", - "elo": 1236, - "win_rate": 58.3, - "rank": 34 + "elo": 1268, + "win_rate": 57.5, + "rank": 28 }, { "arena": "models", "category": "website", - "elo": 1227, - "win_rate": 53.7, - "rank": 43 + "elo": 1231, + "win_rate": 52.5, + "rank": 42 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1066, + "win_rate": 47.4, + "rank": 35 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1054, + "win_rate": 40.8, + "rank": 35 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1135, + "win_rate": 46.9, + "rank": 22 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1141, + "win_rate": 46, + "rank": 33 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1100, + "win_rate": 39.3, + "rank": 32 } ], "artificial_analysis": { - "intelligence_index": 34.7, - "coding_index": 37.8, - "agentic_index": 25.7 + "intelligence_index": 53.1, + "coding_index": 71.1, + "agentic_index": 44.2 } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5-chat", - "canonical_slug": "openai/gpt-5-chat-2025-08-07", + "id": "openai/gpt-5.4-image-2", + "canonical_slug": "openai/gpt-5.4-image-2-20260421", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Chat", - "created": 1754587837, - "description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.", - "context_length": 128000, + "name": "OpenAI: GPT-5.4 Image 2", + "created": 1776797528, + "description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...", + "context_length": 272000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], - "output_modalities": ["text"], + "modality": "text+image+file->text+image", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["image", "text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", + "prompt": "0.000008", + "completion": "0.000015", + "image_output": "0.00003", "web_search": "0.01", - "input_cache_read": "0.000000125" + "input_cache_read": "0.000002" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, + "context_length": 272000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", "response_format", "seed", - "structured_outputs" + "stop", + "structured_outputs", + "top_logprobs" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-09-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-chat-2025-08-07/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5-codex", - "canonical_slug": "openai/gpt-5-codex", + "id": "openai/gpt-5.4-mini", + "canonical_slug": "openai/gpt-5.4-mini-20260317", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Codex", - "created": 1758643403, - "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "name": "OpenAI: GPT-5.4 Mini", + "created": 1773748178, + "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...", "context_length": 400000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", + "prompt": "0.00000075", + "completion": "0.0000045", "web_search": "0.01", - "input_cache_read": "0.000000125" + "input_cache_read": "0.000000075" }, "top_provider": { "context_length": 400000, @@ -14664,8 +22725,10 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -14675,49 +22738,52 @@ "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-09-30", + "knowledge_cutoff": "2025-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-codex/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "mobileapps", - "elo": 1127, - "win_rate": 43.2, - "rank": 29 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 40.9, + "coding_index": 56.1, + "agentic_index": 31.5 + } }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5-image", - "canonical_slug": "openai/gpt-5-image", + "id": "openai/gpt-5.4-mini:batch", + "canonical_slug": "openai/gpt-5.4-mini-20260317", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Image", - "created": 1760447986, - "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...", + "name": "OpenAI: GPT-5.4 Mini (batch)", + "created": 1773748178, + "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...", "context_length": 400000, "architecture": { - "modality": "text+image+file->text+image", - "input_modalities": ["image", "text", "file"], - "output_modalities": ["image", "text"], + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00001", + "prompt": "0.000000375", + "completion": "0.00000225", "web_search": "0.01", - "input_cache_read": "0.00000125" + "input_cache_read": "0.0000000375" }, "top_provider": { "context_length": 400000, @@ -14726,81 +22792,65 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", - "top_logprobs", - "top_p" + "tool_choice", + "tools" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5-image/endpoints" + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "graphicdesign", - "elo": 1210, - "win_rate": 51.3, - "rank": 6 - }, - { - "arena": "models", - "category": "image", - "elo": 1219, - "win_rate": 54.1, - "rank": 7 - }, - { - "arena": "models", - "category": "logo", - "elo": 1223, - "win_rate": 53.7, - "rank": 6 - } - ] + "supported_voices": null, + "knowledge_cutoff": "2025-08-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 40.9, + "coding_index": 56.1, + "agentic_index": 31.5 + } }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5-image-mini", - "canonical_slug": "openai/gpt-5-image-mini", + "id": "openai/gpt-5.4-nano", + "canonical_slug": "openai/gpt-5.4-nano-20260317", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Image Mini", - "created": 1760624583, - "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...", + "name": "OpenAI: GPT-5.4 Nano", + "created": 1773748187, + "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...", "context_length": 400000, "architecture": { - "modality": "text+image+file->text+image", + "modality": "text+image+file->text", "input_modalities": ["file", "image", "text"], - "output_modalities": ["image", "text"], + "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.000002", + "prompt": "0.0000002", + "completion": "0.00000125", "web_search": "0.01", - "input_cache_read": "0.00000025" + "input_cache_read": "0.00000002" }, "top_provider": { "context_length": 400000, @@ -14809,81 +22859,66 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", + "max_completion_tokens", "max_tokens", - "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", - "top_logprobs", - "top_p" + "tool_choice", + "tools" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-image-mini/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "graphicdesign", - "elo": 1203, - "win_rate": 48.6, - "rank": 9 - }, - { - "arena": "models", - "category": "image", - "elo": 1212, - "win_rate": 51.1, - "rank": 9 - }, - { - "arena": "models", - "category": "logo", - "elo": 1229, - "win_rate": 52.6, - "rank": 5 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 39.7, + "coding_index": 56.1, + "agentic_index": 29.7 + } }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5-mini", - "canonical_slug": "openai/gpt-5-mini-2025-08-07", + "id": "openai/gpt-5.4-nano:batch", + "canonical_slug": "openai/gpt-5.4-nano-20260317", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Mini", - "created": 1754587407, - "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....", + "name": "OpenAI: GPT-5.4 Nano (batch)", + "created": 1773748187, + "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...", "context_length": 400000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.000002", + "prompt": "0.0000001", + "completion": "0.000000625", "web_search": "0.01", - "input_cache_read": "0.000000025" + "input_cache_read": "0.00000001" }, "top_provider": { "context_length": 400000, @@ -14893,9 +22928,9 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -14911,90 +22946,34 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-05-31", + "knowledge_cutoff": "2025-08-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1115, - "win_rate": 37, - "rank": 74 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1171, - "win_rate": 45.3, - "rank": 34 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1163, - "win_rate": 43.5, - "rank": 65 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1169, - "win_rate": 43.5, - "rank": 60 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1194, - "win_rate": 46.4, - "rank": 55 - }, - { - "arena": "models", - "category": "svg", - "elo": 1149, - "win_rate": 45.9, - "rank": 44 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1158, - "win_rate": 42, - "rank": 59 - }, - { - "arena": "models", - "category": "website", - "elo": 1167, - "win_rate": 44.4, - "rank": 63 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 25.3, - "coding_index": 15.6, - "agentic_index": 19.4 + "intelligence_index": 39.7, + "coding_index": 56.1, + "agentic_index": 29.7 } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "mandatory": false, + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5-nano", - "canonical_slug": "openai/gpt-5-nano-2025-08-07", + "id": "openai/gpt-5.4-pro", + "canonical_slug": "openai/gpt-5.4-pro-20260305", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Nano", - "created": 1754587402, - "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...", - "context_length": 400000, + "name": "OpenAI: GPT-5.4 Pro", + "created": 1772734366, + "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -15003,15 +22982,21 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000005", - "completion": "0.0000004", + "prompt": "0.00003", + "completion": "0.00018", "web_search": "0.01", - "input_cache_read": "0.00000001" + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00006", + "completion": "0.00027" + } + ] }, "top_provider": { - "context_length": 400000, - "max_completion_tokens": null, - "is_moderated": false + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -15019,6 +23004,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15033,86 +23019,47 @@ "presence_penalty": null, "repetition_penalty": null }, - "supported_voices": null, - "knowledge_cutoff": "2024-05-31", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1042, - "win_rate": 36.1, - "rank": 87 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1134, - "win_rate": 48.1, - "rank": 75 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1103, - "win_rate": 46.7, - "rank": 77 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1111, - "win_rate": 46.6, - "rank": 77 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1121, - "win_rate": 52, - "rank": 71 - }, - { - "arena": "models", - "category": "website", - "elo": 1144, - "win_rate": 48.9, - "rank": 75 - } - ] - }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" + }, "reasoning": { "mandatory": true, - "supported_efforts": ["high", "medium", "low", "minimal"], + "supported_efforts": ["xhigh", "high", "medium"], "default_effort": "medium" } }, { - "id": "openai/gpt-5-pro", - "canonical_slug": "openai/gpt-5-pro-2025-10-06", + "id": "openai/gpt-5.4-pro:batch", + "canonical_slug": "openai/gpt-5.4-pro-20260305", "hugging_face_id": "", - "name": "OpenAI: GPT-5 Pro", - "created": 1759776663, - "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...", - "context_length": 400000, + "name": "OpenAI: GPT-5.4 Pro (batch)", + "created": 1772734366, + "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { "prompt": "0.000015", - "completion": "0.00012", - "web_search": "0.01" + "completion": "0.00009", + "web_search": "0.01", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00003", + "completion": "0.000135" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, @@ -15121,6 +23068,7 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15130,52 +23078,63 @@ "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2024-09-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" }, "reasoning": { "mandatory": true, - "supported_efforts": ["high"], - "default_effort": "high" + "supported_efforts": ["xhigh", "high", "medium"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5.1", - "canonical_slug": "openai/gpt-5.1-20251113", + "id": "openai/gpt-5.4:batch", + "canonical_slug": "openai/gpt-5.4-20260305", "hugging_face_id": "", - "name": "OpenAI: GPT-5.1", - "created": 1763060305, - "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...", - "context_length": 400000, + "name": "OpenAI: GPT-5.4 (batch)", + "created": 1772734352, + "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { "prompt": "0.00000125", - "completion": "0.00001", + "completion": "0.0000075", "web_search": "0.01", - "input_cache_read": "0.00000013" + "input_cache_read": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000025", + "completion": "0.00001125", + "input_cache_read": "0.00000025" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15194,95 +23153,123 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints" + "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "mobileapps", - "elo": 1122, - "win_rate": 43.8, - "rank": 31 - }, { "arena": "models", "category": "3d", - "elo": 1139, - "win_rate": 43.9, - "rank": 67 + "elo": 1156, + "win_rate": 42.4, + "rank": 65 }, { "arena": "models", "category": "asciiart", - "elo": 1164, - "win_rate": 48.6, - "rank": 37 + "elo": 1233, + "win_rate": 55.5, + "rank": 16 }, { "arena": "models", "category": "codecategories", - "elo": 1220, - "win_rate": 53.1, - "rank": 42 + "elo": 1231, + "win_rate": 52.5, + "rank": 39 }, { "arena": "models", "category": "dataviz", - "elo": 1248, - "win_rate": 58, - "rank": 30 + "elo": 1258, + "win_rate": 56.6, + "rank": 27 }, { "arena": "models", "category": "gamedev", - "elo": 1244, - "win_rate": 55.9, - "rank": 33 + "elo": 1276, + "win_rate": 57.6, + "rank": 26 }, { "arena": "models", "category": "svg", - "elo": 1207, - "win_rate": 57.4, - "rank": 28 + "elo": 1229, + "win_rate": 57.9, + "rank": 17 }, { "arena": "models", "category": "uicomponent", - "elo": 1220, - "win_rate": 53, - "rank": 40 + "elo": 1268, + "win_rate": 57.5, + "rank": 28 }, { "arena": "models", "category": "website", - "elo": 1230, - "win_rate": 54.1, - "rank": 40 + "elo": 1231, + "win_rate": 52.5, + "rank": 42 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1066, + "win_rate": 47.4, + "rank": 35 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1054, + "win_rate": 40.8, + "rank": 35 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1135, + "win_rate": 46.9, + "rank": 22 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1141, + "win_rate": 46, + "rank": 33 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1100, + "win_rate": 39.3, + "rank": 32 } ], "artificial_analysis": { - "intelligence_index": 36.9, - "coding_index": 49.4, - "agentic_index": 21 + "intelligence_index": 53.1, + "coding_index": 71.1, + "agentic_index": 44.2 } }, "reasoning": { "mandatory": false, - "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "none"], - "default_effort": "none" + "default_enabled": false, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5.1-chat", - "canonical_slug": "openai/gpt-5.1-chat-20251113", + "id": "openai/gpt-5.5", + "canonical_slug": "openai/gpt-5.5-20260423", "hugging_face_id": "", - "name": "OpenAI: GPT-5.1 Chat", - "created": 1763060302, - "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", - "context_length": 128000, + "name": "OpenAI: GPT-5.5", + "created": 1777051893, + "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["file", "image", "text"], @@ -15291,63 +23278,23 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", - "web_search": "0.01", - "input_cache_read": "0.00000013" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 32000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "max_completion_tokens", - "max_tokens", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.1-chat-20251113/endpoints" - } - }, - { - "id": "openai/gpt-5.1-codex", - "canonical_slug": "openai/gpt-5.1-codex-20251113", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.1-Codex", - "created": 1763060298, - "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", - "context_length": 400000, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", + "prompt": "0.000005", + "completion": "0.00003", "web_search": "0.01", - "input_cache_read": "0.00000013" + "input_cache_read": "0.0000005", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00001", + "completion": "0.000045", + "input_cache_read": "0.000001" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ @@ -15355,6 +23302,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15370,102 +23318,212 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-12-01", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints" + "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1180, + "win_rate": 51.4, + "rank": 12 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1084, + "win_rate": 34.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1150, + "win_rate": 43.5, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1077, + "win_rate": 33.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1155, + "win_rate": 45.2, + "rank": 7 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1196, + "win_rate": 50.8, + "rank": 19 + }, { "arena": "agents", "category": "fullstack", - "elo": 1090, - "win_rate": 44.5, - "rank": 23 + "elo": 1124, + "win_rate": 43, + "rank": 25 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1213, + "win_rate": 52.4, + "rank": 10 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1084, + "win_rate": 34.2, + "rank": 19 }, { "arena": "agents", "category": "mobileapps", - "elo": 1198, - "win_rate": 54, - "rank": 15 + "elo": 1205, + "win_rate": 51.7, + "rank": 19 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1157, + "win_rate": 45.3, + "rank": 7 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1152, + "win_rate": 43.3, + "rank": 16 }, { "arena": "agents", "category": "webapps", - "elo": 1089, - "win_rate": 44.1, - "rank": 24 + "elo": 1158, + "win_rate": 42.7, + "rank": 28 + }, + { + "arena": "models", + "category": "3d", + "elo": 1250, + "win_rate": 52, + "rank": 35 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1286, + "win_rate": 61, + "rank": 8 }, { "arena": "models", "category": "codecategories", - "elo": 1200, - "win_rate": 55.2, - "rank": 53 + "elo": 1279, + "win_rate": 55.3, + "rank": 23 }, { "arena": "models", "category": "dataviz", - "elo": 1216, - "win_rate": 50.7, - "rank": 40 + "elo": 1281, + "win_rate": 56.6, + "rank": 17 }, { "arena": "models", "category": "gamedev", - "elo": 1205, - "win_rate": 52.3, - "rank": 45 + "elo": 1337, + "win_rate": 59.5, + "rank": 7 + }, + { + "arena": "models", + "category": "svg", + "elo": 1267, + "win_rate": 57.4, + "rank": 6 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1285, + "win_rate": 55.7, + "rank": 24 }, { "arena": "models", "category": "website", - "elo": 1204, - "win_rate": 56, - "rank": 54 + "elo": 1268, + "win_rate": 54.5, + "rank": 26 } - ] + ], + "artificial_analysis": { + "intelligence_index": 56.3, + "coding_index": 74.9, + "agentic_index": 47.4 + } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low"], + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.1-codex-max", - "canonical_slug": "openai/gpt-5.1-codex-max-20251204", + "id": "openai/gpt-5.5-pro", + "canonical_slug": "openai/gpt-5.5-pro-20260423", "hugging_face_id": "", - "name": "OpenAI: GPT-5.1-Codex-Max", - "created": 1764878934, - "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...", - "context_length": 400000, + "name": "OpenAI: GPT-5.5 Pro", + "created": 1777051896, + "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...", + "context_length": 1050000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00001", + "prompt": "0.00003", + "completion": "0.00018", "web_search": "0.01", - "input_cache_read": "0.000000125" + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00006", + "completion": "0.00027" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15481,49 +23539,55 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-12-01", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints" + "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" }, "reasoning": { "mandatory": true, - "supported_efforts": ["xhigh", "high", "medium", "low"], + "supported_efforts": ["xhigh", "high", "medium"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.1-codex-mini", - "canonical_slug": "openai/gpt-5.1-codex-mini-20251113", + "id": "openai/gpt-5.5-pro:batch", + "canonical_slug": "openai/gpt-5.5-pro-20260423", "hugging_face_id": "", - "name": "OpenAI: GPT-5.1-Codex-Mini", - "created": 1763057820, - "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", - "context_length": 400000, + "name": "OpenAI: GPT-5.5 Pro (batch)", + "created": 1777051896, + "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...", + "context_length": 1050000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.000002", + "prompt": "0.000015", + "completion": "0.00009", "web_search": "0.01", - "input_cache_read": "0.000000025" + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00003", + "completion": "0.000135" + } + ] }, "top_provider": { - "context_length": 400000, - "max_completion_tokens": 100000, + "context_length": 1050000, + "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15539,85 +23603,25 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-12-01", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1066, - "win_rate": 32.9, - "rank": 83 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1151, - "win_rate": 43, - "rank": 40 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1143, - "win_rate": 41.5, - "rank": 73 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1140, - "win_rate": 40.6, - "rank": 71 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1158, - "win_rate": 43.5, - "rank": 64 - }, - { - "arena": "models", - "category": "svg", - "elo": 1035, - "win_rate": 35.3, - "rank": 68 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1133, - "win_rate": 40.8, - "rank": 66 - }, - { - "arena": "models", - "category": "website", - "elo": 1153, - "win_rate": 42.8, - "rank": 72 - } - ] + "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" }, "reasoning": { - "mandatory": false, - "supported_efforts": ["high", "medium", "low"], + "mandatory": true, + "supported_efforts": ["xhigh", "high", "medium"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.2", - "canonical_slug": "openai/gpt-5.2-20251211", + "id": "openai/gpt-5.5:batch", + "canonical_slug": "openai/gpt-5.5-20260423", "hugging_face_id": "", - "name": "OpenAI: GPT-5.2", - "created": 1765389775, - "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...", - "context_length": 400000, + "name": "OpenAI: GPT-5.5 (batch)", + "created": 1777051893, + "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["file", "image", "text"], @@ -15626,22 +23630,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000175", - "completion": "0.000014", + "prompt": "0.0000025", + "completion": "0.000015", "web_search": "0.01", - "input_cache_read": "0.000000175" + "input_cache_read": "0.00000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000005", + "completion": "0.0000225", + "input_cache_read": "0.0000005" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -15657,337 +23669,217 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-12-01", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.2-20251211/endpoints" + "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" }, "benchmarks": { "design_arena": [ { - "arena": "models", - "category": "website", - "elo": 1237, - "win_rate": 54.5, - "rank": 35 + "arena": "agents", + "category": "agenticgamedev", + "elo": 1180, + "win_rate": 51.4, + "rank": 12 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1084, + "win_rate": 34.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1150, + "win_rate": 43.5, + "rank": 7 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1077, + "win_rate": 33.2, + "rank": 9 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1155, + "win_rate": 45.2, + "rank": 7 }, { "arena": "agents", "category": "androidnative", - "elo": 1071, - "win_rate": 49.2, - "rank": 23 + "elo": 1196, + "win_rate": 50.8, + "rank": 19 }, { "arena": "agents", "category": "fullstack", - "elo": 1108, - "win_rate": 44, - "rank": 21 + "elo": 1124, + "win_rate": 43, + "rank": 25 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1184, - "win_rate": 48.1, - "rank": 13 + "elo": 1213, + "win_rate": 52.4, + "rank": 10 }, { "arena": "agents", - "category": "mobileapps", - "elo": 1169, - "win_rate": 47.4, - "rank": 24 + "category": "htmlslides", + "elo": 1084, + "win_rate": 34.2, + "rank": 19 }, { "arena": "agents", - "category": "webapps", - "elo": 1158, - "win_rate": 45.7, + "category": "mobileapps", + "elo": 1205, + "win_rate": 51.7, "rank": 19 }, { - "arena": "models", - "category": "3d", + "arena": "agents", + "category": "pptxslides", "elo": 1157, - "win_rate": 41.7, - "rank": 61 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1218, - "win_rate": 49.9, - "rank": 44 + "win_rate": 45.3, + "rank": 7 }, { - "arena": "models", - "category": "dataviz", - "elo": 1245, - "win_rate": 56.1, - "rank": 31 + "arena": "agents", + "category": "python-pptxslides", + "elo": 1152, + "win_rate": 43.3, + "rank": 16 }, { - "arena": "models", - "category": "gamedev", - "elo": 1260, - "win_rate": 56, - "rank": 30 + "arena": "agents", + "category": "webapps", + "elo": 1158, + "win_rate": 42.7, + "rank": 28 }, { "arena": "models", - "category": "uicomponent", - "elo": 1242, - "win_rate": 51.5, - "rank": 33 + "category": "3d", + "elo": 1250, + "win_rate": 52, + "rank": 35 }, { "arena": "models", "category": "asciiart", - "elo": 1199, - "win_rate": 50.7, - "rank": 22 + "elo": 1286, + "win_rate": 61, + "rank": 8 }, { "arena": "models", - "category": "svg", - "elo": 1196, - "win_rate": 53.8, - "rank": 33 - } - ] - }, - "reasoning": { - "mandatory": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-5.2-chat", - "canonical_slug": "openai/gpt-5.2-chat-20251211", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.2 Chat", - "created": 1765389783, - "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", - "context_length": 128000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000175", - "completion": "0.000014", - "web_search": "0.01", - "input_cache_read": "0.000000175" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "max_completion_tokens", - "max_tokens", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": "2026-08-10", - "links": { - "details": "/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints" - } - }, - { - "id": "openai/gpt-5.2-codex", - "canonical_slug": "openai/gpt-5.2-codex-20260114", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.2-Codex", - "created": 1768409315, - "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", - "context_length": 400000, - "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000175", - "completion": "0.000014", - "web_search": "0.01", - "input_cache_read": "0.000000175" - }, - "top_provider": { - "context_length": 400000, - "max_completion_tokens": 128000, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_completion_tokens", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints" - }, - "benchmarks": { - "design_arena": [ + "category": "codecategories", + "elo": 1279, + "win_rate": 55.3, + "rank": 23 + }, { - "arena": "agents", - "category": "androidnative", - "elo": 1176, - "win_rate": 47.5, - "rank": 15 + "arena": "models", + "category": "dataviz", + "elo": 1281, + "win_rate": 56.6, + "rank": 17 }, { - "arena": "agents", - "category": "fullstack", - "elo": 1058, - "win_rate": 37, - "rank": 27 + "arena": "models", + "category": "gamedev", + "elo": 1337, + "win_rate": 59.5, + "rank": 7 }, { - "arena": "agents", - "category": "godotgamedev", - "elo": 1187, - "win_rate": 48, - "rank": 12 + "arena": "models", + "category": "svg", + "elo": 1267, + "win_rate": 57.4, + "rank": 6 }, { - "arena": "agents", - "category": "mobileapps", - "elo": 1168, - "win_rate": 47.7, - "rank": 25 + "arena": "models", + "category": "uicomponent", + "elo": 1285, + "win_rate": 55.7, + "rank": 24 }, { - "arena": "agents", - "category": "webapps", - "elo": 1128, - "win_rate": 40.5, - "rank": 22 + "arena": "models", + "category": "website", + "elo": 1268, + "win_rate": 54.5, + "rank": 26 } - ] + ], + "artificial_analysis": { + "intelligence_index": 56.3, + "coding_index": 74.9, + "agentic_index": 47.4 + } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["xhigh", "high", "medium", "low"], + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.2-pro", - "canonical_slug": "openai/gpt-5.2-pro-20251211", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.2 Pro", - "created": 1765389780, - "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...", - "context_length": 400000, + "id": "openai/gpt-5.6-luna", + "canonical_slug": "openai/gpt-5.6-luna-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Luna", + "created": 1783590864, + "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000021", - "completion": "0.000168", - "web_search": "0.01" + "prompt": "0.0000001", + "completion": "0.0000006", + "web_search": "0.01", + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.0000009", + "input_cache_read": "0.00000002", + "input_cache_write": "0.00000025" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints" - }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["xhigh", "high", "medium"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-5.3-chat", - "canonical_slug": "openai/gpt-5.3-chat-20260303", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.3 Chat", - "created": 1772564061, - "description": "GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...", - "context_length": 128000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000175", - "completion": "0.000014", - "web_search": "0.01", - "input_cache_read": "0.000000175" - }, - "top_provider": { - "context_length": 128000, - "max_completion_tokens": 16384, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ "max_completion_tokens", "max_tokens", + "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16003,35 +23895,59 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.3-chat-20260303/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 52.3, + "coding_index": 71.4, + "agentic_index": 46.9 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" } }, { - "id": "openai/gpt-5.3-codex", - "canonical_slug": "openai/gpt-5.3-codex-20260224", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.3-Codex", - "created": 1771959164, - "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...", - "context_length": 400000, + "id": "openai/gpt-5.6-luna-pro", + "canonical_slug": "openai/gpt-5.6-luna-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Luna Pro", + "created": 1783590867, + "description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00000175", - "completion": "0.000014", + "prompt": "0.0000001", + "completion": "0.0000006", "web_search": "0.01", - "input_cache_read": "0.000000175" + "input_cache_read": "0.00000001", + "input_cache_write": "0.000000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.0000009", + "input_cache_read": "0.00000002", + "input_cache_write": "0.00000025" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, @@ -16041,6 +23957,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16056,132 +23973,113 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2026-02-16", "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "androidnative", - "elo": 1084, - "win_rate": 35.2, - "rank": 21 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1049, - "win_rate": 36.4, - "rank": 28 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1166, - "win_rate": 45.1, - "rank": 15 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1129, - "win_rate": 41.6, - "rank": 28 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1119, - "win_rate": 39.1, - "rank": 23 - }, - { - "arena": "models", - "category": "3d", - "elo": 1086, - "win_rate": 35.3, - "rank": 78 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1197, - "win_rate": 51.2, - "rank": 25 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1194, - "win_rate": 47.3, - "rank": 54 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1205, - "win_rate": 50.4, - "rank": 47 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1226, - "win_rate": 51.2, - "rank": 40 - }, - { - "arena": "models", - "category": "svg", - "elo": 1187, - "win_rate": 54, - "rank": 37 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1191, - "win_rate": 47.3, - "rank": 52 - }, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-luna-pro:batch", + "canonical_slug": "openai/gpt-5.6-luna-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Luna Pro (batch)", + "created": 1783590867, + "description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000006", + "web_search": "0.01", + "input_cache_read": "0.00000001", + "overrides": [ { - "arena": "models", - "category": "website", - "elo": 1205, - "win_rate": 48.7, - "rank": 53 + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.0000009", + "input_cache_read": "0.00000002" } ] }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints" + }, "reasoning": { "mandatory": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.4", - "canonical_slug": "openai/gpt-5.4-20260305", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.4", - "created": 1772734352, - "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...", + "id": "openai/gpt-5.6-luna:batch", + "canonical_slug": "openai/gpt-5.6-luna-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Luna (batch)", + "created": 1783590864, + "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000025", - "completion": "0.000015", + "prompt": "0.0000001", + "completion": "0.0000006", "web_search": "0.01", - "input_cache_read": "0.00000025" + "input_cache_read": "0.00000001", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.0000002", + "completion": "0.0000009", + "input_cache_read": "0.00000002" + } + ] }, "top_provider": { "context_length": 1050000, @@ -16191,9 +24089,9 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16209,158 +24107,74 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1178, - "win_rate": 42.4, - "rank": 51 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1245, - "win_rate": 55.2, - "rank": 10 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1261, - "win_rate": 52.8, - "rank": 29 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1276, - "win_rate": 56.5, - "rank": 19 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1306, - "win_rate": 57.9, - "rank": 14 - }, - { - "arena": "models", - "category": "svg", - "elo": 1252, - "win_rate": 57.9, - "rank": 14 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1293, - "win_rate": 57.6, - "rank": 18 - }, - { - "arena": "models", - "category": "website", - "elo": 1263, - "win_rate": 52.8, - "rank": 28 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1038, - "win_rate": 47.4, - "rank": 27 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1083, - "win_rate": 40.8, - "rank": 24 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1177, - "win_rate": 46.9, - "rank": 14 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1149, - "win_rate": 44.4, - "rank": 26 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1139, - "win_rate": 41.7, - "rank": 20 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 51.4, - "coding_index": 71.1, - "agentic_index": 41.1 + "intelligence_index": 52.3, + "coding_index": 71.4, + "agentic_index": 46.9 } }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.4-image-2", - "canonical_slug": "openai/gpt-5.4-image-2-20260421", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.4 Image 2", - "created": 1776797528, - "description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...", - "context_length": 272000, + "id": "openai/gpt-5.6-sol", + "canonical_slug": "openai/gpt-5.6-sol-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol", + "created": 1783590850, + "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...", + "context_length": 1050000, "architecture": { - "modality": "text+image+file->text+image", - "input_modalities": ["image", "text", "file"], - "output_modalities": ["image", "text"], + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000008", - "completion": "0.000015", + "prompt": "0.000005", + "completion": "0.00003", "web_search": "0.01", - "input_cache_read": "0.000002" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00001", + "completion": "0.000045", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125" + } + ] }, "top_provider": { - "context_length": 272000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", + "max_completion_tokens", "max_tokens", - "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "top_logprobs" + "tool_choice", + "tools" ], "default_parameters": { "temperature": null, @@ -16371,26 +24185,34 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 60.9, + "coding_index": 77.4, + "agentic_index": 57.8 + } }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.4-mini", - "canonical_slug": "openai/gpt-5.4-mini-20260317", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.4 Mini", - "created": 1773748178, - "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...", - "context_length": 400000, + "id": "openai/gpt-5.6-sol-pro", + "canonical_slug": "openai/gpt-5.6-sol-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol Pro", + "created": 1783590854, + "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["file", "image", "text"], @@ -16399,13 +24221,23 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000075", - "completion": "0.0000045", + "prompt": "0.000005", + "completion": "0.00003", "web_search": "0.01", - "input_cache_read": "0.000000075" + "input_cache_read": "0.0000005", + "input_cache_write": "0.00000625", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00001", + "completion": "0.000045", + "input_cache_read": "0.000001", + "input_cache_write": "0.0000125" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, "is_moderated": true }, @@ -16415,6 +24247,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16430,34 +24263,26 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-08-31", + "knowledge_cutoff": "2026-02-16", "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 40, - "coding_index": 56.1, - "agentic_index": 30.2 - } + "links": { + "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.4-nano", - "canonical_slug": "openai/gpt-5.4-nano-20260317", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.4 Nano", - "created": 1773748187, - "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...", - "context_length": 400000, + "id": "openai/gpt-5.6-sol-pro:batch", + "canonical_slug": "openai/gpt-5.6-sol-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol Pro (batch)", + "created": 1783590854, + "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["file", "image", "text"], @@ -16466,22 +24291,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.00000125", + "prompt": "0.0000025", + "completion": "0.000015", "web_search": "0.01", - "input_cache_read": "0.00000002" + "input_cache_read": "0.00000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000005", + "completion": "0.0000225", + "input_cache_read": "0.0000005" + } + ] }, "top_provider": { - "context_length": 400000, + "context_length": 1050000, "max_completion_tokens": 128000, - "is_moderated": false + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16497,45 +24330,46 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-08-31", + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 38.2, - "coding_index": 56.1, - "agentic_index": 27.5 - } + "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints" }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.4-pro", - "canonical_slug": "openai/gpt-5.4-pro-20260305", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.4 Pro", - "created": 1772734366, - "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...", + "id": "openai/gpt-5.6-sol:batch", + "canonical_slug": "openai/gpt-5.6-sol-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Sol (batch)", + "created": 1783590850, + "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], + "input_modalities": ["file", "image", "text"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00003", - "completion": "0.00018", - "web_search": "0.01" + "prompt": "0.0000025", + "completion": "0.000015", + "web_search": "0.01", + "input_cache_read": "0.00000025", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000005", + "completion": "0.0000225", + "input_cache_read": "0.0000005" + } + ] }, "top_provider": { "context_length": 1050000, @@ -16545,9 +24379,9 @@ "per_request_limits": null, "supported_parameters": [ "include_reasoning", - "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16563,24 +24397,33 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 60.9, + "coding_index": 77.4, + "agentic_index": 57.8 + } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["xhigh", "high", "medium"], + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.5", - "canonical_slug": "openai/gpt-5.5-20260423", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.5", - "created": 1777051893, - "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...", + "id": "openai/gpt-5.6-terra", + "canonical_slug": "openai/gpt-5.6-terra-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Terra", + "created": 1783590857, + "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -16590,10 +24433,20 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000005", - "completion": "0.00003", + "prompt": "0.000001", + "completion": "0.000006", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.000009", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025" + } + ] }, "top_provider": { "context_length": 1050000, @@ -16606,6 +24459,7 @@ "max_completion_tokens", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16621,181 +24475,170 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-12-01", + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1202, - "win_rate": 53, - "rank": 5 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1084, - "win_rate": 34.2, - "rank": 9 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1150, - "win_rate": 43.5, - "rank": 7 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1077, - "win_rate": 33.2, - "rank": 9 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1155, - "win_rate": 45.2, - "rank": 7 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1261, - "win_rate": 55.4, - "rank": 4 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1151, - "win_rate": 44.2, - "rank": 15 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1215, - "win_rate": 53, - "rank": 10 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1086, - "win_rate": 34.6, - "rank": 11 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1219, - "win_rate": 50.9, - "rank": 11 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1157, - "win_rate": 45.3, - "rank": 7 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1152, - "win_rate": 43.3, - "rank": 9 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1183, - "win_rate": 45.2, - "rank": 18 - }, - { - "arena": "models", - "category": "3d", - "elo": 1266, - "win_rate": 53.3, - "rank": 28 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1308, - "win_rate": 61.9, - "rank": 5 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1296, - "win_rate": 56.6, - "rank": 16 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1299, - "win_rate": 58, - "rank": 9 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1348, - "win_rate": 62.8, - "rank": 3 - }, - { - "arena": "models", - "category": "svg", - "elo": 1284, - "win_rate": 60, - "rank": 5 - }, + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 56.6, + "coding_index": 76.7, + "agentic_index": 50.2 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-terra-pro", + "canonical_slug": "openai/gpt-5.6-terra-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Terra Pro", + "created": 1783590861, + "description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000006", + "web_search": "0.01", + "input_cache_read": "0.0000001", + "input_cache_write": "0.00000125", + "overrides": [ { - "arena": "models", - "category": "uicomponent", - "elo": 1300, - "win_rate": 57, - "rank": 16 - }, + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.000009", + "input_cache_read": "0.0000002", + "input_cache_write": "0.0000025" + } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints" + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], + "default_effort": "medium" + } + }, + { + "id": "openai/gpt-5.6-terra-pro:batch", + "canonical_slug": "openai/gpt-5.6-terra-pro-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Terra Pro (batch)", + "created": 1783590861, + "description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode", + "context_length": 1050000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["file", "image", "text"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000006", + "web_search": "0.01", + "input_cache_read": "0.0000001", + "overrides": [ { - "arena": "models", - "category": "website", - "elo": 1289, - "win_rate": 55.8, - "rank": 20 + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.000009", + "input_cache_read": "0.0000002" } - ], - "artificial_analysis": { - "intelligence_index": 54.8, - "coding_index": 74.9, - "agentic_index": 44.9 - } + ] + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "reasoning_effort", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2026-02-16", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints" }, "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["xhigh", "high", "medium", "low", "none"], + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, { - "id": "openai/gpt-5.5-pro", - "canonical_slug": "openai/gpt-5.5-pro-20260423", - "hugging_face_id": "", - "name": "OpenAI: GPT-5.5 Pro", - "created": 1777051896, - "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...", + "id": "openai/gpt-5.6-terra:batch", + "canonical_slug": "openai/gpt-5.6-terra-20260709", + "hugging_face_id": null, + "name": "OpenAI: GPT-5.6 Terra (batch)", + "created": 1783590857, + "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...", "context_length": 1050000, "architecture": { "modality": "text+image+file->text", @@ -16805,9 +24648,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00003", - "completion": "0.00018", - "web_search": "0.01" + "prompt": "0.000001", + "completion": "0.000006", + "web_search": "0.01", + "input_cache_read": "0.0000001", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.000002", + "completion": "0.000009", + "input_cache_read": "0.0000002" + } + ] }, "top_provider": { "context_length": 1050000, @@ -16819,6 +24671,7 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -16834,14 +24687,23 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-12-01", + "knowledge_cutoff": "2026-02-16", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints" + "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 56.6, + "coding_index": 76.7, + "agentic_index": 50.2 + } }, "reasoning": { - "mandatory": true, - "supported_efforts": ["xhigh", "high", "medium"], + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high", "medium", "low", "none"], "default_effort": "medium" } }, @@ -16863,7 +24725,8 @@ "pricing": { "prompt": "0.0000025", "completion": "0.00001", - "audio": "0.000032" + "audio": "0.000032", + "audio_output": "0.000064" }, "top_provider": { "context_length": 128000, @@ -16920,7 +24783,8 @@ "pricing": { "prompt": "0.0000006", "completion": "0.0000024", - "audio": "0.0000006" + "audio": "0.0000006", + "audio_output": "0.0000024" }, "top_provider": { "context_length": 128000, @@ -16984,18 +24848,12 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", - "logprobs", "max_tokens", - "presence_penalty", "response_format", "seed", - "stop", "structured_outputs", "tool_choice", - "tools", - "top_logprobs" + "tools" ], "default_parameters": { "temperature": null, @@ -17029,7 +24887,8 @@ }, "pricing": { "prompt": "0.00000003", - "completion": "0.00000015" + "completion": "0.00000017", + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 131072, @@ -17046,6 +24905,7 @@ "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -17075,157 +24935,50 @@ { "arena": "models", "category": "3d", - "elo": 978, - "win_rate": 29.4, - "rank": 91 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1012, - "win_rate": 33.4, - "rank": 98 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1043, - "win_rate": 45.1, - "rank": 87 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1059, - "win_rate": 40.6, - "rank": 85 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 978, - "win_rate": 35.5, - "rank": 92 - }, - { - "arena": "models", - "category": "website", - "elo": 1011, - "win_rate": 32.5, - "rank": 100 - } - ], - "artificial_analysis": { - "intelligence_index": 23.8, - "coding_index": 30.4, - "agentic_index": 13.2 - } - }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low"], - "default_effort": "medium" - } - }, - { - "id": "openai/gpt-oss-120b:free", - "canonical_slug": "openai/gpt-oss-120b", - "hugging_face_id": "openai/gpt-oss-120b", - "name": "OpenAI: gpt-oss-120b (free)", - "created": 1754414231, - "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...", - "context_length": 131072, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "GPT", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, - "is_moderated": true - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "min_p", - "reasoning", - "seed", - "stop", - "temperature", - "tool_choice", - "tools", - "top_a", - "top_k", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2024-06-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/openai/gpt-oss-120b/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 978, + "elo": 954, "win_rate": 29.4, - "rank": 91 + "rank": 103 }, { "arena": "models", "category": "codecategories", - "elo": 1012, + "elo": 982, "win_rate": 33.4, - "rank": 98 + "rank": 110 }, { "arena": "models", "category": "dataviz", - "elo": 1043, - "win_rate": 45.1, - "rank": 87 + "elo": 1009, + "win_rate": 43.6, + "rank": 102 }, { "arena": "models", "category": "gamedev", - "elo": 1059, - "win_rate": 40.6, - "rank": 85 + "elo": 1030, + "win_rate": 40.5, + "rank": 102 }, { - "arena": "models", - "category": "uicomponent", - "elo": 978, - "win_rate": 35.5, - "rank": 92 + "arena": "models", + "category": "uicomponent", + "elo": 955, + "win_rate": 35.7, + "rank": 105 }, { "arena": "models", "category": "website", - "elo": 1011, + "elo": 979, "win_rate": 32.5, - "rank": 100 + "rank": 114 } ], "artificial_analysis": { - "intelligence_index": 23.8, + "intelligence_index": 24.1, "coding_index": 30.4, - "agentic_index": 13.2 + "agentic_index": 13.4 } }, "reasoning": { @@ -17250,12 +25003,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000029", - "completion": "0.00000014" + "prompt": "0.00000003", + "completion": "0.00000013", + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": null, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -17268,6 +25022,7 @@ "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -17296,20 +25051,20 @@ { "arena": "models", "category": "dataviz", - "elo": 977, + "elo": 954, "win_rate": 39.7, - "rank": 93 + "rank": 106 }, { "arena": "models", "category": "website", - "elo": 895, + "elo": 863, "win_rate": 27.9, - "rank": 108 + "rank": 122 } ], "artificial_analysis": { - "intelligence_index": 14.9, + "intelligence_index": 15.2, "coding_index": 20.7, "agentic_index": 3.1 } @@ -17350,9 +25105,9 @@ "include_reasoning", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -17361,7 +25116,6 @@ "temperature", "tool_choice", "tools", - "top_a", "top_k", "top_logprobs", "top_p" @@ -17382,20 +25136,20 @@ { "arena": "models", "category": "dataviz", - "elo": 977, + "elo": 954, "win_rate": 39.7, - "rank": 93 + "rank": 106 }, { "arena": "models", "category": "website", - "elo": 895, + "elo": 863, "win_rate": 27.9, - "rank": 108 + "rank": 122 } ], "artificial_analysis": { - "intelligence_index": 14.9, + "intelligence_index": 15.2, "coding_index": 20.7, "agentic_index": 3.1 } @@ -17445,11 +25199,7 @@ "tools", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, @@ -17555,39 +25305,289 @@ "reasoning", "response_format", "seed", - "structured_outputs" + "structured_outputs" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-10-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o1-pro/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "openai/o1-pro:batch", + "canonical_slug": "openai/o1-pro", + "hugging_face_id": "", + "name": "OpenAI: o1-pro (batch)", + "created": 1742423211, + "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...", + "context_length": 200000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000075", + "completion": "0.0003", + "web_search": "0.01" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-10-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o1-pro/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "openai/o1:batch", + "canonical_slug": "openai/o1-2024-12-17", + "hugging_face_id": "", + "name": "OpenAI: o1 (batch)", + "created": 1734459999, + "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...", + "context_length": 200000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000075", + "completion": "0.00003", + "web_search": "0.01", + "input_cache_read": "0.00000375" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2023-10-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o1-2024-12-17/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": null, + "coding_index": 39.7, + "agentic_index": null + } + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "openai/o3", + "canonical_slug": "openai/o3-2025-04-16", + "hugging_face_id": "", + "name": "OpenAI: o3", + "created": 1744823457, + "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....", + "context_length": 200000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000002", + "completion": "0.000008", + "web_search": "0.01", + "input_cache_read": "0.0000005" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1039, + "win_rate": 51.9, + "rank": 101 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1200, + "win_rate": 48.1, + "rank": 49 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1072, + "win_rate": 56.9, + "rank": 94 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1045, + "win_rate": 53.3, + "rank": 93 + }, + { + "arena": "models", + "category": "website", + "elo": 1047, + "win_rate": 53.8, + "rank": 104 + } + ] + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "openai/o3-mini", + "canonical_slug": "openai/o3-mini-2025-01-31", + "hugging_face_id": "", + "name": "OpenAI: o3 Mini", + "created": 1738351721, + "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...", + "context_length": 200000, + "architecture": { + "modality": "text+file->text", + "input_modalities": ["text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000011", + "completion": "0.0000044", + "web_search": "0.01", + "input_cache_read": "0.00000055" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o1-pro/endpoints" + "details": "/api/v1/models/openai/o3-mini-2025-01-31/endpoints" }, "reasoning": { "mandatory": false } }, { - "id": "openai/o3", - "canonical_slug": "openai/o3-2025-04-16", + "id": "openai/o3-mini-high", + "canonical_slug": "openai/o3-mini-high-2025-01-31", "hugging_face_id": "", - "name": "OpenAI: o3", - "created": 1744823457, - "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....", + "name": "OpenAI: o3 Mini High", + "created": 1739372611, + "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", "context_length": 200000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "modality": "text+file->text", + "input_modalities": ["text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000008", + "prompt": "0.0000011", + "completion": "0.0000044", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.00000055" }, "top_provider": { "context_length": 200000, @@ -17599,82 +25599,58 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", "tool_choice", "tools" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" + "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1069, - "win_rate": 51.9, - "rank": 86 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1200, - "win_rate": 48.1, - "rank": 50 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1100, - "win_rate": 56.9, - "rank": 79 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1071, - "win_rate": 53.3, - "rank": 80 - }, - { - "arena": "models", - "category": "website", - "elo": 1079, - "win_rate": 53.8, - "rank": 88 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 15.7, + "coding_index": 16.3, + "agentic_index": 1.7 + } }, "reasoning": { - "mandatory": false + "mandatory": true, + "supported_efforts": ["high"], + "default_effort": "high" } }, { - "id": "openai/o3-deep-research", - "canonical_slug": "openai/o3-deep-research-2025-06-26", + "id": "openai/o3-mini-high:batch", + "canonical_slug": "openai/o3-mini-high-2025-01-31", "hugging_face_id": "", - "name": "OpenAI: o3 Deep Research", - "created": 1760129661, - "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", + "name": "OpenAI: o3 Mini High (batch)", + "created": 1739372611, + "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", "context_length": 200000, "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["image", "text", "file"], + "modality": "text+file->text", + "input_modalities": ["text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.00001", - "completion": "0.00004", + "prompt": "0.00000055", + "completion": "0.0000022", "web_search": "0.01", - "input_cache_read": "0.0000025" + "input_cache_read": "0.000000275" }, "top_provider": { "context_length": 200000, @@ -17683,22 +25659,15 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], "default_parameters": { "temperature": null, @@ -17706,20 +25675,30 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2023-10-31", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o3-deep-research-2025-06-26/endpoints" + "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 15.7, + "coding_index": 16.3, + "agentic_index": 1.7 + } }, "reasoning": { - "mandatory": false + "mandatory": true, + "supported_efforts": ["high"], + "default_effort": "high" } }, { - "id": "openai/o3-mini", + "id": "openai/o3-mini:batch", "canonical_slug": "openai/o3-mini-2025-01-31", "hugging_face_id": "", - "name": "OpenAI: o3 Mini", + "name": "OpenAI: o3 Mini (batch)", "created": 1738351721, "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...", "context_length": 200000, @@ -17731,10 +25710,10 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", + "prompt": "0.00000055", + "completion": "0.0000022", "web_search": "0.01", - "input_cache_read": "0.00000055" + "input_cache_read": "0.000000275" }, "top_provider": { "context_length": 200000, @@ -17771,25 +25750,24 @@ } }, { - "id": "openai/o3-mini-high", - "canonical_slug": "openai/o3-mini-high-2025-01-31", + "id": "openai/o3-pro", + "canonical_slug": "openai/o3-pro-2025-06-10", "hugging_face_id": "", - "name": "OpenAI: o3 Mini High", - "created": 1739372611, - "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", + "name": "OpenAI: o3 Pro", + "created": 1749598352, + "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...", "context_length": 200000, "architecture": { - "modality": "text+file->text", - "input_modalities": ["text", "file"], + "modality": "text+image+file->text", + "input_modalities": ["text", "file", "image"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", - "web_search": "0.01", - "input_cache_read": "0.00000055" + "prompt": "0.00002", + "completion": "0.00008", + "web_search": "0.01" }, "top_provider": { "context_length": 200000, @@ -17813,30 +25791,20 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2023-10-31", + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 15.6, - "coding_index": 16.3, - "agentic_index": 1.7 - } + "details": "/api/v1/models/openai/o3-pro-2025-06-10/endpoints" }, "reasoning": { - "mandatory": true, - "supported_efforts": ["high"], - "default_effort": "high" + "mandatory": false } }, { - "id": "openai/o3-pro", + "id": "openai/o3-pro:batch", "canonical_slug": "openai/o3-pro-2025-06-10", "hugging_face_id": "", - "name": "OpenAI: o3 Pro", + "name": "OpenAI: o3 Pro (batch)", "created": 1749598352, "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...", "context_length": 200000, @@ -17848,8 +25816,8 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00002", - "completion": "0.00008", + "prompt": "0.00001", + "completion": "0.00004", "web_search": "0.01" }, "top_provider": { @@ -17883,6 +25851,93 @@ "mandatory": false } }, + { + "id": "openai/o3:batch", + "canonical_slug": "openai/o3-2025-04-16", + "hugging_face_id": "", + "name": "OpenAI: o3 (batch)", + "created": 1744823457, + "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....", + "context_length": 200000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000001", + "completion": "0.000004", + "web_search": "0.01", + "input_cache_read": "0.00000025" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o3-2025-04-16/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1039, + "win_rate": 51.9, + "rank": 101 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1200, + "win_rate": 48.1, + "rank": 49 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1072, + "win_rate": 56.9, + "rank": 94 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1045, + "win_rate": 53.3, + "rank": 93 + }, + { + "arena": "models", + "category": "website", + "elo": 1047, + "win_rate": 53.8, + "rank": 104 + } + ] + }, + "reasoning": { + "mandatory": false + } + }, { "id": "openai/o4-mini", "canonical_slug": "openai/o4-mini-2025-04-16", @@ -17932,44 +25987,44 @@ { "arena": "models", "category": "3d", - "elo": 931, + "elo": 907, "win_rate": 34, - "rank": 95 + "rank": 107 }, { "arena": "models", "category": "codecategories", - "elo": 1025, + "elo": 995, "win_rate": 46.4, - "rank": 95 + "rank": 108 }, { "arena": "models", "category": "dataviz", - "elo": 1034, + "elo": 1012, "win_rate": 50, - "rank": 88 + "rank": 101 }, { "arena": "models", "category": "gamedev", - "elo": 1069, + "elo": 1041, "win_rate": 50, - "rank": 83 + "rank": 100 }, { "arena": "models", "category": "uicomponent", - "elo": 1038, + "elo": 1012, "win_rate": 46.9, - "rank": 84 + "rank": 98 }, { "arena": "models", "category": "website", - "elo": 1028, + "elo": 996, "win_rate": 47.1, - "rank": 97 + "rank": 112 } ] }, @@ -17978,25 +26033,25 @@ } }, { - "id": "openai/o4-mini-deep-research", - "canonical_slug": "openai/o4-mini-deep-research-2025-06-26", + "id": "openai/o4-mini-high", + "canonical_slug": "openai/o4-mini-high-2025-04-16", "hugging_face_id": "", - "name": "OpenAI: o4 Mini Deep Research", - "created": 1760129642, - "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", + "name": "OpenAI: o4 Mini High", + "created": 1744824212, + "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...", "context_length": 200000, "architecture": { "modality": "text+image+file->text", - "input_modalities": ["file", "image", "text"], + "input_modalities": ["image", "text", "file"], "output_modalities": ["text"], "tokenizer": "GPT", "instruct_type": null }, "pricing": { - "prompt": "0.000002", - "completion": "0.000008", + "prompt": "0.0000011", + "completion": "0.0000044", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.000000275" }, "top_provider": { "context_length": 200000, @@ -18005,22 +26060,15 @@ }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", - "stop", "structured_outputs", - "temperature", "tool_choice", - "tools", - "top_logprobs", - "top_p" + "tools" ], "default_parameters": { "temperature": null, @@ -18028,20 +26076,22 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/openai/o4-mini-deep-research-2025-06-26/endpoints" + "details": "/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": true, + "supported_efforts": ["high"], + "default_effort": "high" } }, { - "id": "openai/o4-mini-high", + "id": "openai/o4-mini-high:batch", "canonical_slug": "openai/o4-mini-high-2025-04-16", "hugging_face_id": "", - "name": "OpenAI: o4 Mini High", + "name": "OpenAI: o4 Mini High (batch)", "created": 1744824212, "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...", "context_length": 200000, @@ -18053,10 +26103,10 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000011", - "completion": "0.0000044", + "prompt": "0.00000055", + "completion": "0.0000022", "web_search": "0.01", - "input_cache_read": "0.000000275" + "input_cache_read": "0.0000001375" }, "top_provider": { "context_length": 200000, @@ -18068,6 +26118,7 @@ "include_reasoning", "max_tokens", "reasoning", + "reasoning_effort", "response_format", "seed", "structured_outputs", @@ -18091,6 +26142,100 @@ "default_effort": "high" } }, + { + "id": "openai/o4-mini:batch", + "canonical_slug": "openai/o4-mini-2025-04-16", + "hugging_face_id": "", + "name": "OpenAI: o4 Mini (batch)", + "created": 1744820942, + "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...", + "context_length": 200000, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["image", "text", "file"], + "output_modalities": ["text"], + "tokenizer": "GPT", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000055", + "completion": "0.0000022", + "web_search": "0.01", + "input_cache_read": "0.0000001375" + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/openai/o4-mini-2025-04-16/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 907, + "win_rate": 34, + "rank": 107 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 995, + "win_rate": 46.4, + "rank": 108 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1012, + "win_rate": 50, + "rank": 101 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1041, + "win_rate": 50, + "rank": 100 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1012, + "win_rate": 46.9, + "rank": 98 + }, + { + "arena": "models", + "category": "website", + "elo": 996, + "win_rate": 47.1, + "rank": 112 + } + ] + }, + "reasoning": { + "mandatory": false + } + }, { "id": "perceptron/perceptron-mk1", "canonical_slug": "perceptron/perceptron-mk1-20260512", @@ -18378,122 +26523,17 @@ "details": "/api/v1/models/perplexity/sonar-reasoning-pro/endpoints" }, "reasoning": { - "mandatory": false - } - }, - { - "id": "poolside/laguna-m.1", - "canonical_slug": "poolside/laguna-m.1-20260312", - "hugging_face_id": "poolside/Laguna-M.1", - "name": "Poolside: Laguna M.1", - "created": 1777388504, - "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0.0000002", - "completion": "0.0000004", - "input_cache_read": "0.0000001" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/poolside/laguna-m.1-20260312/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "poolside/laguna-m.1:free", - "canonical_slug": "poolside/laguna-m.1-20260312", - "hugging_face_id": "poolside/Laguna-M.1", - "name": "Poolside: Laguna M.1 (free)", - "created": 1777388504, - "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "max_tokens", - "reasoning", - "temperature", - "tool_choice", - "tools" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/poolside/laguna-m.1-20260312/endpoints" - }, - "reasoning": { - "mandatory": false, - "default_enabled": true - } - }, - { - "id": "poolside/laguna-xs-2.1", - "canonical_slug": "poolside/laguna-xs-2.1-20260625", - "hugging_face_id": "poolside/Laguna-XS-2.1", - "name": "Poolside: Laguna XS 2.1", - "created": 1783002429, - "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", - "context_length": 262144, + "mandatory": false + } + }, + { + "id": "poolside/laguna-s-2.1", + "canonical_slug": "poolside/laguna-s-2.1-20260720", + "hugging_face_id": "poolside/Laguna-S-2.1", + "name": "Poolside: Laguna S 2.1", + "created": 1784652683, + "description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...", + "context_length": 1048576, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -18502,13 +26542,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000006", - "completion": "0.00000012", - "input_cache_read": "0.00000003" + "prompt": "0.00000009", + "completion": "0.00000018", + "input_cache_read": "0.000000009" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 32768, + "context_length": 1048576, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -18520,19 +26560,12 @@ "tool_choice", "tools" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.9, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" + "details": "/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints" }, "reasoning": { "mandatory": false, @@ -18540,12 +26573,12 @@ } }, { - "id": "poolside/laguna-xs-2.1:free", - "canonical_slug": "poolside/laguna-xs-2.1-20260625", - "hugging_face_id": "poolside/Laguna-XS-2.1", - "name": "Poolside: Laguna XS 2.1 (free)", - "created": 1783002429, - "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", + "id": "poolside/laguna-s-2.1:free", + "canonical_slug": "poolside/laguna-s-2.1-20260720", + "hugging_face_id": "poolside/Laguna-S-2.1", + "name": "Poolside: Laguna S 2.1 (free)", + "created": 1784652683, + "description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -18572,19 +26605,12 @@ "tool_choice", "tools" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.9, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" + "details": "/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints" }, "reasoning": { "mandatory": false, @@ -18592,12 +26618,12 @@ } }, { - "id": "poolside/laguna-xs.2", - "canonical_slug": "poolside/laguna-xs.2-20260421", - "hugging_face_id": "poolside/Laguna-XS.2", - "name": "Poolside: Laguna XS.2", - "created": 1777389604, - "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...", + "id": "poolside/laguna-xs-2.1", + "canonical_slug": "poolside/laguna-xs-2.1-20260625", + "hugging_face_id": "poolside/Laguna-XS-2.1", + "name": "Poolside: Laguna XS 2.1", + "created": 1783002429, + "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -18607,9 +26633,9 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000002", - "input_cache_read": "0.00000005" + "prompt": "0.00000006", + "completion": "0.00000012", + "input_cache_read": "0.00000003" }, "top_provider": { "context_length": 262144, @@ -18625,19 +26651,12 @@ "tool_choice", "tools" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.9, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-07-09", + "expiration_date": null, "links": { - "details": "/api/v1/models/poolside/laguna-xs.2-20260421/endpoints" + "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" }, "reasoning": { "mandatory": false, @@ -18645,12 +26664,12 @@ } }, { - "id": "poolside/laguna-xs.2:free", - "canonical_slug": "poolside/laguna-xs.2-20260421", - "hugging_face_id": "poolside/Laguna-XS.2", - "name": "Poolside: Laguna XS.2 (free)", - "created": 1777389604, - "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...", + "id": "poolside/laguna-xs-2.1:free", + "canonical_slug": "poolside/laguna-xs-2.1-20260625", + "hugging_face_id": "poolside/Laguna-XS-2.1", + "name": "Poolside: Laguna XS 2.1 (free)", + "created": 1783002429, + "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -18677,19 +26696,12 @@ "tool_choice", "tools" ], - "default_parameters": { - "temperature": 0.7, - "top_p": 0.9, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-07-09", + "expiration_date": null, "links": { - "details": "/api/v1/models/poolside/laguna-xs.2-20260421/endpoints" + "details": "/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints" }, "reasoning": { "mandatory": false, @@ -18703,7 +26715,7 @@ "name": "Qwen2.5 72B Instruct", "created": 1726704000, "description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", - "context_length": 131072, + "context_length": 32768, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -18753,7 +26765,7 @@ "name": "Qwen: Qwen2.5 7B Instruct", "created": 1729036800, "description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", - "context_length": 131072, + "context_length": 32768, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -18762,8 +26774,8 @@ "instruct_type": "chatml" }, "pricing": { - "prompt": "0.00000004", - "completion": "0.0000001" + "prompt": "0.0000001", + "completion": "0.0000002" }, "top_provider": { "context_length": 32768, @@ -18774,7 +26786,6 @@ "supported_parameters": [ "frequency_penalty", "logit_bias", - "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -18787,7 +26798,6 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -18809,7 +26819,7 @@ "name": "Qwen2.5 Coder 32B Instruct", "created": 1731368400, "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...", - "context_length": 128000, + "context_length": 32768, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -18840,192 +26850,435 @@ "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints" + } + }, + { + "id": "qwen/qwen-plus", + "canonical_slug": "qwen/qwen-plus-2025-01-25", + "hugging_face_id": "", + "name": "Qwen: Qwen-Plus", + "created": 1738409840, + "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Qwen", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000026", + "completion": "0.00000078", + "input_cache_read": "0.000000052", + "input_cache_write": "0.000000325", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.00000078", + "completion": "0.00000234", + "input_cache_read": "0.000000156", + "input_cache_write": "0.000000975" + } + ] + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints" + } + }, + { + "id": "qwen/qwen-plus-2025-07-28", + "canonical_slug": "qwen/qwen-plus-2025-07-28", + "hugging_face_id": "", + "name": "Qwen: Qwen Plus 0728", + "created": 1757347599, + "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000026", + "completion": "0.00000078", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.00000078", + "completion": "0.00000234" + } + ] + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2025-03-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" + }, + "reasoning": { + "mandatory": false + } + }, + { + "id": "qwen/qwen-plus-2025-07-28:thinking", + "canonical_slug": "qwen/qwen-plus-2025-07-28", + "hugging_face_id": "", + "name": "Qwen: Qwen Plus 0728 (thinking)", + "created": 1757347599, + "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", + "context_length": 1000000, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000026", + "completion": "0.00000078", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.00000078", + "completion": "0.00000234" + } + ] + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" + }, + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen-plus", - "canonical_slug": "qwen/qwen-plus-2025-01-25", - "hugging_face_id": "", - "name": "Qwen: Qwen-Plus", - "created": 1738409840, - "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, + "id": "qwen/qwen2.5-vl-72b-instruct", + "canonical_slug": "qwen/qwen2.5-vl-72b-instruct", + "hugging_face_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "name": "Qwen: Qwen2.5 VL 72B Instruct", + "created": 1738410311, + "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", + "context_length": 128000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000078", - "input_cache_read": "0.000000052", - "input_cache_write": "0.000000325" + "prompt": "0.00000025", + "completion": "0.00000075" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 32768, + "context_length": 32000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "logit_bias", "logprobs", "max_tokens", "presence_penalty", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", - "tool_choice", - "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints" + "details": "/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints" } }, { - "id": "qwen/qwen-plus-2025-07-28", - "canonical_slug": "qwen/qwen-plus-2025-07-28", - "hugging_face_id": "", - "name": "Qwen: Qwen Plus 0728", - "created": 1757347599, - "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, + "id": "qwen/qwen3-14b", + "canonical_slug": "qwen/qwen3-14b-04-28", + "hugging_face_id": "Qwen/Qwen3-14B", + "name": "Qwen: Qwen3 14B", + "created": 1745876478, + "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Qwen3", - "instruct_type": null + "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000078" + "prompt": "0.00000012", + "completion": "0.00000024" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 32768, + "context_length": 40960, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-14b-04-28/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 10.4, + "coding_index": 13.8, + "agentic_index": 1.9 + } }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen-plus-2025-07-28:thinking", - "canonical_slug": "qwen/qwen-plus-2025-07-28", - "hugging_face_id": "", - "name": "Qwen: Qwen Plus 0728 (thinking)", - "created": 1757347599, - "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, + "id": "qwen/qwen3-235b-a22b", + "canonical_slug": "qwen/qwen3-235b-a22b-04-28", + "hugging_face_id": "Qwen/Qwen3-235B-A22B", + "name": "Qwen: Qwen3 235B A22B", + "created": 1745875757, + "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Qwen3", - "instruct_type": null + "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000078", - "input_cache_write": "0.000000325" + "prompt": "0.000000455", + "completion": "0.00000182" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 32768, + "context_length": 131072, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", - "structured_outputs", + "stop", "temperature", "tool_choice", "tools", + "top_k", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 912, + "win_rate": 24.5, + "rank": 106 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1021, + "win_rate": 38.2, + "rank": 105 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1018, + "win_rate": 40, + "rank": 99 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 966, + "win_rate": 32.9, + "rank": 112 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 987, + "win_rate": 38.6, + "rank": 102 + }, + { + "arena": "models", + "category": "website", + "elo": 1041, + "win_rate": 40.4, + "rank": 105 + } + ] }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen2.5-vl-72b-instruct", - "canonical_slug": "qwen/qwen2.5-vl-72b-instruct", - "hugging_face_id": "Qwen/Qwen2.5-VL-72B-Instruct", - "name": "Qwen: Qwen2.5 VL 72B Instruct", - "created": 1738410311, - "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", - "context_length": 131072, + "id": "qwen/qwen3-235b-a22b-2507", + "canonical_slug": "qwen/qwen3-235b-a22b-07-25", + "hugging_face_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "name": "Qwen: Qwen3 235B A22B Instruct 2507", + "created": 1753119555, + "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.0000008", - "completion": "0.000001", - "input_cache_read": "0.0000004" + "prompt": "0.00000009", + "completion": "0.00000055" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 128000, + "context_length": 262144, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -19034,6 +27287,7 @@ "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -19041,26 +27295,74 @@ "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1048, + "win_rate": 41.1, + "rank": 94 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1057, + "win_rate": 42.6, + "rank": 96 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1092, + "win_rate": 49, + "rank": 90 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 990, + "win_rate": 35, + "rank": 110 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 993, + "win_rate": 38.4, + "rank": 100 + }, + { + "arena": "models", + "category": "website", + "elo": 1069, + "win_rate": 43.6, + "rank": 98 + } + ] } }, { - "id": "qwen/qwen3-14b", - "canonical_slug": "qwen/qwen3-14b-04-28", - "hugging_face_id": "Qwen/Qwen3-14B", - "name": "Qwen: Qwen3 14B", - "created": 1745876478, - "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", - "context_length": 131702, + "id": "qwen/qwen3-235b-a22b-thinking-2507", + "canonical_slug": "qwen/qwen3-235b-a22b-thinking-2507", + "hugging_face_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", + "name": "Qwen: Qwen3 235B A22B Thinking 2507", + "created": 1753449557, + "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19069,12 +27371,12 @@ "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.0000001", - "completion": "0.00000024" + "prompt": "0.00000023", + "completion": "0.0000023" }, "top_provider": { - "context_length": 40960, - "max_completion_tokens": 40960, + "context_length": 131072, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, @@ -19091,7 +27393,6 @@ "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -19099,32 +27400,79 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-14b-04-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1051, + "win_rate": 40.4, + "rank": 93 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1052, + "win_rate": 40.8, + "rank": 98 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 971, + "win_rate": 32.6, + "rank": 105 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 995, + "win_rate": 34.2, + "rank": 109 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 973, + "win_rate": 34, + "rank": 104 + }, + { + "arena": "models", + "category": "website", + "elo": 1063, + "win_rate": 42, + "rank": 99 + } + ], "artificial_analysis": { - "intelligence_index": 10.4, - "coding_index": 13.8, - "agentic_index": 1.8 + "intelligence_index": 19.9, + "coding_index": 22.1, + "agentic_index": 3.8 } }, "reasoning": { - "mandatory": false + "mandatory": true } }, { - "id": "qwen/qwen3-235b-a22b", - "canonical_slug": "qwen/qwen3-235b-a22b-04-28", - "hugging_face_id": "Qwen/Qwen3-235B-A22B", - "name": "Qwen: Qwen3 235B A22B", - "created": 1745875757, - "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...", + "id": "qwen/qwen3-30b-a3b", + "canonical_slug": "qwen/qwen3-30b-a3b-04-28", + "hugging_face_id": "Qwen/Qwen3-30B-A3B", + "name": "Qwen: Qwen3 30B A3B", + "created": 1745878604, + "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...", "context_length": 131072, "architecture": { "modality": "text->text", @@ -19134,8 +27482,8 @@ "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.000000455", - "completion": "0.00000182" + "prompt": "0.00000013", + "completion": "0.00000052" }, "top_provider": { "context_length": 131072, @@ -19144,81 +27492,85 @@ }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "temperature", "tool_choice", "tools", + "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 936, - "win_rate": 24.5, - "rank": 94 - }, { "arena": "models", "category": "codecategories", - "elo": 1052, - "win_rate": 38.3, - "rank": 91 + "elo": 961, + "win_rate": 37.5, + "rank": 113 }, { "arena": "models", "category": "dataviz", - "elo": 1044, - "win_rate": 41, - "rank": 86 + "elo": 988, + "win_rate": 39, + "rank": 103 }, { "arena": "models", "category": "gamedev", - "elo": 994, - "win_rate": 33.1, - "rank": 98 + "elo": 937, + "win_rate": 33.9, + "rank": 115 }, { "arena": "models", "category": "uicomponent", - "elo": 1016, - "win_rate": 39.1, - "rank": 89 + "elo": 974, + "win_rate": 42.4, + "rank": 103 }, { "arena": "models", "category": "website", - "elo": 1073, - "win_rate": 40.5, - "rank": 89 + "elo": 965, + "win_rate": 37.7, + "rank": 117 } ] }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true } }, { - "id": "qwen/qwen3-235b-a22b-2507", - "canonical_slug": "qwen/qwen3-235b-a22b-07-25", - "hugging_face_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", - "name": "Qwen: Qwen3 235B A22B Instruct 2507", - "created": 1753119555, - "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...", + "id": "qwen/qwen3-30b-a3b-instruct-2507", + "canonical_slug": "qwen/qwen3-30b-a3b-instruct-2507", + "hugging_face_id": "Qwen/Qwen3-30B-A3B-Instruct-2507", + "name": "Qwen: Qwen3 30B A3B Instruct 2507", + "created": 1753806965, + "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -19228,12 +27580,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.0000001" + "prompt": "0.00000004815", + "completion": "0.00000019305" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, + "context_length": 128000, + "max_completion_tokens": 32000, "is_moderated": false }, "per_request_limits": null, @@ -19242,7 +27594,6 @@ "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -19261,63 +27612,91 @@ "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints" + "details": "/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints" + } + }, + { + "id": "qwen/qwen3-30b-a3b-thinking-2507", + "canonical_slug": "qwen/qwen3-30b-a3b-thinking-2507", + "hugging_face_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "name": "Qwen: Qwen3 30B A3B Thinking 2507", + "created": 1756399192, + "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...", + "context_length": 81920, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.0000024" + }, + "top_provider": { + "context_length": 81920, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2025-06-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1072, - "win_rate": 41.1, - "rank": 81 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1088, - "win_rate": 42.7, - "rank": 82 - }, { "arena": "models", "category": "dataviz", - "elo": 1101, - "win_rate": 47.7, - "rank": 78 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1018, - "win_rate": 35.2, - "rank": 95 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1020, - "win_rate": 38.8, - "rank": 87 + "elo": 947, + "win_rate": 33.3, + "rank": 109 }, { "arena": "models", "category": "website", - "elo": 1101, - "win_rate": 43.7, - "rank": 84 + "elo": 941, + "win_rate": 35.5, + "rank": 118 } - ] + ], + "artificial_analysis": { + "intelligence_index": 14.6, + "coding_index": 12.1, + "agentic_index": 1.8 + } + }, + "reasoning": { + "mandatory": true } }, { - "id": "qwen/qwen3-235b-a22b-thinking-2507", - "canonical_slug": "qwen/qwen3-235b-a22b-thinking-2507", - "hugging_face_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", - "name": "Qwen: Qwen3 235B A22B Thinking 2507", - "created": 1753449557, - "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...", - "context_length": 262144, + "id": "qwen/qwen3-32b", + "canonical_slug": "qwen/qwen3-32b-04-28", + "hugging_face_id": "Qwen/Qwen3-32B", + "name": "Qwen: Qwen3 32B", + "created": 1745875945, + "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19326,12 +27705,12 @@ "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.0000001495", - "completion": "0.000001495" + "prompt": "0.00000008", + "completion": "0.00000028" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 40960, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -19348,6 +27727,7 @@ "response_format", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", @@ -19355,79 +27735,32 @@ "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-06-30", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints" + "details": "/api/v1/models/qwen/qwen3-32b-04-28/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1077, - "win_rate": 40.7, - "rank": 80 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1082, - "win_rate": 40.9, - "rank": 84 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 990, - "win_rate": 32.3, - "rank": 91 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1023, - "win_rate": 34.3, - "rank": 94 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 996, - "win_rate": 33.9, - "rank": 91 - }, - { - "arena": "models", - "category": "website", - "elo": 1095, - "win_rate": 42.1, - "rank": 85 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 19.6, - "coding_index": 22.1, - "agentic_index": 3.8 + "intelligence_index": 11.4, + "coding_index": 15.3, + "agentic_index": 1.8 } }, "reasoning": { - "mandatory": true + "mandatory": false } }, { - "id": "qwen/qwen3-30b-a3b", - "canonical_slug": "qwen/qwen3-30b-a3b-04-28", - "hugging_face_id": "Qwen/Qwen3-30B-A3B", - "name": "Qwen: Qwen3 30B A3B", - "created": 1745878604, - "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...", + "id": "qwen/qwen3-8b", + "canonical_slug": "qwen/qwen3-8b-04-28", + "hugging_face_id": "Qwen/Qwen3-8B", + "name": "Qwen: Qwen3 8B", + "created": 1745876632, + "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...", "context_length": 131072, "architecture": { "modality": "text->text", @@ -19437,85 +27770,51 @@ "instruct_type": "qwen3" }, "pricing": { - "prompt": "0.00000012", - "completion": "0.0000005" + "prompt": "0.000000117", + "completion": "0.000000455" }, "top_provider": { - "context_length": 40960, - "max_completion_tokens": 16384, + "context_length": 131072, + "max_completion_tokens": 8192, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null + "temperature": 0.6, + "top_p": 0.95, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-8b-04-28/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 991, - "win_rate": 37.5, - "rank": 99 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1011, - "win_rate": 39, - "rank": 89 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 963, - "win_rate": 33.8, - "rank": 100 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1000, - "win_rate": 42.4, - "rank": 90 - }, - { - "arena": "models", - "category": "website", - "elo": 997, - "win_rate": 37.7, - "rank": 101 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 8.3, + "coding_index": 9, + "agentic_index": 1.6 + } }, "reasoning": { "mandatory": false, @@ -19523,13 +27822,13 @@ } }, { - "id": "qwen/qwen3-30b-a3b-instruct-2507", - "canonical_slug": "qwen/qwen3-30b-a3b-instruct-2507", - "hugging_face_id": "Qwen/Qwen3-30B-A3B-Instruct-2507", - "name": "Qwen: Qwen3 30B A3B Instruct 2507", - "created": 1753806965, - "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...", - "context_length": 131072, + "id": "qwen/qwen3-coder", + "canonical_slug": "qwen/qwen3-coder-480b-a35b-07-25", + "hugging_face_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen: Qwen3 Coder 480B A35B", + "created": 1753230546, + "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19538,12 +27837,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000004815", - "completion": "0.00000019305" + "prompt": "0.0000003", + "completion": "0.000001", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 128000, - "max_completion_tokens": 32000, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -19571,17 +27871,56 @@ "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints" + "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "codecategories", + "elo": 1162, + "win_rate": 61.2, + "rank": 67 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1104, + "win_rate": 54.9, + "rank": 89 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1137, + "win_rate": 58.7, + "rank": 75 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1141, + "win_rate": 61.4, + "rank": 70 + }, + { + "arena": "models", + "category": "website", + "elo": 1169, + "win_rate": 61.7, + "rank": 69 + } + ] } }, { - "id": "qwen/qwen3-30b-a3b-thinking-2507", - "canonical_slug": "qwen/qwen3-30b-a3b-thinking-2507", - "hugging_face_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", - "name": "Qwen: Qwen3 30B A3B Thinking 2507", - "created": 1756399192, - "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...", - "context_length": 131072, + "id": "qwen/qwen3-coder-30b-a3b-instruct", + "canonical_slug": "qwen/qwen3-coder-30b-a3b-instruct", + "hugging_face_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", + "name": "Qwen: Qwen3 Coder 30B A3B Instruct", + "created": 1753972379, + "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19590,25 +27929,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000013", - "completion": "0.00000156" + "prompt": "0.00000007", + "completion": "0.00000028" }, "top_provider": { - "context_length": 81920, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logprobs", "max_tokens", "presence_penalty", - "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -19616,74 +27960,85 @@ "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints" + "details": "/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", "category": "dataviz", - "elo": 969, - "win_rate": 33.3, - "rank": 95 + "elo": 1105, + "win_rate": 54.7, + "rank": 88 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1074, + "win_rate": 54.1, + "rank": 87 }, { "arena": "models", "category": "website", - "elo": 973, - "win_rate": 35.5, - "rank": 103 + "elo": 1098, + "win_rate": 57.1, + "rank": 93 } - ], - "artificial_analysis": { - "intelligence_index": 14.4, - "coding_index": 12.1, - "agentic_index": 1.8 - } - }, - "reasoning": { - "mandatory": true + ] } }, { - "id": "qwen/qwen3-32b", - "canonical_slug": "qwen/qwen3-32b-04-28", - "hugging_face_id": "Qwen/Qwen3-32B", - "name": "Qwen: Qwen3 32B", - "created": 1745875945, - "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", - "context_length": 131072, + "id": "qwen/qwen3-coder-flash", + "canonical_slug": "qwen/qwen3-coder-flash", + "hugging_face_id": "", + "name": "Qwen: Qwen3 Coder Flash", + "created": 1758115536, + "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...", + "context_length": 1000000, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Qwen3", - "instruct_type": "qwen3" + "instruct_type": null }, "pricing": { - "prompt": "0.00000008", - "completion": "0.00000028" + "prompt": "0.000000195", + "completion": "0.000000975", + "input_cache_read": "0.000000039", + "input_cache_write": "0.00000024375", + "overrides": [ + { + "min_prompt_tokens": 32000, + "prompt": "0.000000325", + "completion": "0.000001625", + "input_cache_read": "0.000000065", + "input_cache_write": "0.00000040625" + }, + { + "min_prompt_tokens": 128000, + "prompt": "0.00000052", + "completion": "0.0000026", + "input_cache_read": "0.000000104", + "input_cache_write": "0.00000065" + } + ] }, "top_provider": { - "context_length": 40960, - "max_completion_tokens": 16384, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -19691,97 +28046,90 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-32b-04-28/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 11.5, - "coding_index": 15.3, - "agentic_index": 1.8 - } - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/qwen/qwen3-coder-flash/endpoints" } }, { - "id": "qwen/qwen3-8b", - "canonical_slug": "qwen/qwen3-8b-04-28", - "hugging_face_id": "Qwen/Qwen3-8B", - "name": "Qwen: Qwen3 8B", - "created": 1745876632, - "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...", - "context_length": 131072, + "id": "qwen/qwen3-coder-next", + "canonical_slug": "qwen/qwen3-coder-next-2025-02-03", + "hugging_face_id": "Qwen/Qwen3-Coder-Next", + "name": "Qwen: Qwen3 Coder Next", + "created": 1770164101, + "description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": "qwen3" + "tokenizer": "Qwen", + "instruct_type": null }, "pricing": { - "prompt": "0.000000117", - "completion": "0.000000455" + "prompt": "0.00000012", + "completion": "0.0000008", + "input_cache_read": "0.00000007" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 8192, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", "presence_penalty", - "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.6, + "temperature": 1, "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-8b-04-28/endpoints" + "details": "/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 8.3, - "coding_index": 9, - "agentic_index": 1.5 + "intelligence_index": 21.3, + "coding_index": 36.2, + "agentic_index": 8.9 } - }, - "reasoning": { - "mandatory": false, - "default_enabled": true } }, { - "id": "qwen/qwen3-coder", - "canonical_slug": "qwen/qwen3-coder-480b-a35b-07-25", - "hugging_face_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", - "name": "Qwen: Qwen3 Coder 480B A35B", - "created": 1753230546, - "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", - "context_length": 1048576, + "id": "qwen/qwen3-coder-plus", + "canonical_slug": "qwen/qwen3-coder-plus", + "hugging_face_id": "", + "name": "Qwen: Qwen3 Coder Plus", + "created": 1758662707, + "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...", + "context_length": 1000000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19790,23 +28138,38 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000022", - "completion": "0.0000018" + "prompt": "0.00000065", + "completion": "0.00000325", + "input_cache_read": "0.00000013", + "input_cache_write": "0.0000008125", + "overrides": [ + { + "min_prompt_tokens": 32000, + "prompt": "0.00000117", + "completion": "0.00000585", + "input_cache_read": "0.000000234", + "input_cache_write": "0.0000014625" + }, + { + "min_prompt_tokens": 128000, + "prompt": "0.00000195", + "completion": "0.00000975", + "input_cache_read": "0.00000039", + "input_cache_write": "0.0000024375" + } + ] }, "top_provider": { - "context_length": 262144, + "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", @@ -19818,61 +28181,29 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" + "details": "/api/v1/models/qwen/qwen3-coder-plus/endpoints" }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1192, - "win_rate": 61.2, - "rank": 55 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1126, - "win_rate": 54.9, - "rank": 75 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1167, - "win_rate": 59, - "rank": 59 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1169, - "win_rate": 61.5, - "rank": 57 - }, - { - "arena": "models", - "category": "website", - "elo": 1201, - "win_rate": 61.7, - "rank": 56 - } - ] + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-coder-30b-a3b-instruct", - "canonical_slug": "qwen/qwen3-coder-30b-a3b-instruct", - "hugging_face_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", - "name": "Qwen: Qwen3 Coder 30B A3B Instruct", - "created": 1753972379, - "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...", - "context_length": 160000, + "id": "qwen/qwen3-max", + "canonical_slug": "qwen/qwen3-max", + "hugging_face_id": "", + "name": "Qwen: Qwen3 Max", + "created": 1758662808, + "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -19881,12 +28212,30 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000007", - "completion": "0.00000027" + "prompt": "0.00000078", + "completion": "0.0000039", + "input_cache_read": "0.000000156", + "input_cache_write": "0.000000975", + "overrides": [ + { + "min_prompt_tokens": 32000, + "prompt": "0.00000156", + "completion": "0.0000078", + "input_cache_read": "0.000000312", + "input_cache_write": "0.00000195" + }, + { + "min_prompt_tokens": 128000, + "prompt": "0.00000195", + "completion": "0.00000975", + "input_cache_read": "0.00000039", + "input_cache_write": "0.0000024375" + } + ] }, "top_provider": { - "context_length": 160000, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -19895,7 +28244,6 @@ "logprobs", "max_tokens", "presence_penalty", - "repetition_penalty", "response_format", "seed", "stop", @@ -19907,75 +28255,133 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 1, + "top_p": 1, + "frequency_penalty": null + }, "supported_voices": null, "knowledge_cutoff": "2025-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen3-max/endpoints" }, "benchmarks": { "design_arena": [ { "arena": "models", - "category": "dataviz", - "elo": 1128, - "win_rate": 54.7, - "rank": 74 + "category": "3d", + "elo": 1127, + "win_rate": 43.6, + "rank": 80 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1160, + "win_rate": 47.2, + "rank": 39 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1129, + "win_rate": 44, + "rank": 82 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1123, + "win_rate": 41.3, + "rank": 82 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1132, + "win_rate": 43.9, + "rank": 79 + }, + { + "arena": "models", + "category": "svg", + "elo": 1045, + "win_rate": 36.9, + "rank": 69 }, { "arena": "models", "category": "uicomponent", - "elo": 1100, - "win_rate": 54.1, - "rank": 73 + "elo": 1104, + "win_rate": 40, + "rank": 83 }, { "arena": "models", "category": "website", "elo": 1130, - "win_rate": 57.1, - "rank": 78 + "win_rate": 44.4, + "rank": 84 } ] + }, + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-coder-flash", - "canonical_slug": "qwen/qwen3-coder-flash", - "hugging_face_id": "", - "name": "Qwen: Qwen3 Coder Flash", - "created": 1758115536, - "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...", - "context_length": 1000000, + "id": "qwen/qwen3-max-thinking", + "canonical_slug": "qwen/qwen3-max-thinking-20260123", + "hugging_face_id": null, + "name": "Qwen: Qwen3 Max Thinking", + "created": 1770671901, + "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.000000195", - "completion": "0.000000975", - "input_cache_read": "0.000000039", - "input_cache_write": "0.00000024375" + "prompt": "0.00000078", + "completion": "0.0000039", + "overrides": [ + { + "min_prompt_tokens": 32000, + "prompt": "0.00000156", + "completion": "0.0000078" + }, + { + "min_prompt_tokens": 128000, + "prompt": "0.00000195", + "completion": "0.00000975" + } + ] }, "top_provider": { - "context_length": 1000000, + "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", "logprobs", "max_tokens", "presence_penalty", + "reasoning", "response_format", "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -19985,30 +28391,33 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-coder-flash/endpoints" + "details": "/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints" + }, + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-coder-next", - "canonical_slug": "qwen/qwen3-coder-next-2025-02-03", - "hugging_face_id": "Qwen/Qwen3-Coder-Next", - "name": "Qwen: Qwen3 Coder Next", - "created": 1770164101, - "description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...", + "id": "qwen/qwen3-next-80b-a3b-instruct", + "canonical_slug": "qwen/qwen3-next-80b-a3b-instruct-2509", + "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen: Qwen3 Next 80B A3B Instruct", + "created": 1757612213, + "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000011", - "completion": "0.0000008", + "prompt": "0.0000001", + "completion": "0.0000011", "input_cache_read": "0.00000007" }, "top_provider": { @@ -20022,6 +28431,7 @@ "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -20035,34 +28445,22 @@ "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 21.1, - "coding_index": 36.2, - "agentic_index": 8.8 - } + "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" } }, { - "id": "qwen/qwen3-coder-plus", - "canonical_slug": "qwen/qwen3-coder-plus", - "hugging_face_id": "", - "name": "Qwen: Qwen3 Coder Plus", - "created": 1758662707, - "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...", - "context_length": 1000000, + "id": "qwen/qwen3-next-80b-a3b-thinking", + "canonical_slug": "qwen/qwen3-next-80b-a3b-thinking-2509", + "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", + "name": "Qwen: Qwen3 Next 80B A3B Thinking", + "created": 1757612284, + "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...", + "context_length": 262144, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -20071,27 +28469,32 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000065", - "completion": "0.00000325", - "input_cache_read": "0.00000013", - "input_cache_write": "0.0000008125" + "prompt": "0.00000015", + "completion": "0.0000012" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 65536, + "context_length": 131072, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", "logprobs", "max_tokens", "presence_penalty", + "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -20101,290 +28504,163 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-06-30", - "expiration_date": null, - "links": { - "details": "/api/v1/models/qwen/qwen3-coder-plus/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "qwen/qwen3-coder:free", - "canonical_slug": "qwen/qwen3-coder-480b-a35b-07-25", - "hugging_face_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", - "name": "Qwen: Qwen3 Coder 480B A35B (free)", - "created": 1753230546, - "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", - "context_length": 1048576, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen3", - "instruct_type": null - }, - "pricing": { - "prompt": "0", - "completion": "0" - }, - "top_provider": { - "context_length": 262000, - "max_completion_tokens": 262000, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "frequency_penalty", - "max_tokens", - "presence_penalty", - "stop", - "temperature", - "tool_choice", - "tools", - "top_k", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": "2025-06-30", + "knowledge_cutoff": "2025-09-30", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints" + "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "codecategories", - "elo": 1192, - "win_rate": 61.2, - "rank": 55 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1126, - "win_rate": 54.9, - "rank": 75 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1167, - "win_rate": 59, - "rank": 59 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1169, - "win_rate": 61.5, - "rank": 57 - }, - { - "arena": "models", - "category": "website", - "elo": 1201, - "win_rate": 61.7, - "rank": 56 - } - ] + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 16.9, + "coding_index": 17.4, + "agentic_index": 2.1 + } + }, + "reasoning": { + "mandatory": true } }, { - "id": "qwen/qwen3-max", - "canonical_slug": "qwen/qwen3-max", - "hugging_face_id": "", - "name": "Qwen: Qwen3 Max", - "created": 1758662808, - "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...", + "id": "qwen/qwen3-vl-235b-a22b-instruct", + "canonical_slug": "qwen/qwen3-vl-235b-a22b-instruct", + "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Instruct", + "name": "Qwen: Qwen3 VL 235B A22B Instruct", + "created": 1758668687, + "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...", "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000078", - "completion": "0.0000039", - "input_cache_read": "0.000000156", - "input_cache_write": "0.000000975" + "prompt": "0.00000026", + "completion": "0.00000104" }, "top_provider": { - "context_length": 262144, + "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 1, + "temperature": 0.7, + "top_p": 0.8, "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-06-30", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-max/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1151, - "win_rate": 43.5, - "rank": 63 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1174, - "win_rate": 47.2, - "rank": 33 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1159, - "win_rate": 44, - "rank": 67 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1148, - "win_rate": 41.8, - "rank": 65 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1160, - "win_rate": 43.9, - "rank": 63 - }, - { - "arena": "models", - "category": "svg", - "elo": 1068, - "win_rate": 37.2, - "rank": 62 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1130, - "win_rate": 40.1, - "rank": 68 - }, - { - "arena": "models", - "category": "website", - "elo": 1161, - "win_rate": 44.4, - "rank": 67 - } - ] - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints" } }, { - "id": "qwen/qwen3-max-thinking", - "canonical_slug": "qwen/qwen3-max-thinking-20260123", - "hugging_face_id": null, - "name": "Qwen: Qwen3 Max Thinking", - "created": 1770671901, - "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...", - "context_length": 262144, + "id": "qwen/qwen3-vl-235b-a22b-thinking", + "canonical_slug": "qwen/qwen3-vl-235b-a22b-thinking", + "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Thinking", + "name": "Qwen: Qwen3 VL 235B A22B Thinking", + "created": 1758668690, + "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....", + "context_length": 131072, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Qwen", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000078", - "completion": "0.0000039" + "prompt": "0.0000004", + "completion": "0.000004" }, "top_provider": { - "context_length": 262144, + "context_length": 131072, "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null + "temperature": 0.8, + "top_p": 0.95, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": 1 }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints" + "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": true } }, { - "id": "qwen/qwen3-next-80b-a3b-instruct", - "canonical_slug": "qwen/qwen3-next-80b-a3b-instruct-2509", - "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", - "name": "Qwen: Qwen3 Next 80B A3B Instruct", - "created": 1757612213, - "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", + "id": "qwen/qwen3-vl-30b-a3b-instruct", + "canonical_slug": "qwen/qwen3-vl-30b-a3b-instruct", + "hugging_face_id": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "name": "Qwen: Qwen3 VL 30B A3B Instruct", + "created": 1759794476, + "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...", "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000009", - "completion": "0.0000011" + "prompt": "0.00000013", + "completion": "0.00000052" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, + "context_length": 131072, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -20407,78 +28683,100 @@ "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 0.7, + "top_p": 0.8, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": 1 + }, "supported_voices": null, - "knowledge_cutoff": "2025-09-30", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" + "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints" } }, { - "id": "qwen/qwen3-next-80b-a3b-instruct:free", - "canonical_slug": "qwen/qwen3-next-80b-a3b-instruct-2509", - "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", - "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)", - "created": 1757612213, - "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", + "id": "qwen/qwen3-vl-30b-a3b-thinking", + "canonical_slug": "qwen/qwen3-vl-30b-a3b-thinking", + "hugging_face_id": "Qwen/Qwen3-VL-30B-A3B-Thinking", + "name": "Qwen: Qwen3 VL 30B A3B Thinking", + "created": 1759794479, + "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...", "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.0000002", + "completion": "0.0000024" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, + "context_length": 131072, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", + "logprobs", "max_tokens", "presence_penalty", + "reasoning", "response_format", + "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": 0.8, + "top_p": 0.95, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": 1 + }, "supported_voices": null, - "knowledge_cutoff": "2025-09-30", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints" + "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints" + }, + "reasoning": { + "mandatory": true } }, { - "id": "qwen/qwen3-next-80b-a3b-thinking", - "canonical_slug": "qwen/qwen3-next-80b-a3b-thinking-2509", - "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", - "name": "Qwen: Qwen3 Next 80B A3B Thinking", - "created": 1757612284, - "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...", - "context_length": 262144, + "id": "qwen/qwen3-vl-32b-instruct", + "canonical_slug": "qwen/qwen3-vl-32b-instruct", + "hugging_face_id": "Qwen/Qwen3-VL-32B-Instruct", + "name": "Qwen: Qwen3 VL 32B Instruct", + "created": 1761231332, + "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...", + "context_length": 131072, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.0000000975", - "completion": "0.00000078" + "prompt": "0.000000104", + "completion": "0.000000416" }, "top_provider": { "context_length": 131072, @@ -20488,12 +28786,9 @@ "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", "logprobs", "max_tokens", "presence_penalty", - "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -20506,51 +28801,42 @@ "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null + "temperature": 0.7, + "top_p": 0.8, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": 1 }, "supported_voices": null, - "knowledge_cutoff": "2025-09-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 16.7, - "coding_index": 17.4, - "agentic_index": 2.1 - } - }, - "reasoning": { - "mandatory": true + "details": "/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints" } }, { - "id": "qwen/qwen3-vl-235b-a22b-instruct", - "canonical_slug": "qwen/qwen3-vl-235b-a22b-instruct", - "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Instruct", - "name": "Qwen: Qwen3 VL 235B A22B Instruct", - "created": 1758668687, - "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...", + "id": "qwen/qwen3-vl-8b-instruct", + "canonical_slug": "qwen/qwen3-vl-8b-instruct", + "hugging_face_id": "Qwen/Qwen3-VL-8B-Instruct", + "name": "Qwen: Qwen3 VL 8B Instruct", + "created": 1760463308, + "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...", "context_length": 262144, "architecture": { "modality": "text+image->text", - "input_modalities": ["text", "image"], + "input_modalities": ["image", "text"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.00000088", - "input_cache_read": "0.00000011" + "prompt": "0.000000117", + "completion": "0.000000455" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 16384, + "context_length": 131072, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, @@ -20559,7 +28845,6 @@ "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -20579,30 +28864,30 @@ "frequency_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints" } }, { - "id": "qwen/qwen3-vl-235b-a22b-thinking", - "canonical_slug": "qwen/qwen3-vl-235b-a22b-thinking", - "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Thinking", - "name": "Qwen: Qwen3 VL 235B A22B Thinking", - "created": 1758668690, - "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....", + "id": "qwen/qwen3-vl-8b-thinking", + "canonical_slug": "qwen/qwen3-vl-8b-thinking", + "hugging_face_id": "Qwen/Qwen3-VL-8B-Thinking", + "name": "Qwen: Qwen3 VL 8B Thinking", + "created": 1760463746, + "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...", "context_length": 131072, "architecture": { "modality": "text+image->text", - "input_modalities": ["text", "image"], + "input_modalities": ["image", "text"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000026", - "completion": "0.0000026" + "prompt": "0.00000018", + "completion": "0.0000021" }, "top_provider": { "context_length": 131072, @@ -20617,7 +28902,6 @@ "max_tokens", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -20630,55 +28914,53 @@ "top_p" ], "default_parameters": { - "temperature": 0.8, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": 1 + "temperature": 1, + "top_p": 0.95 }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints" + "details": "/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints" }, "reasoning": { "mandatory": true } }, { - "id": "qwen/qwen3-vl-30b-a3b-instruct", - "canonical_slug": "qwen/qwen3-vl-30b-a3b-instruct", - "hugging_face_id": "Qwen/Qwen3-VL-30B-A3B-Instruct", - "name": "Qwen: Qwen3 VL 30B A3B Instruct", - "created": 1759794476, - "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...", + "id": "qwen/qwen3.5-122b-a10b", + "canonical_slug": "qwen/qwen3.5-122b-a10b-20260224", + "hugging_face_id": "Qwen/Qwen3.5-122B-A10B", + "name": "Qwen: Qwen3.5-122B-A10B", + "created": 1772053789, + "description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...", "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000013", - "completion": "0.00000052" + "prompt": "0.00000029", + "completion": "0.0000024" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 81920, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", @@ -20692,54 +28974,69 @@ "top_p" ], "default_parameters": { - "temperature": 0.7, - "top_p": 0.8, + "temperature": 0.6, + "top_p": 0.95, "top_k": 20, "frequency_penalty": null, "presence_penalty": null, - "repetition_penalty": 1 + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 32.8, + "coding_index": 45.7, + "agentic_index": 21.3 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-vl-30b-a3b-thinking", - "canonical_slug": "qwen/qwen3-vl-30b-a3b-thinking", - "hugging_face_id": "Qwen/Qwen3-VL-30B-A3B-Thinking", - "name": "Qwen: Qwen3 VL 30B A3B Thinking", - "created": 1759794479, - "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...", - "context_length": 131072, + "id": "qwen/qwen3.5-27b", + "canonical_slug": "qwen/qwen3.5-27b-20260224", + "hugging_face_id": "Qwen/Qwen3.5-27B", + "name": "Qwen: Qwen3.5-27B", + "created": 1772053810, + "description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.00000013", + "prompt": "0.000000195", "completion": "0.00000156" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", @@ -20749,107 +29046,130 @@ "top_p" ], "default_parameters": { - "temperature": 0.8, + "temperature": 0.6, "top_p": 0.95, "top_k": 20, "frequency_penalty": null, "presence_penalty": null, - "repetition_penalty": 1 + "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints" }, "reasoning": { - "mandatory": true + "mandatory": false } }, { - "id": "qwen/qwen3-vl-32b-instruct", - "canonical_slug": "qwen/qwen3-vl-32b-instruct", - "hugging_face_id": "Qwen/Qwen3-VL-32B-Instruct", - "name": "Qwen: Qwen3 VL 32B Instruct", - "created": 1761231332, - "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...", + "id": "qwen/qwen3.5-35b-a3b", + "canonical_slug": "qwen/qwen3.5-35b-a3b-20260224", + "hugging_face_id": "Qwen/Qwen3.5-35B-A3B", + "name": "Qwen: Qwen3.5-35B-A3B", + "created": 1772053822, + "description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...", "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Qwen", + "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.000000104", - "completion": "0.000000416" + "prompt": "0.000000225", + "completion": "0.0000018", + "input_cache_read": "0.000000225" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.7, - "top_p": 0.8, + "temperature": 1, + "top_p": 0.95, "top_k": 20, "frequency_penalty": null, "presence_penalty": null, - "repetition_penalty": 1 + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 24.3, + "coding_index": 37, + "agentic_index": 11.8 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-vl-8b-instruct", - "canonical_slug": "qwen/qwen3-vl-8b-instruct", - "hugging_face_id": "Qwen/Qwen3-VL-8B-Instruct", - "name": "Qwen: Qwen3 VL 8B Instruct", - "created": 1760463308, - "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...", - "context_length": 256000, + "id": "qwen/qwen3.5-397b-a17b", + "canonical_slug": "qwen/qwen3.5-397b-a17b-20260216", + "hugging_face_id": "Qwen/Qwen3.5-397B-A17B", + "name": "Qwen: Qwen3.5 397B A17B", + "created": 1771223018, + "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.000000117", - "completion": "0.000000455" + "prompt": "0.00000039", + "completion": "0.00000234" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "include_reasoning", "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", + "reasoning", "repetition_penalty", "response_format", "seed", @@ -20863,79 +29183,161 @@ "top_p" ], "default_parameters": { - "temperature": 0.7, - "top_p": 0.8, - "frequency_penalty": null + "temperature": 0.6, + "top_p": 0.95, + "top_k": 20, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1215, + "win_rate": 56.6, + "rank": 46 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1200, + "win_rate": 52.7, + "rank": 49 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1198, + "win_rate": 53.2, + "rank": 50 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1178, + "win_rate": 50.2, + "rank": 60 + }, + { + "arena": "models", + "category": "svg", + "elo": 1169, + "win_rate": 55.2, + "rank": 40 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1195, + "win_rate": 52.2, + "rank": 56 + }, + { + "arena": "models", + "category": "website", + "elo": 1203, + "win_rate": 52.5, + "rank": 51 + } + ], + "artificial_analysis": { + "intelligence_index": 34.3, + "coding_index": 48.2, + "agentic_index": 19.8 + } }, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints" + "reasoning": { + "mandatory": false } }, { - "id": "qwen/qwen3-vl-8b-thinking", - "canonical_slug": "qwen/qwen3-vl-8b-thinking", - "hugging_face_id": "Qwen/Qwen3-VL-8B-Thinking", - "name": "Qwen: Qwen3 VL 8B Thinking", - "created": 1760463746, - "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...", - "context_length": 256000, + "id": "qwen/qwen3.5-9b", + "canonical_slug": "qwen/qwen3.5-9b-20260310", + "hugging_face_id": "Qwen/Qwen3.5-9B", + "name": "Qwen: Qwen3.5-9B", + "created": 1773152396, + "description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...", + "context_length": 262144, "architecture": { - "modality": "text+image->text", - "input_modalities": ["image", "text"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen3", "instruct_type": null }, "pricing": { - "prompt": "0.000000117", - "completion": "0.000001365" + "prompt": "0.0000001", + "completion": "0.00000015" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 32768, + "context_length": 262144, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95 + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 21.8, + "coding_index": 28.7, + "agentic_index": 7 + } }, "reasoning": { - "mandatory": true + "mandatory": false } }, { - "id": "qwen/qwen3.5-122b-a10b", - "canonical_slug": "qwen/qwen3.5-122b-a10b-20260224", - "hugging_face_id": "Qwen/Qwen3.5-122B-A10B", - "name": "Qwen: Qwen3.5-122B-A10B", - "created": 1772053789, - "description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...", - "context_length": 262144, + "id": "qwen/qwen3.5-flash-02-23", + "canonical_slug": "qwen/qwen3.5-flash-20260224", + "hugging_face_id": null, + "name": "Qwen: Qwen3.5-Flash", + "created": 1772053776, + "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...", + "context_length": 1000000, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -20944,25 +29346,21 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000208" + "prompt": "0.000000065", + "completion": "0.00000026" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -20971,43 +29369,31 @@ "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 32.3, - "coding_index": 45.7, - "agentic_index": 20.7 - } + "details": "/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints" }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen3.5-27b", - "canonical_slug": "qwen/qwen3.5-27b-20260224", - "hugging_face_id": "Qwen/Qwen3.5-27B", - "name": "Qwen: Qwen3.5-27B", - "created": 1772053810, - "description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...", - "context_length": 262144, + "id": "qwen/qwen3.5-plus-02-15", + "canonical_slug": "qwen/qwen3.5-plus-20260216", + "hugging_face_id": "", + "name": "Qwen: Qwen3.5 Plus 2026-02-15", + "created": 1771229416, + "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...", + "context_length": 1000000, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -21016,11 +29402,18 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000195", - "completion": "0.00000156" + "prompt": "0.00000026", + "completion": "0.00000156", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.000000325", + "completion": "0.00000195" + } + ] }, "top_provider": { - "context_length": 262144, + "context_length": 1000000, "max_completion_tokens": 65536, "is_moderated": false }, @@ -21028,13 +29421,10 @@ "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -21047,31 +29437,88 @@ "top_p" ], "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": null, + "top_p": null, + "frequency_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1173, + "win_rate": 47.7, + "rank": 61 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1126, + "win_rate": 43.2, + "rank": 49 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1186, + "win_rate": 48.5, + "rank": 59 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1159, + "win_rate": 44.9, + "rank": 69 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1143, + "win_rate": 42.6, + "rank": 72 + }, + { + "arena": "models", + "category": "svg", + "elo": 1139, + "win_rate": 48.5, + "rank": 47 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1209, + "win_rate": 52.7, + "rank": 46 + }, + { + "arena": "models", + "category": "website", + "elo": 1199, + "win_rate": 50, + "rank": 54 + } + ] }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen3.5-35b-a3b", - "canonical_slug": "qwen/qwen3.5-35b-a3b-20260224", - "hugging_face_id": "Qwen/Qwen3.5-35B-A3B", - "name": "Qwen: Qwen3.5-35B-A3B", - "created": 1772053822, - "description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...", - "context_length": 262144, + "id": "qwen/qwen3.5-plus-20260420", + "canonical_slug": "qwen/qwen3.5-plus-20260420", + "hugging_face_id": null, + "name": "Qwen: Qwen3.5 Plus 2026-04-20", + "created": 1777261368, + "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...", + "context_length": 1000000, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -21080,26 +29527,31 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000014", - "completion": "0.000001", - "input_cache_read": "0.00000005" + "prompt": "0.0000003", + "completion": "0.0000018", + "input_cache_write": "0.000000375", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.000000375", + "completion": "0.00000225", + "input_cache_write": "0.00000046875" + } + ] }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 81920, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -21111,32 +29563,25 @@ "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": 20, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints" + "details": "/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints" }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen3.5-397b-a17b", - "canonical_slug": "qwen/qwen3.5-397b-a17b-20260216", - "hugging_face_id": "Qwen/Qwen3.5-397B-A17B", - "name": "Qwen: Qwen3.5 397B A17B", - "created": 1771223018, - "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...", - "context_length": 256000, + "id": "qwen/qwen3.6-27b", + "canonical_slug": "qwen/qwen3.6-27b-20260422", + "hugging_face_id": "Qwen/Qwen3.6-27B", + "name": "Qwen: Qwen3.6 27B", + "created": 1777255064, + "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...", + "context_length": 262144, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], @@ -21145,13 +29590,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000385", - "completion": "0.00000245", - "input_cache_read": "0.000000111" + "prompt": "0.0000003", + "completion": "0.000002", + "input_cache_read": "0.00000003" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 262144, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, @@ -21177,9 +29622,9 @@ "top_p" ], "default_parameters": { - "temperature": 0.6, - "top_p": 0.95, - "top_k": 20, + "temperature": null, + "top_p": null, + "top_k": null, "frequency_penalty": null, "presence_penalty": null, "repetition_penalty": null @@ -21188,88 +29633,40 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints" + "details": "/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1238, - "win_rate": 56.7, - "rank": 34 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1229, - "win_rate": 52.6, - "rank": 36 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1218, - "win_rate": 53.2, - "rank": 39 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1206, - "win_rate": 50.1, - "rank": 44 - }, - { - "arena": "models", - "category": "svg", - "elo": 1199, - "win_rate": 56.1, - "rank": 32 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1216, - "win_rate": 51.4, - "rank": 43 - }, - { - "arena": "models", - "category": "website", - "elo": 1233, - "win_rate": 52.6, - "rank": 38 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 33.7, - "coding_index": 48.2, - "agentic_index": 19.8 + "intelligence_index": 37.7, + "coding_index": 53.7, + "agentic_index": 27.5 } }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true } }, { - "id": "qwen/qwen3.5-9b", - "canonical_slug": "qwen/qwen3.5-9b-20260310", - "hugging_face_id": "Qwen/Qwen3.5-9B", - "name": "Qwen: Qwen3.5-9B", - "created": 1773152396, - "description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...", + "id": "qwen/qwen3.6-35b-a3b", + "canonical_slug": "qwen/qwen3.6-35b-a3b-20260415", + "hugging_face_id": "Qwen/Qwen3.6-35B-A3B", + "name": "Qwen: Qwen3.6 35B A3B", + "created": 1777260255, + "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...", "context_length": 262144, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.00000015" + "prompt": "0.00000015", + "completion": "0.000001", + "input_cache_read": "0.00000005" }, "top_provider": { "context_length": 262144, @@ -21299,38 +29696,36 @@ "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": 1, + "top_p": 0.95, + "top_k": 20 }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints" + "details": "/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints" }, "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 21.4, - "coding_index": 28.7, - "agentic_index": 7.4 + "intelligence_index": 32.1, + "coding_index": 41.9, + "agentic_index": 21.6 } }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true } }, { - "id": "qwen/qwen3.5-flash-02-23", - "canonical_slug": "qwen/qwen3.5-flash-20260224", + "id": "qwen/qwen3.6-flash", + "canonical_slug": "qwen/qwen3.6-flash", "hugging_face_id": null, - "name": "Qwen: Qwen3.5-Flash", - "created": 1772053776, - "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...", + "name": "Qwen: Qwen3.6 Flash", + "created": 1777261362, + "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...", "context_length": 1000000, "architecture": { "modality": "text+image+video->text", @@ -21340,8 +29735,17 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000065", - "completion": "0.00000026" + "prompt": "0.0000001875", + "completion": "0.000001125", + "input_cache_write": "0.000000234375", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.00000075", + "completion": "0.000003", + "input_cache_write": "0.0000009375" + } + ] }, "top_provider": { "context_length": 1000000, @@ -21350,59 +29754,70 @@ }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", + "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints" + "details": "/api/v1/models/qwen/qwen3.6-flash/endpoints" }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen3.5-plus-02-15", - "canonical_slug": "qwen/qwen3.5-plus-20260216", - "hugging_face_id": "", - "name": "Qwen: Qwen3.5 Plus 2026-02-15", - "created": 1771229416, - "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...", - "context_length": 1000000, + "id": "qwen/qwen3.6-max-preview", + "canonical_slug": "qwen/qwen3.6-max-preview-20260420", + "hugging_face_id": null, + "name": "Qwen: Qwen3.6 Max Preview", + "created": 1777260242, + "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...", + "context_length": 262144, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000026", - "completion": "0.00000156" + "prompt": "0.000001027", + "completion": "0.000006162", + "input_cache_write": "0.00000128375", + "overrides": [ + { + "min_prompt_tokens": 128000, + "prompt": "0.00000158", + "completion": "0.00000948", + "input_cache_write": "0.000001975" + } + ] }, "top_provider": { - "context_length": 1000000, + "context_length": 262144, "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", @@ -21410,95 +29825,34 @@ "reasoning", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1197, - "win_rate": 47.8, - "rank": 47 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1140, - "win_rate": 43.2, - "rank": 42 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1216, - "win_rate": 48.5, - "rank": 46 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1178, - "win_rate": 44.8, - "rank": 58 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1172, - "win_rate": 42.7, - "rank": 58 - }, - { - "arena": "models", - "category": "svg", - "elo": 1165, - "win_rate": 48.9, - "rank": 41 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1231, - "win_rate": 52.2, - "rank": 37 - }, - { - "arena": "models", - "category": "website", - "elo": 1230, - "win_rate": 50.1, - "rank": 41 - } - ] + "details": "/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": false, + "default_enabled": true } }, { - "id": "qwen/qwen3.5-plus-20260420", - "canonical_slug": "qwen/qwen3.5-plus-20260420", - "hugging_face_id": null, - "name": "Qwen: Qwen3.5 Plus 2026-04-20", - "created": 1777261368, - "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...", + "id": "qwen/qwen3.6-plus", + "canonical_slug": "qwen/qwen3.6-plus-04-02", + "hugging_face_id": "", + "name": "Qwen: Qwen3.6 Plus", + "created": 1775133557, + "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...", "context_length": 1000000, "architecture": { "modality": "text+image+video->text", @@ -21508,9 +29862,17 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000018", - "input_cache_write": "0.000000375" + "prompt": "0.000000325", + "completion": "0.00000195", + "input_cache_write": "0.00000040625", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.0000013", + "completion": "0.0000039", + "input_cache_write": "0.000001625" + } + ] }, "top_provider": { "context_length": 1000000, @@ -21519,6 +29881,7 @@ }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", @@ -21526,68 +29889,152 @@ "reasoning", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints" + "details": "/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1254, + "win_rate": 51.4, + "rank": 34 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1148, + "win_rate": 43.4, + "rank": 44 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1254, + "win_rate": 51.9, + "rank": 33 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1251, + "win_rate": 51.2, + "rank": 32 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1245, + "win_rate": 50.6, + "rank": 36 + }, + { + "arena": "models", + "category": "svg", + "elo": 1196, + "win_rate": 51.8, + "rank": 29 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1266, + "win_rate": 52.5, + "rank": 31 + }, + { + "arena": "models", + "category": "website", + "elo": 1252, + "win_rate": 52.2, + "rank": 34 + } + ], + "artificial_analysis": { + "intelligence_index": 40.5, + "coding_index": 54.5, + "agentic_index": 29 + } }, "reasoning": { "mandatory": false } }, { - "id": "qwen/qwen3.6-27b", - "canonical_slug": "qwen/qwen3.6-27b-20260422", - "hugging_face_id": "Qwen/Qwen3.6-27B", - "name": "Qwen: Qwen3.6 27B", - "created": 1777255064, - "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...", - "context_length": 262144, + "id": "qwen/qwen3.7-flash", + "canonical_slug": "qwen/qwen3.7-flash-20260727", + "hugging_face_id": null, + "name": "Qwen: Qwen3.7 Flash", + "created": 1785190561, + "description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...", + "context_length": 1000000, "architecture": { "modality": "text+image+video->text", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.000000285", - "completion": "0.0000024", - "input_cache_read": "0.00000015" + "prompt": "0.00000003", + "completion": "0.00000013", + "input_cache_read": "0.000000006", + "input_cache_write": "0.000000038", + "overrides": [ + { + "min_prompt_tokens": 32000, + "prompt": "0.0000001", + "completion": "0.0000004", + "input_cache_read": "0.00000002", + "input_cache_write": "0.000000125" + }, + { + "min_prompt_tokens": 256000, + "prompt": "0.0000002", + "completion": "0.0000008", + "input_cache_read": "0.00000004", + "input_cache_write": "0.00000025" + } + ] }, "top_provider": { - "context_length": 262140, - "max_completion_tokens": 262140, + "context_length": 1000000, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", "top_logprobs", "top_p" ], @@ -21603,56 +30050,48 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 37.1, - "coding_index": 53.7, - "agentic_index": 27 - } + "details": "/api/v1/models/qwen/qwen3.7-flash-20260727/endpoints" }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supports_max_tokens": true } }, { - "id": "qwen/qwen3.6-35b-a3b", - "canonical_slug": "qwen/qwen3.6-35b-a3b-20260415", - "hugging_face_id": "Qwen/Qwen3.6-35B-A3B", - "name": "Qwen: Qwen3.6 35B A3B", - "created": 1777260255, - "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...", - "context_length": 262144, + "id": "qwen/qwen3.7-max", + "canonical_slug": "qwen/qwen3.7-max-20260520", + "hugging_face_id": null, + "name": "Qwen: Qwen3.7 Max", + "created": 1779376861, + "description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...", + "context_length": 1000000, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000014", - "completion": "0.000001" + "prompt": "0.000001475", + "completion": "0.000004425", + "input_cache_read": "0.000000295", + "input_cache_write": "0.00000184375" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 1000000, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", - "logit_bias", "logprobs", "max_tokens", - "min_p", "presence_penalty", "reasoning", - "repetition_penalty", "response_format", "seed", "stop", @@ -21665,22 +30104,138 @@ "top_p" ], "default_parameters": { - "temperature": 1, - "top_p": 0.95, - "top_k": 20 + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints" + "details": "/api/v1/models/qwen/qwen3.7-max-20260520/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1174, + "win_rate": 48.3, + "rank": 13 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1188, + "win_rate": 49.4, + "rank": 21 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1222, + "win_rate": 51.3, + "rank": 16 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1225, + "win_rate": 55.4, + "rank": 8 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1187, + "win_rate": 45, + "rank": 12 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1206, + "win_rate": 49, + "rank": 18 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1216, + "win_rate": 49.7, + "rank": 10 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1251, + "win_rate": 51.3, + "rank": 12 + }, + { + "arena": "models", + "category": "3d", + "elo": 1322, + "win_rate": 56.4, + "rank": 12 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1248, + "win_rate": 53.6, + "rank": 12 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1296, + "win_rate": 55.8, + "rank": 15 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1301, + "win_rate": 54, + "rank": 13 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1309, + "win_rate": 55.7, + "rank": 14 + }, + { + "arena": "models", + "category": "svg", + "elo": 1254, + "win_rate": 59.7, + "rank": 11 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1302, + "win_rate": 53.8, + "rank": 16 + }, + { + "arena": "models", + "category": "website", + "elo": 1285, + "win_rate": 56.1, + "rank": 17 + } + ], "artificial_analysis": { - "intelligence_index": 31.6, - "coding_index": 41.9, - "agentic_index": 21.4 + "intelligence_index": 46.7, + "coding_index": 66, + "agentic_index": 30.9 } }, "reasoning": { @@ -21689,32 +30244,43 @@ } }, { - "id": "qwen/qwen3.6-flash", - "canonical_slug": "qwen/qwen3.6-flash", + "id": "qwen/qwen3.7-plus", + "canonical_slug": "qwen/qwen3.7-plus-20260602", "hugging_face_id": null, - "name": "Qwen: Qwen3.6 Flash", - "created": 1777261362, - "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...", + "name": "Qwen: Qwen3.7 Plus", + "created": 1780491783, + "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...", "context_length": 1000000, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text+image->text", + "input_modalities": ["text", "image"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.0000001875", - "completion": "0.000001125", - "input_cache_write": "0.000000234375" + "prompt": "0.00000032", + "completion": "0.00000128", + "input_cache_read": "0.000000064", + "input_cache_write": "0.0000004", + "overrides": [ + { + "min_prompt_tokens": 256000, + "prompt": "0.00000096", + "completion": "0.00000384", + "input_cache_read": "0.000000192", + "input_cache_write": "0.0000012" + } + ] }, "top_provider": { "context_length": 1000000, - "max_completion_tokens": 65536, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", @@ -21722,10 +30288,12 @@ "reasoning", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -21734,59 +30302,65 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.6-flash/endpoints" - }, - "reasoning": { - "mandatory": false - } - }, - { - "id": "qwen/qwen3.6-max-preview", - "canonical_slug": "qwen/qwen3.6-max-preview-20260420", - "hugging_face_id": null, - "name": "Qwen: Qwen3.6 Max Preview", - "created": 1777260242, - "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...", - "context_length": 262144, - "architecture": { - "modality": "text->text", - "input_modalities": ["text"], - "output_modalities": ["text"], - "tokenizer": "Qwen", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000104", - "completion": "0.00000624", - "input_cache_write": "0.0000013" - }, - "top_provider": { - "context_length": 262144, - "max_completion_tokens": 65536, - "is_moderated": false + "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "logprobs", - "max_tokens", - "presence_penalty", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "temperature", - "tool_choice", - "tools", - "top_logprobs", - "top_p" - ], - "default_parameters": {}, - "supported_voices": null, - "knowledge_cutoff": null, - "expiration_date": null, - "links": { - "details": "/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints" + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1292, + "win_rate": 49, + "rank": 23 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1178, + "win_rate": 44.4, + "rank": 32 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1282, + "win_rate": 50.3, + "rank": 21 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1273, + "win_rate": 50.6, + "rank": 20 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1294, + "win_rate": 50.9, + "rank": 21 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1273, + "win_rate": 48.4, + "rank": 27 + }, + { + "arena": "models", + "category": "website", + "elo": 1282, + "win_rate": 51.5, + "rank": 21 + } + ], + "artificial_analysis": { + "intelligence_index": 39.4, + "coding_index": 55.9, + "agentic_index": 20.7 + } }, "reasoning": { "mandatory": false, @@ -21794,329 +30368,177 @@ } }, { - "id": "qwen/qwen3.6-plus", - "canonical_slug": "qwen/qwen3.6-plus-04-02", - "hugging_face_id": "", - "name": "Qwen: Qwen3.6 Plus", - "created": 1775133557, - "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...", - "context_length": 1000000, + "id": "qwen/qwen3.8-2.4t-a95b", + "canonical_slug": "qwen/qwen3.8-2.4t-a95b-20260812", + "hugging_face_id": "Qwen/Qwen3.8-2.4T-A95B", + "name": "Qwen: Qwen3.8 2.4T A95B", + "created": 1786551702, + "description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...", + "context_length": 1048576, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen3", + "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.000000325", - "completion": "0.00000195", - "input_cache_write": "0.00000040625" + "prompt": "0.000002", + "completion": "0.000006", + "input_cache_read": "0.00000025" }, "top_provider": { "context_length": 1000000, - "max_completion_tokens": 65536, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", + "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": 1, + "top_p": 0.95, + "top_k": 20 }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1273, - "win_rate": 51.5, - "rank": 24 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1169, - "win_rate": 45.7, - "rank": 36 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1273, - "win_rate": 51.6, - "rank": 26 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1261, - "win_rate": 50.7, - "rank": 25 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1270, - "win_rate": 51.9, - "rank": 25 - }, - { - "arena": "models", - "category": "svg", - "elo": 1219, - "win_rate": 52, - "rank": 24 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1282, - "win_rate": 52.1, - "rank": 23 - }, - { - "arena": "models", - "category": "website", - "elo": 1263, - "win_rate": 51.4, - "rank": 29 - } - ], - "artificial_analysis": { - "intelligence_index": 39.6, - "coding_index": 54.5, - "agentic_index": 27.6 - } + "details": "/api/v1/models/qwen/qwen3.8-2.4t-a95b-20260812/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "medium", "low"], + "default_effort": "xhigh" } }, { - "id": "qwen/qwen3.7-max", - "canonical_slug": "qwen/qwen3.7-max-20260520", - "hugging_face_id": null, - "name": "Qwen: Qwen3.7 Max", - "created": 1779376861, - "description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...", - "context_length": 1000000, + "id": "qwen/qwen3.8-27b", + "canonical_slug": "qwen/qwen3.8-27b-20260814", + "hugging_face_id": "Qwen/Qwen3.8-27B", + "name": "Qwen: Qwen3.8 27B", + "created": 1786722910, + "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...", + "context_length": 262144, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.00000375", - "input_cache_read": "0.00000025", - "input_cache_write": "0.0000015625" + "prompt": "0.00000045", + "completion": "0.0000032" }, "top_provider": { - "context_length": 1000000, - "max_completion_tokens": 65536, + "context_length": 262144, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null + "temperature": 1, + "top_p": 0.95, + "top_k": 20 }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.7-max-20260520/endpoints" - }, - "benchmarks": { - "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1163, - "win_rate": 48, - "rank": 9 - }, - { - "arena": "agents", - "category": "androidnative", - "elo": 1193, - "win_rate": 47.1, - "rank": 13 - }, - { - "arena": "agents", - "category": "fullstack", - "elo": 1220, - "win_rate": 47.9, - "rank": 11 - }, - { - "arena": "agents", - "category": "mobileapps", - "elo": 1207, - "win_rate": 47, - "rank": 14 - }, - { - "arena": "agents", - "category": "webapps", - "elo": 1269, - "win_rate": 52, - "rank": 4 - }, - { - "arena": "models", - "category": "3d", - "elo": 1326, - "win_rate": 58.2, - "rank": 8 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1256, - "win_rate": 53.6, - "rank": 9 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1312, - "win_rate": 57.2, - "rank": 11 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1288, - "win_rate": 55.7, - "rank": 13 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1323, - "win_rate": 58.7, - "rank": 11 - }, - { - "arena": "models", - "category": "svg", - "elo": 1277, - "win_rate": 60.1, - "rank": 8 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1331, - "win_rate": 59.9, - "rank": 6 - }, - { - "arena": "models", - "category": "website", - "elo": 1303, - "win_rate": 56.4, - "rank": 14 - } - ], - "artificial_analysis": { - "intelligence_index": 46, - "coding_index": 66, - "agentic_index": 30.6 - } + "details": "/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints" }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supported_efforts": ["xhigh", "medium", "low"], + "default_effort": "xhigh" } }, { - "id": "qwen/qwen3.7-plus", - "canonical_slug": "qwen/qwen3.7-plus-20260602", + "id": "qwen/qwen3.8-max", + "canonical_slug": "qwen/qwen3.8-max-20260803", "hugging_face_id": null, - "name": "Qwen: Qwen3.7 Plus", - "created": 1780491783, - "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...", + "name": "Qwen: Qwen3.8 Max", + "created": 1785731612, + "description": "Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...", "context_length": 1000000, "architecture": { - "modality": "text+image->text", - "input_modalities": ["text", "image"], + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "tokenizer": "Qwen", "instruct_type": null }, "pricing": { - "prompt": "0.00000032", - "completion": "0.00000128", - "input_cache_read": "0.000000064", - "input_cache_write": "0.0000004" + "prompt": "0.000002", + "completion": "0.000006", + "input_cache_read": "0.00000025", + "input_cache_write": "0.0000025" }, "top_provider": { "context_length": 1000000, - "max_completion_tokens": 65536, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", "tools", + "top_k", "top_logprobs", "top_p" ], @@ -22125,19 +30547,64 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints" + "details": "/api/v1/models/qwen/qwen3.8-max-20260803/endpoints" }, "benchmarks": { - "design_arena": [], + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1386, + "win_rate": 59.5, + "rank": 2 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1323, + "win_rate": 56.1, + "rank": 7 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1271, + "win_rate": 51.5, + "rank": 21 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1334, + "win_rate": 57.3, + "rank": 8 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1352, + "win_rate": 59.5, + "rank": 3 + }, + { + "arena": "models", + "category": "website", + "elo": 1302, + "win_rate": 54.8, + "rank": 12 + } + ], "artificial_analysis": { - "intelligence_index": 39, - "coding_index": 55.9, - "agentic_index": 20.8 + "intelligence_index": 58.1, + "coding_index": 71.8, + "agentic_index": 58.4 } }, "reasoning": { - "mandatory": false, - "default_enabled": true + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low", "minimal"], + "default_effort": "xhigh" } }, { @@ -22360,7 +30827,15 @@ "prompt": "0.000005", "completion": "0.00003", "web_search": "0.01", - "input_cache_read": "0.0000005" + "input_cache_read": "0.0000005", + "overrides": [ + { + "min_prompt_tokens": 272000, + "prompt": "0.00001", + "completion": "0.000045", + "input_cache_read": "0.000001" + } + ] }, "top_provider": { "context_length": 1000000, @@ -22371,30 +30846,81 @@ "supported_parameters": [ "include_reasoning", "reasoning", + "reasoning_effort", + "structured_outputs", + "tool_choice", + "tools", + "web_search_options" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/sakana/fugu-ultra-20260615/endpoints" + }, + "reasoning": { + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["max", "xhigh", "high"], + "default_effort": "xhigh" + } + }, + { + "id": "sakana/sakana-namazu", + "canonical_slug": "sakana/namazu-20260811", + "hugging_face_id": null, + "name": "Sakana: Sakana Namazu", + "created": 1786410129, + "description": "Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...", + "context_length": 262144, + "architecture": { + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.00000095", + "completion": "0.000004", + "web_search": "0.007", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "reasoning", + "reasoning_effort", "structured_outputs", "tool_choice", "tools", "web_search_options" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/sakana/fugu-ultra-20260615/endpoints" + "details": "/api/v1/models/sakana/namazu-20260811/endpoints" }, "reasoning": { - "mandatory": true, + "mandatory": false, "default_enabled": true, - "supported_efforts": ["max", "xhigh", "high"], - "default_effort": "xhigh" + "supported_efforts": ["high", "none"], + "default_effort": "high" } }, { @@ -22425,6 +30951,7 @@ "supported_parameters": [ "frequency_penalty", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", @@ -22435,6 +30962,7 @@ "structured_outputs", "temperature", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, @@ -22446,27 +30974,27 @@ } }, { - "id": "sao10k/l3.1-70b-hanami-x1", - "canonical_slug": "sao10k/l3.1-70b-hanami-x1", - "hugging_face_id": "Sao10K/L3.1-70B-Hanami-x1", - "name": "Sao10K: Llama 3.1 70B Hanami x1", - "created": 1736302854, - "description": "This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).", - "context_length": 16000, + "id": "sao10k/l3.1-euryale-70b", + "canonical_slug": "sao10k/l3.1-euryale-70b", + "hugging_face_id": "Sao10K/L3.1-70B-Euryale-v2.2", + "name": "Sao10K: Llama 3.1 Euryale 70B v2.2", + "created": 1724803200, + "description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Llama3", - "instruct_type": null + "instruct_type": "llama3" }, "pricing": { - "prompt": "0.000003", - "completion": "0.000003" + "prompt": "0.00000085", + "completion": "0.00000085" }, "top_provider": { - "context_length": 16000, - "max_completion_tokens": null, + "context_length": 131072, + "max_completion_tokens": 16384, "is_moderated": false }, "per_request_limits": null, @@ -22477,10 +31005,13 @@ "min_p", "presence_penalty", "repetition_penalty", + "response_format", "seed", "stop", "structured_outputs", "temperature", + "tool_choice", + "tools", "top_k", "top_p" ], @@ -22489,16 +31020,16 @@ "knowledge_cutoff": "2023-12-31", "expiration_date": null, "links": { - "details": "/api/v1/models/sao10k/l3.1-70b-hanami-x1/endpoints" + "details": "/api/v1/models/sao10k/l3.1-euryale-70b/endpoints" } }, { - "id": "sao10k/l3.1-euryale-70b", - "canonical_slug": "sao10k/l3.1-euryale-70b", - "hugging_face_id": "Sao10K/L3.1-70B-Euryale-v2.2", - "name": "Sao10K: Llama 3.1 Euryale 70B v2.2", - "created": 1724803200, - "description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).", + "id": "sao10k/l3.3-euryale-70b", + "canonical_slug": "sao10k/l3.3-euryale-70b-v2.3", + "hugging_face_id": "Sao10K/L3.3-70B-Euryale-v2.3", + "name": "Sao10K: Llama 3.3 Euryale 70B", + "created": 1734535928, + "description": "Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).", "context_length": 131072, "architecture": { "modality": "text->text", @@ -22508,8 +31039,8 @@ "instruct_type": "llama3" }, "pricing": { - "prompt": "0.00000085", - "completion": "0.00000085" + "prompt": "0.00000065", + "completion": "0.00000075" }, "top_provider": { "context_length": 131072, @@ -22519,10 +31050,116 @@ "per_request_limits": null, "supported_parameters": [ "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2023-12-31", + "expiration_date": null, + "links": { + "details": "/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints" + } + }, + { + "id": "stepfun/step-3.5-flash", + "canonical_slug": "stepfun/step-3.5-flash", + "hugging_face_id": "stepfun-ai/Step-3.5-Flash", + "name": "StepFun: Step 3.5 Flash", + "created": 1769728337, + "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....", + "context_length": 262144, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000001", + "completion": "0.0000003" + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints" + }, + "reasoning": { + "mandatory": true + } + }, + { + "id": "stepfun/step-3.7-flash", + "canonical_slug": "stepfun/step-3.7-flash-20260528", + "hugging_face_id": "stepfun-ai/Step-3.7-Flash", + "name": "StepFun: Step 3.7 Flash", + "created": 1779985069, + "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...", + "context_length": 262144, + "architecture": { + "modality": "text+image+video->text", + "input_modalities": ["text", "image", "video"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000002", + "completion": "0.00000115", + "input_cache_read": "0.00000004" + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 256000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", "logit_bias", + "logprobs", "max_tokens", "min_p", "presence_penalty", + "reasoning", + "reasoning_effort", "repetition_penalty", "response_format", "seed", @@ -22532,70 +31169,148 @@ "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/sao10k/l3.1-euryale-70b/endpoints" + "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1177, + "win_rate": 41.8, + "rank": 58 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1191, + "win_rate": 46.6, + "rank": 24 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1195, + "win_rate": 44.1, + "rank": 52 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1191, + "win_rate": 44.1, + "rank": 54 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1191, + "win_rate": 41.2, + "rank": 54 + }, + { + "arena": "models", + "category": "svg", + "elo": 1105, + "win_rate": 38.6, + "rank": 54 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1201, + "win_rate": 43.6, + "rank": 51 + }, + { + "arena": "models", + "category": "website", + "elo": 1201, + "win_rate": 45.5, + "rank": 53 + } + ], + "artificial_analysis": { + "intelligence_index": 30.9, + "coding_index": 39.6, + "agentic_index": 21.7 + } + }, + "reasoning": { + "mandatory": true, + "supported_efforts": ["high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "sao10k/l3.3-euryale-70b", - "canonical_slug": "sao10k/l3.3-euryale-70b-v2.3", - "hugging_face_id": "Sao10K/L3.3-70B-Euryale-v2.3", - "name": "Sao10K: Llama 3.3 Euryale 70B", - "created": 1734535928, - "description": "Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).", + "id": "tencent/hunyuan-a13b-instruct", + "canonical_slug": "tencent/hunyuan-a13b-instruct", + "hugging_face_id": "tencent/Hunyuan-A13B-Instruct", + "name": "Tencent: Hunyuan A13B Instruct", + "created": 1751987664, + "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...", "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Llama3", - "instruct_type": "llama3" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000065", - "completion": "0.00000075" + "prompt": "0.00000014", + "completion": "0.00000057" }, "top_provider": { "context_length": 131072, - "max_completion_tokens": 16384, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logprobs", + "include_reasoning", "max_tokens", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", - "seed", - "stop", "structured_outputs", "temperature", - "top_logprobs", + "top_k", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2023-12-31", + "knowledge_cutoff": "2025-03-31", "expiration_date": null, "links": { - "details": "/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints" + "details": "/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints" + }, + "reasoning": { + "mandatory": false } }, { - "id": "stepfun/step-3.5-flash", - "canonical_slug": "stepfun/step-3.5-flash", - "hugging_face_id": "stepfun-ai/Step-3.5-Flash", - "name": "StepFun: Step 3.5 Flash", - "created": 1769728337, - "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....", + "id": "tencent/hy3", + "canonical_slug": "tencent/hy3-20260706", + "hugging_face_id": "tencent/Hy3", + "name": "Tencent: Hy3", + "created": 1783344048, + "description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...", "context_length": 262144, "architecture": { "modality": "text->text", @@ -22605,20 +31320,31 @@ "instruct_type": null }, "pricing": { - "prompt": "0.0000001", - "completion": "0.0000003" + "prompt": "0.000000132", + "completion": "0.000000528", + "input_cache_read": "0.000000033" }, "top_provider": { "context_length": 262144, - "max_completion_tokens": 65536, + "max_completion_tokens": 128000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", + "max_completion_tokens", "max_tokens", + "min_p", + "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", "temperature", "tool_choice", "tools", @@ -22626,8 +31352,8 @@ "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, + "temperature": 0.9, + "top_p": 1, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -22637,62 +31363,101 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints" + "details": "/api/v1/models/tencent/hy3-20260706/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1229, + "win_rate": 43.8, + "rank": 41 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1197, + "win_rate": 41.1, + "rank": 51 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1149, + "win_rate": 36.1, + "rank": 74 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1174, + "win_rate": 38.6, + "rank": 62 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1192, + "win_rate": 40.2, + "rank": 58 + }, + { + "arena": "models", + "category": "website", + "elo": 1194, + "win_rate": 41.4, + "rank": 58 + } + ] }, "reasoning": { - "mandatory": true + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "low", "none"], + "default_effort": "high" } }, { - "id": "stepfun/step-3.7-flash", - "canonical_slug": "stepfun/step-3.7-flash-20260528", - "hugging_face_id": "stepfun-ai/Step-3.7-Flash", - "name": "StepFun: Step 3.7 Flash", - "created": 1779985069, - "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...", - "context_length": 256000, + "id": "tencent/hy3-preview", + "canonical_slug": "tencent/hy3-preview-20260421", + "hugging_face_id": "tencent/Hy3-preview", + "name": "Tencent: Hy3 preview", + "created": 1776878150, + "description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...", + "context_length": 262144, "architecture": { - "modality": "text+image+video->text", - "input_modalities": ["text", "image", "video"], + "modality": "text->text", + "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.00000115", - "input_cache_read": "0.00000004" + "prompt": "0.00000018", + "completion": "0.0000006", + "input_cache_read": "0.00000006" }, "top_provider": { - "context_length": 256000, - "max_completion_tokens": 256000, + "context_length": 262144, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", - "logprobs", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", - "response_format", + "reasoning_effort", "seed", - "stop", - "structured_outputs", "temperature", "tool_choice", "tools", - "top_k", - "top_logprobs", "top_p" ], "default_parameters": { - "temperature": null, - "top_p": null, + "temperature": 0.9, + "top_p": 1, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -22702,134 +31467,134 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints" + "details": "/api/v1/models/tencent/hy3-preview-20260421/endpoints" }, "benchmarks": { - "design_arena": [ - { - "arena": "models", - "category": "3d", - "elo": 1197, - "win_rate": 43, - "rank": 48 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1214, - "win_rate": 49.8, - "rank": 17 - }, - { - "arena": "models", - "category": "codecategories", - "elo": 1217, - "win_rate": 45.5, - "rank": 45 - }, - { - "arena": "models", - "category": "dataviz", - "elo": 1213, - "win_rate": 46.7, - "rank": 43 - }, - { - "arena": "models", - "category": "gamedev", - "elo": 1205, - "win_rate": 41.3, - "rank": 46 - }, - { - "arena": "models", - "category": "svg", - "elo": 1125, - "win_rate": 39.9, - "rank": 50 - }, - { - "arena": "models", - "category": "uicomponent", - "elo": 1213, - "win_rate": 44.4, - "rank": 44 - }, - { - "arena": "models", - "category": "website", - "elo": 1225, - "win_rate": 47, - "rank": 44 - } - ], + "design_arena": [], "artificial_analysis": { - "intelligence_index": 29.7, - "coding_index": 37.3, - "agentic_index": 21.5 + "intelligence_index": 42.2, + "coding_index": 58.8, + "agentic_index": 31.4 } }, - "reasoning": { - "mandatory": true, - "supported_efforts": ["high", "medium", "low"], - "default_effort": "medium" + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "low", "none"], + "default_effort": "high" + } + }, + { + "id": "thedrummer/cydonia-24b-v4.1", + "canonical_slug": "thedrummer/cydonia-24b-v4.1", + "hugging_face_id": "thedrummer/cydonia-24b-v4.1", + "name": "TheDrummer: Cydonia 24B V4.1", + "created": 1758931878, + "description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.", + "context_length": 131072, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.0000003", + "completion": "0.0000005", + "input_cache_read": "0.00000015" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": "2024-04-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints" } }, { - "id": "switchpoint/router", - "canonical_slug": "switchpoint/router", - "hugging_face_id": "", - "name": "Switchpoint Router", - "created": 1752272899, - "description": "Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...", - "context_length": 131072, + "id": "thedrummer/rocinante-12b", + "canonical_slug": "thedrummer/rocinante-12b", + "hugging_face_id": "TheDrummer/Rocinante-12B-v1.1", + "name": "TheDrummer: Rocinante 12B", + "created": 1727654400, + "description": "Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...", + "context_length": 65536, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null + "tokenizer": "Qwen", + "instruct_type": "chatml" }, "pricing": { - "prompt": "0.00000085", - "completion": "0.0000034" + "prompt": "0.00000025", + "completion": "0.0000005" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": null, + "context_length": 65536, + "max_completion_tokens": 65536, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "include_reasoning", + "frequency_penalty", + "logit_bias", + "logprobs", "max_tokens", - "reasoning", + "presence_penalty", + "repetition_penalty", "response_format", "seed", "stop", + "structured_outputs", "temperature", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-04-30", "expiration_date": null, "links": { - "details": "/api/v1/models/switchpoint/router/endpoints" - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/thedrummer/rocinante-12b/endpoints" } }, { - "id": "tencent/hunyuan-a13b-instruct", - "canonical_slug": "tencent/hunyuan-a13b-instruct", - "hugging_face_id": "tencent/Hunyuan-A13B-Instruct", - "name": "Tencent: Hunyuan A13B Instruct", - "created": 1751987664, - "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...", - "context_length": 131072, + "id": "thedrummer/skyfall-36b-v2", + "canonical_slug": "thedrummer/skyfall-36b-v2", + "hugging_face_id": "TheDrummer/Skyfall-36B-v2", + "name": "TheDrummer: Skyfall 36B V2", + "created": 1741636566, + "description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.", + "context_length": 32768, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -22838,60 +31603,114 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000014", - "completion": "0.00000057" + "prompt": "0.00000055", + "completion": "0.0000008", + "input_cache_read": "0.00000025" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, + "context_length": 32768, + "max_completion_tokens": 32768, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", - "reasoning", + "presence_penalty", + "repetition_penalty", "response_format", + "seed", + "stop", "structured_outputs", "temperature", "top_k", + "top_logprobs", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-03-31", + "knowledge_cutoff": "2024-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints" - }, - "reasoning": { - "mandatory": false + "details": "/api/v1/models/thedrummer/skyfall-36b-v2/endpoints" } }, { - "id": "tencent/hy3", - "canonical_slug": "tencent/hy3-20260706", - "hugging_face_id": "tencent/Hy3", - "name": "Tencent: Hy3", - "created": 1783344048, - "description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...", - "context_length": 262144, + "id": "thedrummer/unslopnemo-12b", + "canonical_slug": "thedrummer/unslopnemo-12b", + "hugging_face_id": "TheDrummer/UnslopNemo-12B-v4.1", + "name": "TheDrummer: UnslopNemo 12B", + "created": 1731103448, + "description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.", + "context_length": 1024000, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "pricing": { + "prompt": "0.0000004", + "completion": "0.0000004" + }, + "top_provider": { + "context_length": 1024000, + "max_completion_tokens": 1024000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": {}, + "supported_voices": null, + "knowledge_cutoff": "2024-04-30", + "expiration_date": null, + "links": { + "details": "/api/v1/models/thedrummer/unslopnemo-12b/endpoints" + } + }, + { + "id": "thinkingmachines/inkling", + "canonical_slug": "thinkingmachines/inkling-20260715", + "hugging_face_id": "thinkingmachines/Inkling", + "name": "Thinking Machines: Inkling", + "created": 1784325956, + "description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...", + "context_length": 1048576, + "architecture": { + "modality": "text+image+audio->text", + "input_modalities": ["text", "image", "audio"], + "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.0000002", - "completion": "0.0000008", - "input_cache_read": "0.0000005" + "prompt": "0.00000095", + "completion": "0.00000405", + "input_cache_read": "0.00000016" }, "top_provider": { - "context_length": 202752, - "max_completion_tokens": 131072, + "context_length": 524288, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, @@ -22903,10 +31722,11 @@ "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", + "response_format", "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -22914,8 +31734,8 @@ "top_p" ], "default_parameters": { - "temperature": 0.9, - "top_p": 1, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -22925,58 +31745,116 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/tencent/hy3-20260706/endpoints" + "details": "/api/v1/models/thinkingmachines/inkling-20260715/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1217, + "win_rate": 43.9, + "rank": 45 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1216, + "win_rate": 42.7, + "rank": 43 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1196, + "win_rate": 39.9, + "rank": 51 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1190, + "win_rate": 38.1, + "rank": 56 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1203, + "win_rate": 39.8, + "rank": 49 + }, + { + "arena": "models", + "category": "website", + "elo": 1225, + "win_rate": 44.1, + "rank": 43 + } + ], + "artificial_analysis": { + "intelligence_index": 42.3, + "coding_index": 52.1, + "agentic_index": 34.1 + } }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["high", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "high", "medium", "low", "minimal", "none"], "default_effort": "high" } }, { - "id": "tencent/hy3-preview", - "canonical_slug": "tencent/hy3-preview-20260421", - "hugging_face_id": "tencent/Hy3-preview", - "name": "Tencent: Hy3 preview", - "created": 1776878150, - "description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...", - "context_length": 262144, + "id": "thinkingmachines/inkling-small", + "canonical_slug": "thinkingmachines/inkling-small-20260730", + "hugging_face_id": "thinkingmachines/Inkling-Small", + "name": "Thinking Machines: Inkling Small", + "created": 1785443117, + "description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...", + "context_length": 524288, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+audio->text", + "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0.000000063", - "completion": "0.00000021", - "input_cache_read": "0.000000021" + "prompt": "0.00000045", + "completion": "0.0000012", + "input_cache_read": "0.0000001" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": null, + "context_length": 524288, + "max_completion_tokens": 262144, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", + "logprobs", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "reasoning_effort", + "repetition_penalty", "seed", "stop", + "structured_outputs", "temperature", "tool_choice", "tools", "top_k", + "top_logprobs", "top_p" ], "default_parameters": { - "temperature": 0.9, - "top_p": 1, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -22986,50 +31864,60 @@ "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/tencent/hy3-preview-20260421/endpoints" + "details": "/api/v1/models/thinkingmachines/inkling-small-20260730/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 41.2, + "coding_index": 52.9, + "agentic_index": 31.9 + } }, "reasoning": { "mandatory": false, "default_enabled": true, - "supported_efforts": ["high", "low", "none"], + "supported_efforts": ["max", "high", "medium", "low", "minimal", "none"], "default_effort": "high" } }, - { - "id": "tencent/hy3:free", - "canonical_slug": "tencent/hy3-20260706", - "hugging_face_id": "tencent/Hy3", - "name": "Tencent: Hy3 (free)", - "created": 1783344048, - "description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...", - "context_length": 262144, + { + "id": "thinkingmachines/inkling:batch", + "canonical_slug": "thinkingmachines/inkling-20260715", + "hugging_face_id": "thinkingmachines/Inkling", + "name": "Thinking Machines: Inkling (batch)", + "created": 1784325956, + "description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...", + "context_length": 524288, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+audio->text", + "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "tokenizer": "Other", "instruct_type": null }, "pricing": { - "prompt": "0", - "completion": "0" + "prompt": "0.0000005", + "completion": "0.000002025", + "input_cache_read": "0.000000085" }, "top_provider": { - "context_length": 262144, - "max_completion_tokens": 262144, + "context_length": 524288, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", + "logit_bias", "max_tokens", + "min_p", "presence_penalty", "reasoning", + "reasoning_effort", "repetition_penalty", - "seed", "stop", - "structured_outputs", "temperature", "tool_choice", "tools", @@ -23037,8 +31925,8 @@ "top_p" ], "default_parameters": { - "temperature": 0.9, - "top_p": 1, + "temperature": null, + "top_p": null, "top_k": null, "frequency_penalty": null, "presence_penalty": null, @@ -23046,40 +31934,90 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": "2026-07-21", + "expiration_date": null, "links": { - "details": "/api/v1/models/tencent/hy3-20260706/endpoints" + "details": "/api/v1/models/thinkingmachines/inkling-20260715/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "3d", + "elo": 1217, + "win_rate": 43.9, + "rank": 45 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1216, + "win_rate": 42.7, + "rank": 43 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1196, + "win_rate": 39.9, + "rank": 51 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1190, + "win_rate": 38.1, + "rank": 56 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1203, + "win_rate": 39.8, + "rank": 49 + }, + { + "arena": "models", + "category": "website", + "elo": 1225, + "win_rate": 44.1, + "rank": 43 + } + ], + "artificial_analysis": { + "intelligence_index": 42.3, + "coding_index": 52.1, + "agentic_index": 34.1 + } }, "reasoning": { "mandatory": false, - "default_enabled": false, - "supported_efforts": ["high", "low", "none"], + "default_enabled": true, + "supported_efforts": ["max", "high", "medium", "low", "minimal", "none"], "default_effort": "high" } }, { - "id": "thedrummer/cydonia-24b-v4.1", - "canonical_slug": "thedrummer/cydonia-24b-v4.1", - "hugging_face_id": "thedrummer/cydonia-24b-v4.1", - "name": "TheDrummer: Cydonia 24B V4.1", - "created": 1758931878, - "description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.", - "context_length": 131072, + "id": "undi95/remm-slerp-l2-13b", + "canonical_slug": "undi95/remm-slerp-l2-13b", + "hugging_face_id": "Undi95/ReMM-SLERP-L2-13B", + "name": "ReMM SLERP 13B", + "created": 1689984000, + "description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge", + "context_length": 6144, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Other", - "instruct_type": null + "tokenizer": "Llama2", + "instruct_type": "alpaca" }, "pricing": { - "prompt": "0.0000003", - "completion": "0.0000005", - "input_cache_read": "0.00000015" + "prompt": "0.00000045", + "completion": "0.00000065" }, "top_provider": { - "context_length": 131072, - "max_completion_tokens": 131072, + "context_length": 6144, + "max_completion_tokens": 6144, "is_moderated": false }, "per_request_limits": null, @@ -23088,6 +32026,7 @@ "logit_bias", "logprobs", "max_tokens", + "min_p", "presence_penalty", "repetition_penalty", "response_format", @@ -23095,80 +32034,92 @@ "stop", "structured_outputs", "temperature", + "top_a", "top_k", "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "frequency_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-04-30", + "knowledge_cutoff": "2023-06-30", "expiration_date": null, "links": { - "details": "/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints" + "details": "/api/v1/models/undi95/remm-slerp-l2-13b/endpoints" } }, { - "id": "thedrummer/rocinante-12b", - "canonical_slug": "thedrummer/rocinante-12b", - "hugging_face_id": "TheDrummer/Rocinante-12B-v1.1", - "name": "TheDrummer: Rocinante 12B", - "created": 1727654400, - "description": "Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...", - "context_length": 65536, + "id": "upstage/solar-pro-3", + "canonical_slug": "upstage/solar-pro-3", + "hugging_face_id": "", + "name": "Upstage: Solar Pro 3", + "created": 1769481200, + "description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...", + "context_length": 131072, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Qwen", - "instruct_type": "chatml" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.00000025", - "completion": "0.0000005" + "prompt": "0.00000015", + "completion": "0.0000006", + "input_cache_read": "0.000000015" }, "top_provider": { - "context_length": 65536, - "max_completion_tokens": 65536, + "context_length": 131072, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", - "min_p", "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", - "seed", - "stop", "structured_outputs", "temperature", - "top_k", - "top_logprobs", + "tool_choice", + "tools", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-04-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/thedrummer/rocinante-12b/endpoints" + "details": "/api/v1/models/upstage/solar-pro-3/endpoints" + }, + "benchmarks": { + "design_arena": [], + "artificial_analysis": { + "intelligence_index": 14.5, + "coding_index": 16.2, + "agentic_index": 2.9 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "thedrummer/skyfall-36b-v2", - "canonical_slug": "thedrummer/skyfall-36b-v2", - "hugging_face_id": "TheDrummer/Skyfall-36B-v2", - "name": "TheDrummer: Skyfall 36B V2", - "created": 1741636566, - "description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.", - "context_length": 32768, + "id": "upstage/solar-pro4", + "canonical_slug": "upstage/solar-pro4-20260810", + "hugging_face_id": null, + "name": "Upstage: Solar Pro 4", + "created": 1786371636, + "description": "Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...", + "context_length": 524288, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -23177,175 +32128,331 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000055", - "completion": "0.0000008", - "input_cache_read": "0.00000025" + "prompt": "0.00000003", + "completion": "0.00000012", + "input_cache_read": "0.000000006" }, "top_provider": { - "context_length": 32768, - "max_completion_tokens": 32768, + "context_length": 524288, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", - "logit_bias", - "logprobs", + "include_reasoning", "max_tokens", "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", - "seed", - "stop", "structured_outputs", "temperature", - "top_k", - "top_logprobs", + "tool_choice", + "tools", "top_p" ], "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2024-06-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/thedrummer/skyfall-36b-v2/endpoints" + "details": "/api/v1/models/upstage/solar-pro4-20260810/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "models", + "category": "dataviz", + "elo": 1133, + "win_rate": 29.6, + "rank": 78 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1155, + "win_rate": 32.1, + "rank": 70 + }, + { + "arena": "models", + "category": "website", + "elo": 1160, + "win_rate": 33.6, + "rank": 71 + } + ], + "artificial_analysis": { + "intelligence_index": 41.6, + "coding_index": 52.7, + "agentic_index": 33.6 + } + }, + "reasoning": { + "mandatory": false } }, { - "id": "thedrummer/unslopnemo-12b", - "canonical_slug": "thedrummer/unslopnemo-12b", - "hugging_face_id": "TheDrummer/UnslopNemo-12B-v4.1", - "name": "TheDrummer: UnslopNemo 12B", - "created": 1731103448, - "description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.", - "context_length": 32768, + "id": "writer/palmyra-x5", + "canonical_slug": "writer/palmyra-x5-20250428", + "hugging_face_id": "", + "name": "Writer: Palmyra X5", + "created": 1769003823, + "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...", + "context_length": 1040000, "architecture": { "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"], - "tokenizer": "Mistral", - "instruct_type": "mistral" + "tokenizer": "Other", + "instruct_type": null }, "pricing": { - "prompt": "0.0000004", - "completion": "0.0000004" + "prompt": "0.0000006", + "completion": "0.000006" }, - "top_provider": { - "context_length": 32768, - "max_completion_tokens": 32768, - "is_moderated": false + "top_provider": { + "context_length": 1040000, + "max_completion_tokens": 8192, + "is_moderated": true }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logprobs", "max_tokens", - "presence_penalty", - "repetition_penalty", - "response_format", - "seed", "stop", - "structured_outputs", "temperature", - "tool_choice", - "tools", - "top_logprobs", + "top_k", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "frequency_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2024-04-30", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/thedrummer/unslopnemo-12b/endpoints" + "details": "/api/v1/models/writer/palmyra-x5-20250428/endpoints" } }, { - "id": "undi95/remm-slerp-l2-13b", - "canonical_slug": "undi95/remm-slerp-l2-13b", - "hugging_face_id": "Undi95/ReMM-SLERP-L2-13B", - "name": "ReMM SLERP 13B", - "created": 1689984000, - "description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge", - "context_length": 6144, + "id": "x-ai/grok-4.20", + "canonical_slug": "x-ai/grok-4.20-20260309", + "hugging_face_id": "", + "name": "SpaceXAI: Grok 4.20", + "created": 1774979019, + "description": "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...", + "context_length": 2000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Llama2", - "instruct_type": "alpaca" + "tokenizer": "Grok", + "instruct_type": null }, "pricing": { - "prompt": "0.00000045", - "completion": "0.00000065" + "prompt": "0.00000125", + "completion": "0.0000025", + "web_search": "0.005", + "input_cache_read": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000005", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { - "context_length": 6144, - "max_completion_tokens": 4096, + "context_length": 2000000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", - "logit_bias", + "include_reasoning", "logprobs", "max_tokens", - "min_p", - "presence_penalty", - "repetition_penalty", + "reasoning", "response_format", "seed", - "stop", "structured_outputs", "temperature", - "top_a", - "top_k", + "tool_choice", + "tools", "top_logprobs", "top_p" ], - "default_parameters": {}, + "default_parameters": { + "temperature": null, + "top_p": null, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, "supported_voices": null, - "knowledge_cutoff": "2023-06-30", + "knowledge_cutoff": "2025-09-01", "expiration_date": null, "links": { - "details": "/api/v1/models/undi95/remm-slerp-l2-13b/endpoints" + "details": "/api/v1/models/x-ai/grok-4.20-20260309/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "androidnative", + "elo": 1078, + "win_rate": 35.1, + "rank": 34 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1089, + "win_rate": 41, + "rank": 28 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1089, + "win_rate": 38.5, + "rank": 26 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1175, + "win_rate": 45.7, + "rank": 13 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1143, + "win_rate": 45.4, + "rank": 32 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1183, + "win_rate": 48.6, + "rank": 22 + }, + { + "arena": "models", + "category": "3d", + "elo": 1246, + "win_rate": 52.9, + "rank": 37 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1210, + "win_rate": 48.6, + "rank": 18 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1239, + "win_rate": 52.9, + "rank": 37 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1241, + "win_rate": 52.7, + "rank": 37 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1234, + "win_rate": 52.2, + "rank": 40 + }, + { + "arena": "models", + "category": "svg", + "elo": 1199, + "win_rate": 53.6, + "rank": 28 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1231, + "win_rate": 50.5, + "rank": 41 + }, + { + "arena": "models", + "category": "website", + "elo": 1239, + "win_rate": 53, + "rank": 37 + } + ] + }, + "reasoning": { + "mandatory": false, + "default_enabled": false } }, { - "id": "upstage/solar-pro-3", - "canonical_slug": "upstage/solar-pro-3", + "id": "x-ai/grok-4.20-multi-agent", + "canonical_slug": "x-ai/grok-4.20-multi-agent-20260309", "hugging_face_id": "", - "name": "Upstage: Solar Pro 3", - "created": 1769481200, - "description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...", - "context_length": 128000, + "name": "SpaceXAI: Grok 4.20 Multi-Agent", + "created": 1774979158, + "description": "Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...", + "context_length": 2000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Grok", "instruct_type": null }, "pricing": { - "prompt": "0.00000015", - "completion": "0.0000006", - "input_cache_read": "0.000000015" + "prompt": "0.00000125", + "completion": "0.0000025", + "web_search": "0.005", + "input_cache_read": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000005", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { - "context_length": 128000, + "context_length": 2000000, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", + "logprobs", "max_tokens", "reasoning", + "reasoning_effort", "response_format", + "seed", "structured_outputs", "temperature", - "tool_choice", - "tools" + "top_logprobs", + "top_p" ], "default_parameters": { "temperature": null, @@ -23356,75 +32463,256 @@ "repetition_penalty": null }, "supported_voices": null, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-09-01", "expiration_date": null, "links": { - "details": "/api/v1/models/upstage/solar-pro-3/endpoints" - }, - "benchmarks": { - "design_arena": [], - "artificial_analysis": { - "intelligence_index": 14.1, - "coding_index": 16.2, - "agentic_index": 2.7 - } + "details": "/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints" }, "reasoning": { - "mandatory": false + "mandatory": true, + "default_enabled": true, + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "medium" } }, { - "id": "writer/palmyra-x5", - "canonical_slug": "writer/palmyra-x5-20250428", - "hugging_face_id": "", - "name": "Writer: Palmyra X5", - "created": 1769003823, - "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...", - "context_length": 1040000, + "id": "x-ai/grok-4.3", + "canonical_slug": "x-ai/grok-4.3-20260430", + "hugging_face_id": null, + "name": "SpaceXAI: Grok 4.3", + "created": 1777591821, + "description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...", + "context_length": 1000000, "architecture": { - "modality": "text->text", - "input_modalities": ["text"], + "modality": "text+image+file->text", + "input_modalities": ["text", "image", "file"], "output_modalities": ["text"], - "tokenizer": "Other", + "tokenizer": "Grok", "instruct_type": null }, "pricing": { - "prompt": "0.0000006", - "completion": "0.000006" + "prompt": "0.00000125", + "completion": "0.0000025", + "web_search": "0.005", + "input_cache_read": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.0000025", + "completion": "0.000005", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { - "context_length": 1040000, - "max_completion_tokens": 8192, - "is_moderated": true + "context_length": 1000000, + "max_completion_tokens": null, + "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", "max_tokens", + "presence_penalty", + "reasoning", + "reasoning_effort", + "response_format", + "seed", "stop", + "structured_outputs", "temperature", - "top_k", + "tool_choice", + "tools", + "top_logprobs", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/writer/palmyra-x5-20250428/endpoints" + "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1007, + "win_rate": 28, + "rank": 19 + }, + { + "arena": "agents", + "category": "agentichtmlslides", + "elo": 1066, + "win_rate": 31.8, + "rank": 10 + }, + { + "arena": "agents", + "category": "agenticslides", + "elo": 1072, + "win_rate": 31.9, + "rank": 10 + }, + { + "arena": "agents", + "category": "agenticslides(html)", + "elo": 1066, + "win_rate": 31.7, + "rank": 10 + }, + { + "arena": "agents", + "category": "agenticslides(python-pptx)", + "elo": 1068, + "win_rate": 32.4, + "rank": 10 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 993, + "win_rate": 22.7, + "rank": 36 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1042, + "win_rate": 29.6, + "rank": 36 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1035, + "win_rate": 31.2, + "rank": 29 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1050, + "win_rate": 29.8, + "rank": 21 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1112, + "win_rate": 36.8, + "rank": 35 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1071, + "win_rate": 32.5, + "rank": 9 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1072, + "win_rate": 30.8, + "rank": 20 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1171, + "win_rate": 44.4, + "rank": 24 + }, + { + "arena": "models", + "category": "3d", + "elo": 1177, + "win_rate": 43.3, + "rank": 57 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1169, + "win_rate": 45.5, + "rank": 36 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1206, + "win_rate": 46.5, + "rank": 46 + }, + { + "arena": "models", + "category": "dataviz", + "elo": 1205, + "win_rate": 46.5, + "rank": 47 + }, + { + "arena": "models", + "category": "gamedev", + "elo": 1214, + "win_rate": 48.1, + "rank": 46 + }, + { + "arena": "models", + "category": "svg", + "elo": 1120, + "win_rate": 41.2, + "rank": 51 + }, + { + "arena": "models", + "category": "uicomponent", + "elo": 1222, + "win_rate": 47.1, + "rank": 43 + }, + { + "arena": "models", + "category": "website", + "elo": 1204, + "win_rate": 46.3, + "rank": 50 + } + ], + "artificial_analysis": { + "intelligence_index": 37.9, + "coding_index": 42.2, + "agentic_index": 24.2 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true, + "supported_efforts": ["high", "medium", "low", "none"], + "default_effort": "low" } }, { - "id": "x-ai/grok-4.20", - "canonical_slug": "x-ai/grok-4.20-20260309", - "hugging_face_id": "", - "name": "xAI: Grok 4.20", - "created": 1774979019, - "description": "Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...", - "context_length": 2000000, + "id": "x-ai/grok-4.5", + "canonical_slug": "x-ai/grok-4.5-20260708", + "hugging_face_id": null, + "name": "SpaceXAI: Grok 4.5", + "created": 1783523154, + "description": "Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.", + "context_length": 500000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -23433,24 +32721,36 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.0000025", + "prompt": "0.000002", + "completion": "0.000006", "web_search": "0.005", - "input_cache_read": "0.0000002" + "input_cache_read": "0.0000003", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000012", + "input_cache_read": "0.0000006" + } + ] }, "top_provider": { - "context_length": 2000000, + "context_length": 500000, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ + "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", + "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", + "stop", "structured_outputs", "temperature", "tool_choice", @@ -23458,188 +32758,149 @@ "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, - "knowledge_cutoff": "2025-09-01", + "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/x-ai/grok-4.20-20260309/endpoints" + "details": "/api/v1/models/x-ai/grok-4.5-20260708/endpoints" }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1220, + "win_rate": 56.6, + "rank": 5 + }, { "arena": "agents", "category": "androidnative", - "elo": 1176, - "win_rate": 44.1, - "rank": 16 + "elo": 1273, + "win_rate": 67.7, + "rank": 2 }, { "arena": "agents", "category": "fullstack", - "elo": 1119, - "win_rate": 41.2, - "rank": 18 + "elo": 1280, + "win_rate": 63.3, + "rank": 8 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1131, - "win_rate": 38.5, - "rank": 17 + "elo": 1271, + "win_rate": 62.2, + "rank": 2 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1220, + "win_rate": 52.9, + "rank": 5 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1253, + "win_rate": 55, + "rank": 7 }, { "arena": "agents", - "category": "mobileapps", - "elo": 1182, - "win_rate": 48.4, - "rank": 20 + "category": "python-pptxslides", + "elo": 1241, + "win_rate": 54.5, + "rank": 8 }, { "arena": "agents", "category": "webapps", - "elo": 1214, - "win_rate": 50, - "rank": 12 + "elo": 1252, + "win_rate": 53.9, + "rank": 11 }, { "arena": "models", "category": "3d", - "elo": 1266, - "win_rate": 53.8, - "rank": 29 + "elo": 1311, + "win_rate": 50.3, + "rank": 14 }, { "arena": "models", "category": "asciiart", - "elo": 1225, - "win_rate": 49.8, - "rank": 14 + "elo": 1298, + "win_rate": 58.3, + "rank": 5 }, { "arena": "models", "category": "codecategories", - "elo": 1267, - "win_rate": 54.7, - "rank": 27 + "elo": 1300, + "win_rate": 52.5, + "rank": 11 }, { "arena": "models", "category": "dataviz", - "elo": 1252, - "win_rate": 53, - "rank": 28 + "elo": 1299, + "win_rate": 51.5, + "rank": 14 }, { "arena": "models", "category": "gamedev", - "elo": 1262, - "win_rate": 53.9, - "rank": 29 + "elo": 1307, + "win_rate": 50.7, + "rank": 16 }, { "arena": "models", "category": "svg", - "elo": 1221, - "win_rate": 54.2, - "rank": 22 + "elo": 1257, + "win_rate": 50.4, + "rank": 10 }, { "arena": "models", "category": "uicomponent", - "elo": 1253, + "elo": 1314, "win_rate": 52.3, - "rank": 30 + "rank": 11 }, { "arena": "models", "category": "website", - "elo": 1270, - "win_rate": 55.1, - "rank": 25 + "elo": 1303, + "win_rate": 55.8, + "rank": 11 } - ] - }, - "reasoning": { - "mandatory": false, - "default_enabled": false - } - }, - { - "id": "x-ai/grok-4.20-multi-agent", - "canonical_slug": "x-ai/grok-4.20-multi-agent-20260309", - "hugging_face_id": "", - "name": "xAI: Grok 4.20 Multi-Agent", - "created": 1774979158, - "description": "Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...", - "context_length": 2000000, - "architecture": { - "modality": "text+image+file->text", - "input_modalities": ["text", "image", "file"], - "output_modalities": ["text"], - "tokenizer": "Grok", - "instruct_type": null - }, - "pricing": { - "prompt": "0.00000125", - "completion": "0.0000025", - "web_search": "0.005", - "input_cache_read": "0.0000002" - }, - "top_provider": { - "context_length": 2000000, - "max_completion_tokens": null, - "is_moderated": false - }, - "per_request_limits": null, - "supported_parameters": [ - "include_reasoning", - "logprobs", - "max_tokens", - "reasoning", - "response_format", - "seed", - "structured_outputs", - "temperature", - "top_logprobs", - "top_p" - ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, - "supported_voices": null, - "knowledge_cutoff": "2025-09-01", - "expiration_date": null, - "links": { - "details": "/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints" + ], + "artificial_analysis": { + "intelligence_index": 55.8, + "coding_index": 72.4, + "agentic_index": 48.9 + } }, "reasoning": { "mandatory": true, "default_enabled": true, - "supported_efforts": ["xhigh", "high", "medium", "low"], - "default_effort": "medium" + "supported_efforts": ["high", "medium", "low"], + "default_effort": "high" } }, { - "id": "x-ai/grok-4.3", - "canonical_slug": "x-ai/grok-4.3-20260430", + "id": "x-ai/grok-4.6", + "canonical_slug": "x-ai/grok-4.6-20260810", "hugging_face_id": null, - "name": "xAI: Grok 4.3", - "created": 1777591821, - "description": "Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...", - "context_length": 1000000, + "name": "SpaceXAI: Grok 4.6", + "created": 1786548957, + "description": "Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.", + "context_length": 500000, "architecture": { "modality": "text+image+file->text", "input_modalities": ["text", "image", "file"], @@ -23648,13 +32909,21 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000125", - "completion": "0.0000025", + "prompt": "0.000002", + "completion": "0.000006", "web_search": "0.005", - "input_cache_read": "0.0000002" + "input_cache_read": "0.0000005", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000004", + "completion": "0.000012", + "input_cache_read": "0.000001" + } + ] }, "top_provider": { - "context_length": 1000000, + "context_length": 500000, "max_completion_tokens": null, "is_moderated": false }, @@ -23666,6 +32935,7 @@ "max_tokens", "presence_penalty", "reasoning", + "reasoning_effort", "response_format", "seed", "stop", @@ -23676,190 +32946,106 @@ "top_logprobs", "top_p" ], - "default_parameters": { - "temperature": null, - "top_p": null, - "top_k": null, - "frequency_penalty": null, - "presence_penalty": null, - "repetition_penalty": null - }, + "default_parameters": {}, "supported_voices": null, "knowledge_cutoff": null, "expiration_date": null, "links": { - "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints" + "details": "/api/v1/models/x-ai/grok-4.6-20260810/endpoints" }, "benchmarks": { "design_arena": [ - { - "arena": "agents", - "category": "agenticgamedev", - "elo": 1027, - "win_rate": 27.8, - "rank": 12 - }, - { - "arena": "agents", - "category": "agentichtmlslides", - "elo": 1066, - "win_rate": 31.8, - "rank": 10 - }, - { - "arena": "agents", - "category": "agenticslides", - "elo": 1072, - "win_rate": 31.9, - "rank": 10 - }, - { - "arena": "agents", - "category": "agenticslides(html)", - "elo": 1066, - "win_rate": 31.7, - "rank": 10 - }, - { - "arena": "agents", - "category": "agenticslides(python-pptx)", - "elo": 1068, - "win_rate": 32.4, - "rank": 10 - }, { "arena": "agents", "category": "androidnative", - "elo": 1078, - "win_rate": 29, - "rank": 22 + "elo": 1208, + "win_rate": 49.8, + "rank": 18 }, { "arena": "agents", "category": "fullstack", - "elo": 1078, - "win_rate": 32.1, - "rank": 25 - }, - { - "arena": "agents", - "category": "godotgamedev", - "elo": 1132, - "win_rate": 38.6, - "rank": 16 - }, - { - "arena": "agents", - "category": "htmlslides", - "elo": 1067, - "win_rate": 31.8, - "rank": 12 + "elo": 1288, + "win_rate": 55, + "rank": 5 }, { "arena": "agents", "category": "mobileapps", - "elo": 1139, - "win_rate": 38.8, - "rank": 27 - }, - { - "arena": "agents", - "category": "pptxslides", - "elo": 1071, - "win_rate": 32.5, - "rank": 9 - }, - { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1072, - "win_rate": 30.8, - "rank": 11 + "elo": 1270, + "win_rate": 56.5, + "rank": 2 }, { "arena": "agents", "category": "webapps", - "elo": 1195, - "win_rate": 46.4, - "rank": 15 + "elo": 1277, + "win_rate": 56.8, + "rank": 6 }, { "arena": "models", "category": "3d", - "elo": 1202, - "win_rate": 44.6, - "rank": 44 - }, - { - "arena": "models", - "category": "asciiart", - "elo": 1192, - "win_rate": 47.3, - "rank": 27 + "elo": 1346, + "win_rate": 56.4, + "rank": 7 }, { "arena": "models", "category": "codecategories", - "elo": 1242, - "win_rate": 49.4, - "rank": 32 + "elo": 1327, + "win_rate": 56.3, + "rank": 6 }, { "arena": "models", "category": "dataviz", - "elo": 1231, - "win_rate": 48.1, - "rank": 36 + "elo": 1336, + "win_rate": 56.6, + "rank": 6 }, { "arena": "models", "category": "gamedev", - "elo": 1242, - "win_rate": 49.5, - "rank": 35 - }, - { - "arena": "models", - "category": "svg", - "elo": 1142, - "win_rate": 41.9, - "rank": 46 + "elo": 1356, + "win_rate": 58.8, + "rank": 5 }, { "arena": "models", "category": "uicomponent", - "elo": 1249, - "win_rate": 48.9, - "rank": 32 + "elo": 1346, + "win_rate": 59, + "rank": 4 }, { "arena": "models", "category": "website", - "elo": 1243, - "win_rate": 49.9, - "rank": 33 + "elo": 1309, + "win_rate": 54.6, + "rank": 8 } ], "artificial_analysis": { - "intelligence_index": 37.6, - "coding_index": 42.2, - "agentic_index": 24.1 + "intelligence_index": 60.9, + "coding_index": 76.8, + "agentic_index": 58.7 } }, "reasoning": { - "mandatory": false, + "mandatory": true, "default_enabled": true, - "supported_efforts": ["high", "medium", "low", "none"], - "default_effort": "low" + "supported_efforts": ["xhigh", "high", "medium", "low"], + "default_effort": "high" } }, { "id": "x-ai/grok-build-0.1", "canonical_slug": "x-ai/grok-build-0.1-20260520", "hugging_face_id": null, - "name": "xAI: Grok Build 0.1", + "name": "SpaceXAI: Grok Build 0.1", "created": 1779298123, - "description": "Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...", + "description": "Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...", "context_length": 256000, "architecture": { "modality": "text+image+file->text", @@ -23872,7 +33058,15 @@ "prompt": "0.000001", "completion": "0.000002", "web_search": "0.005", - "input_cache_read": "0.0000002" + "input_cache_read": "0.0000002", + "overrides": [ + { + "min_prompt_tokens": 200000, + "prompt": "0.000002", + "completion": "0.000004", + "input_cache_read": "0.0000004" + } + ] }, "top_provider": { "context_length": 256000, @@ -23914,9 +33108,9 @@ "benchmarks": { "design_arena": [], "artificial_analysis": { - "intelligence_index": 39.8, + "intelligence_index": 40.7, "coding_index": 51.5, - "agentic_index": 28 + "agentic_index": 28.9 } }, "reasoning": { @@ -23930,7 +33124,7 @@ "name": "Xiaomi: MiMo-V2.5", "created": 1776874269, "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...", - "context_length": 1048576, + "context_length": 1050000, "architecture": { "modality": "text+image+audio+video->text", "input_modalities": ["text", "audio", "image", "video"], @@ -23939,13 +33133,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.000000105", + "prompt": "0.00000014", "completion": "0.00000028", - "input_cache_read": "0.000000028" + "input_cache_read": "0.0000000028" }, "top_provider": { - "context_length": 32000, - "max_completion_tokens": null, + "context_length": 1048576, + "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, @@ -23989,60 +33183,65 @@ { "arena": "models", "category": "3d", - "elo": 1294, - "win_rate": 53.2, - "rank": 19 + "elo": 1268, + "win_rate": 51.7, + "rank": 31 }, { "arena": "models", "category": "asciiart", - "elo": 1187, - "win_rate": 47, - "rank": 29 + "elo": 1167, + "win_rate": 45.6, + "rank": 38 }, { "arena": "models", "category": "codecategories", - "elo": 1302, + "elo": 1280, "win_rate": 54.8, - "rank": 15 + "rank": 22 }, { "arena": "models", "category": "dataviz", - "elo": 1283, - "win_rate": 54.2, - "rank": 15 + "elo": 1276, + "win_rate": 55.2, + "rank": 19 }, { "arena": "models", "category": "gamedev", - "elo": 1298, - "win_rate": 55.6, - "rank": 17 + "elo": 1278, + "win_rate": 55, + "rank": 25 }, { "arena": "models", "category": "svg", - "elo": 1221, - "win_rate": 52.5, - "rank": 23 + "elo": 1207, + "win_rate": 52.6, + "rank": 25 }, { "arena": "models", "category": "uicomponent", - "elo": 1310, - "win_rate": 56, - "rank": 13 + "elo": 1288, + "win_rate": 55.1, + "rank": 23 }, { "arena": "models", "category": "website", - "elo": 1304, - "win_rate": 55.2, - "rank": 12 + "elo": 1279, + "win_rate": 55, + "rank": 23 } - ] + ], + "artificial_analysis": { + "intelligence_index": 38, + "coding_index": 56.8, + "agentic_index": 24.4 + } }, "reasoning": { "mandatory": false @@ -24055,7 +33254,7 @@ "name": "Xiaomi: MiMo-V2.5-Pro", "created": 1776874273, "description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....", - "context_length": 1048576, + "context_length": 1050000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -24114,64 +33313,64 @@ { "arena": "models", "category": "3d", - "elo": 1321, - "win_rate": 57.1, - "rank": 12 + "elo": 1299, + "win_rate": 55.8, + "rank": 20 }, { "arena": "models", "category": "asciiart", - "elo": 1199, - "win_rate": 50.7, - "rank": 23 + "elo": 1178, + "win_rate": 47.4, + "rank": 31 }, { "arena": "models", "category": "codecategories", - "elo": 1319, - "win_rate": 57.5, - "rank": 10 + "elo": 1292, + "win_rate": 54.6, + "rank": 17 }, { "arena": "models", "category": "dataviz", - "elo": 1294, - "win_rate": 58.2, - "rank": 10 + "elo": 1290, + "win_rate": 51.8, + "rank": 15 }, { "arena": "models", "category": "gamedev", - "elo": 1338, - "win_rate": 61.1, - "rank": 8 + "elo": 1302, + "win_rate": 55.1, + "rank": 17 }, { "arena": "models", "category": "svg", - "elo": 1237, - "win_rate": 54.8, - "rank": 18 + "elo": 1215, + "win_rate": 51.8, + "rank": 23 }, { "arena": "models", "category": "uicomponent", - "elo": 1301, - "win_rate": 56, - "rank": 15 + "elo": 1294, + "win_rate": 55.7, + "rank": 20 }, { "arena": "models", "category": "website", - "elo": 1310, - "win_rate": 56.3, - "rank": 11 + "elo": 1286, + "win_rate": 54.4, + "rank": 16 } ], "artificial_analysis": { - "intelligence_index": 42.2, + "intelligence_index": 42.9, "coding_index": 60.2, - "agentic_index": 29.1 + "agentic_index": 29.5 } }, "reasoning": { @@ -24231,51 +33430,51 @@ { "arena": "models", "category": "3d", - "elo": 1248, - "win_rate": 59.7, - "rank": 31 + "elo": 1224, + "win_rate": 59.9, + "rank": 42 }, { "arena": "models", "category": "codecategories", - "elo": 1214, + "elo": 1184, "win_rate": 54.4, - "rank": 48 + "rank": 61 }, { "arena": "models", "category": "dataviz", - "elo": 1203, + "elo": 1182, "win_rate": 53.3, - "rank": 48 + "rank": 60 }, { "arena": "models", "category": "gamedev", - "elo": 1211, - "win_rate": 54.4, - "rank": 42 + "elo": 1185, + "win_rate": 54.7, + "rank": 57 }, { "arena": "models", "category": "svg", - "elo": 1154, - "win_rate": 50.8, - "rank": 43 + "elo": 1126, + "win_rate": 49.4, + "rank": 49 }, { "arena": "models", "category": "uicomponent", - "elo": 1198, + "elo": 1173, "win_rate": 55.1, - "rank": 50 + "rank": 63 }, { "arena": "models", "category": "website", - "elo": 1212, - "win_rate": 53.8, - "rank": 49 + "elo": 1180, + "win_rate": 53.6, + "rank": 63 } ] }, @@ -24340,51 +33539,51 @@ { "arena": "models", "category": "3d", - "elo": 1200, - "win_rate": 54.1, - "rank": 45 + "elo": 1176, + "win_rate": 54.3, + "rank": 59 }, { "arena": "models", "category": "codecategories", - "elo": 1187, - "win_rate": 51.5, - "rank": 59 + "elo": 1156, + "win_rate": 51.4, + "rank": 71 }, { "arena": "models", "category": "dataviz", - "elo": 1236, - "win_rate": 59.4, - "rank": 34 + "elo": 1209, + "win_rate": 58.5, + "rank": 46 }, { "arena": "models", "category": "gamedev", - "elo": 1160, - "win_rate": 48.4, - "rank": 62 + "elo": 1133, + "win_rate": 48.7, + "rank": 77 }, { "arena": "models", "category": "svg", - "elo": 1129, - "win_rate": 50.8, - "rank": 49 + "elo": 1104, + "win_rate": 49.4, + "rank": 55 }, { "arena": "models", "category": "uicomponent", - "elo": 1178, - "win_rate": 54.6, - "rank": 55 + "elo": 1151, + "win_rate": 54.5, + "rank": 69 }, { "arena": "models", "category": "website", - "elo": 1189, - "win_rate": 51.3, - "rank": 58 + "elo": 1157, + "win_rate": 51.2, + "rank": 74 } ] }, @@ -24456,7 +33655,7 @@ "name": "Z.ai: GLM 4.6", "created": 1759235576, "description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...", - "context_length": 202752, + "context_length": 204800, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -24465,12 +33664,12 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000043", - "completion": "0.00000174", - "input_cache_read": "0.00000008" + "prompt": "0.00000055", + "completion": "0.0000022", + "input_cache_read": "0.00000011" }, "top_provider": { - "context_length": 202752, + "context_length": 204800, "max_completion_tokens": 131072, "is_moderated": false }, @@ -24513,85 +33712,85 @@ { "arena": "agents", "category": "androidnative", - "elo": 1095, + "elo": 1120, "win_rate": 52.6, - "rank": 20 + "rank": 28 }, { "arena": "agents", "category": "fullstack", - "elo": 1097, + "elo": 1068, "win_rate": 42.3, - "rank": 22 + "rank": 34 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1220, + "elo": 1180, "win_rate": 53.2, - "rank": 6 + "rank": 13 }, { "arena": "agents", "category": "mobileapps", - "elo": 1182, - "win_rate": 49.3, - "rank": 19 + "elo": 1148, + "win_rate": 46.8, + "rank": 27 }, { "arena": "models", "category": "3d", - "elo": 1205, - "win_rate": 54, - "rank": 43 + "elo": 1183, + "win_rate": 54.3, + "rank": 56 }, { "arena": "models", "category": "codecategories", - "elo": 1215, - "win_rate": 54.3, - "rank": 47 + "elo": 1185, + "win_rate": 54.2, + "rank": 60 }, { "arena": "models", - "category": "dataviz", - "elo": 1208, - "win_rate": 52.8, - "rank": 45 + "category": "dataviz", + "elo": 1184, + "win_rate": 52.5, + "rank": 59 }, { "arena": "models", "category": "gamedev", - "elo": 1215, - "win_rate": 54.6, - "rank": 41 + "elo": 1190, + "win_rate": 55.1, + "rank": 55 }, { "arena": "models", "category": "svg", - "elo": 1167, - "win_rate": 52.1, - "rank": 40 + "elo": 1139, + "win_rate": 50.4, + "rank": 46 }, { "arena": "models", "category": "uicomponent", - "elo": 1212, - "win_rate": 54, - "rank": 45 + "elo": 1176, + "win_rate": 52.3, + "rank": 62 }, { "arena": "models", "category": "website", - "elo": 1217, - "win_rate": 54.4, - "rank": 47 + "elo": 1185, + "win_rate": 54.2, + "rank": 62 } ], "artificial_analysis": { - "intelligence_index": 28.7, + "intelligence_index": 29.3, "coding_index": 45.8, - "agentic_index": 17.7 + "agentic_index": 18.6 } }, "reasoning": { @@ -24662,7 +33861,7 @@ "name": "Z.ai: GLM 4.7", "created": 1766378014, "description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...", - "context_length": 202752, + "context_length": 204800, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -24698,6 +33897,7 @@ "temperature", "tool_choice", "tools", + "top_a", "top_k", "top_logprobs", "top_p" @@ -24705,7 +33905,10 @@ "default_parameters": { "temperature": 1, "top_p": 0.95, - "frequency_penalty": null + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null }, "supported_voices": null, "knowledge_cutoff": null, @@ -24718,92 +33921,92 @@ { "arena": "agents", "category": "androidnative", - "elo": 1124, - "win_rate": 56, - "rank": 18 + "elo": 1149, + "win_rate": 56.2, + "rank": 27 }, { "arena": "agents", "category": "fullstack", - "elo": 1116, + "elo": 1086, "win_rate": 44.9, - "rank": 20 + "rank": 30 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1130, - "win_rate": 39.1, - "rank": 18 + "elo": 1058, + "win_rate": 35.8, + "rank": 28 }, { "arena": "agents", "category": "mobileapps", - "elo": 1185, - "win_rate": 49.9, - "rank": 17 + "elo": 1160, + "win_rate": 49, + "rank": 26 }, { "arena": "models", "category": "3d", - "elo": 1268, - "win_rate": 54.3, - "rank": 26 + "elo": 1245, + "win_rate": 54.4, + "rank": 38 }, { "arena": "models", "category": "asciiart", - "elo": 1213, - "win_rate": 48.4, - "rank": 18 + "elo": 1198, + "win_rate": 48.1, + "rank": 22 }, { "arena": "models", "category": "codecategories", - "elo": 1265, - "win_rate": 54.8, - "rank": 28 + "elo": 1237, + "win_rate": 54.9, + "rank": 38 }, { "arena": "models", "category": "dataviz", - "elo": 1237, - "win_rate": 51.2, - "rank": 33 + "elo": 1219, + "win_rate": 51.3, + "rank": 45 }, { "arena": "models", "category": "gamedev", - "elo": 1254, - "win_rate": 55.1, - "rank": 31 + "elo": 1226, + "win_rate": 55.2, + "rank": 42 }, { "arena": "models", "category": "svg", - "elo": 1200, - "win_rate": 54.3, - "rank": 31 + "elo": 1178, + "win_rate": 54, + "rank": 36 }, { "arena": "models", "category": "uicomponent", - "elo": 1251, - "win_rate": 51, - "rank": 31 + "elo": 1230, + "win_rate": 51.4, + "rank": 42 }, { "arena": "models", "category": "website", - "elo": 1268, + "elo": 1238, "win_rate": 55.3, - "rank": 26 + "rank": 38 } ], "artificial_analysis": { - "intelligence_index": 33.7, + "intelligence_index": 34.5, "coding_index": 45.3, - "agentic_index": 25.4 + "agentic_index": 26.2 } }, "reasoning": { @@ -24874,51 +34077,51 @@ { "arena": "models", "category": "3d", - "elo": 1198, - "win_rate": 51.2, - "rank": 46 + "elo": 1175, + "win_rate": 51.4, + "rank": 60 }, { "arena": "models", "category": "codecategories", - "elo": 1227, + "elo": 1197, "win_rate": 53.1, - "rank": 37 + "rank": 50 }, { "arena": "models", "category": "dataviz", - "elo": 1167, - "win_rate": 45.3, - "rank": 62 + "elo": 1146, + "win_rate": 45.6, + "rank": 76 }, { "arena": "models", "category": "gamedev", - "elo": 1200, - "win_rate": 49.7, - "rank": 49 + "elo": 1172, + "win_rate": 50, + "rank": 63 }, { "arena": "models", "category": "svg", - "elo": 1096, - "win_rate": 44.2, - "rank": 54 + "elo": 1064, + "win_rate": 42.4, + "rank": 63 }, { "arena": "models", "category": "uicomponent", - "elo": 1261, - "win_rate": 57.6, - "rank": 27 + "elo": 1235, + "win_rate": 57.8, + "rank": 40 }, { "arena": "models", "category": "website", - "elo": 1237, + "elo": 1205, "win_rate": 54, - "rank": 36 + "rank": 49 } ] }, @@ -24934,7 +34137,7 @@ "name": "Z.ai: GLM 5", "created": 1770829182, "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...", - "context_length": 202752, + "context_length": 204800, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -24948,8 +34151,8 @@ "input_cache_read": "0.00000012" }, "top_provider": { - "context_length": 202752, - "max_completion_tokens": null, + "context_length": 198000, + "max_completion_tokens": 128000, "is_moderated": false }, "per_request_limits": null, @@ -24990,86 +34193,93 @@ { "arena": "agents", "category": "androidnative", - "elo": 1244, - "win_rate": 61.6, - "rank": 8 + "elo": 1179, + "win_rate": 55.2, + "rank": 22 }, { "arena": "agents", "category": "fullstack", - "elo": 1188, - "win_rate": 52.6, - "rank": 13 + "elo": 1158, + "win_rate": 51.6, + "rank": 23 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1231, - "win_rate": 54.8, - "rank": 4 + "elo": 1144, + "win_rate": 46.7, + "rank": 16 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1161, + "win_rate": 45, + "rank": 17 }, { "arena": "agents", "category": "mobileapps", - "elo": 1217, - "win_rate": 53, - "rank": 12 + "elo": 1190, + "win_rate": 51.8, + "rank": 23 }, { "arena": "models", "category": "3d", - "elo": 1307, - "win_rate": 56.4, - "rank": 17 + "elo": 1283, + "win_rate": 56.3, + "rank": 26 }, { "arena": "models", "category": "asciiart", - "elo": 1195, + "elo": 1181, "win_rate": 48, - "rank": 26 + "rank": 30 }, { "arena": "models", "category": "codecategories", - "elo": 1295, - "win_rate": 55.6, - "rank": 17 + "elo": 1267, + "win_rate": 55.5, + "rank": 26 }, { "arena": "models", "category": "dataviz", - "elo": 1270, + "elo": 1252, "win_rate": 53, - "rank": 21 + "rank": 31 }, { "arena": "models", "category": "gamedev", - "elo": 1299, + "elo": 1272, "win_rate": 57.4, - "rank": 16 + "rank": 27 }, { "arena": "models", "category": "svg", - "elo": 1225, + "elo": 1202, "win_rate": 54.4, - "rank": 21 + "rank": 27 }, { "arena": "models", "category": "uicomponent", - "elo": 1286, - "win_rate": 53.9, - "rank": 22 + "elo": 1262, + "win_rate": 54, + "rank": 34 }, { "arena": "models", "category": "website", - "elo": 1290, - "win_rate": 55.1, - "rank": 19 + "elo": 1260, + "win_rate": 55, + "rank": 30 } ] }, @@ -25085,7 +34295,7 @@ "name": "Z.ai: GLM 5 Turbo", "created": 1773583573, "description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...", - "context_length": 262144, + "context_length": 202752, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -25099,23 +34309,16 @@ "input_cache_read": "0.00000024" }, "top_provider": { - "context_length": 262144, + "context_length": 202752, "max_completion_tokens": 131072, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ - "frequency_penalty", "include_reasoning", - "logit_bias", "max_tokens", - "min_p", - "presence_penalty", "reasoning", - "repetition_penalty", "response_format", - "seed", - "stop", "temperature", "tool_choice", "tools", @@ -25132,7 +34335,7 @@ }, "supported_voices": null, "knowledge_cutoff": null, - "expiration_date": null, + "expiration_date": "2098-12-31", "links": { "details": "/api/v1/models/z-ai/glm-5-turbo-20260315/endpoints" }, @@ -25141,58 +34344,58 @@ { "arena": "models", "category": "3d", - "elo": 1329, - "win_rate": 59.6, - "rank": 7 + "elo": 1304, + "win_rate": 57.8, + "rank": 18 }, { "arena": "models", "category": "asciiart", - "elo": 1197, - "win_rate": 50.4, - "rank": 24 + "elo": 1185, + "win_rate": 49.4, + "rank": 26 }, { "arena": "models", "category": "codecategories", - "elo": 1319, - "win_rate": 57.4, - "rank": 9 + "elo": 1286, + "win_rate": 55.6, + "rank": 19 }, { "arena": "models", "category": "dataviz", - "elo": 1308, - "win_rate": 58.3, - "rank": 7 + "elo": 1289, + "win_rate": 57.3, + "rank": 16 }, { "arena": "models", "category": "gamedev", - "elo": 1325, - "win_rate": 59.6, - "rank": 10 + "elo": 1289, + "win_rate": 54.7, + "rank": 24 }, { "arena": "models", "category": "svg", - "elo": 1272, - "win_rate": 59.7, - "rank": 9 + "elo": 1240, + "win_rate": 56.6, + "rank": 14 }, { "arena": "models", "category": "uicomponent", - "elo": 1320, - "win_rate": 58.1, - "rank": 9 + "elo": 1293, + "win_rate": 56.8, + "rank": 21 }, { "arena": "models", "category": "website", - "elo": 1314, - "win_rate": 56.4, - "rank": 10 + "elo": 1281, + "win_rate": 55, + "rank": 22 } ] }, @@ -25208,7 +34411,7 @@ "name": "Z.ai: GLM 5.1", "created": 1775578025, "description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...", - "context_length": 202752, + "context_length": 204800, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -25269,63 +34472,63 @@ "category": "3d", "elo": 1336, "win_rate": 62.6, - "rank": 5 + "rank": 8 }, { "arena": "models", "category": "asciiart", - "elo": 1180, - "win_rate": 47.9, - "rank": 32 + "elo": 1168, + "win_rate": 46.4, + "rank": 37 }, { "arena": "models", "category": "codecategories", - "elo": 1329, - "win_rate": 59.4, - "rank": 5 + "elo": 1291, + "win_rate": 55.3, + "rank": 18 }, { "arena": "models", "category": "dataviz", "elo": 1366, "win_rate": 67, - "rank": 2 + "rank": 3 }, { "arena": "models", "category": "gamedev", - "elo": 1338, - "win_rate": 61.9, - "rank": 7 + "elo": 1300, + "win_rate": 56.5, + "rank": 18 }, { "arena": "models", "category": "svg", - "elo": 1280, - "win_rate": 61.3, - "rank": 7 + "elo": 1253, + "win_rate": 58.9, + "rank": 12 }, { "arena": "models", "category": "uicomponent", - "elo": 1335, - "win_rate": 61.5, - "rank": 5 + "elo": 1301, + "win_rate": 54.2, + "rank": 17 }, { "arena": "models", "category": "website", - "elo": 1318, - "win_rate": 57.1, - "rank": 7 + "elo": 1290, + "win_rate": 55.1, + "rank": 14 }, { "arena": "agents", "category": "agenticgamedev", - "elo": 1206, - "win_rate": 54, - "rank": 4 + "elo": 1173, + "win_rate": 50.7, + "rank": 14 }, { "arena": "agents", @@ -25358,79 +34561,270 @@ { "arena": "agents", "category": "androidnative", - "elo": 1248, - "win_rate": 54.1, - "rank": 7 + "elo": 1208, + "win_rate": 52.3, + "rank": 17 }, { "arena": "agents", "category": "fullstack", - "elo": 1230, - "win_rate": 56.4, - "rank": 8 + "elo": 1203, + "win_rate": 55.3, + "rank": 19 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1240, - "win_rate": 55.9, - "rank": 3 + "elo": 1104, + "win_rate": 39.5, + "rank": 25 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1191, + "win_rate": 48.5, + "rank": 11 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1211, + "win_rate": 54, + "rank": 14 + }, + { + "arena": "agents", + "category": "pptxslides", + "elo": 1241, + "win_rate": 53.5, + "rank": 4 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1258, + "win_rate": 54.2, + "rank": 5 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1217, + "win_rate": 52.8, + "rank": 19 + } + ], + "artificial_analysis": { + "intelligence_index": 41, + "coding_index": 55.8, + "agentic_index": 30.6 + } + }, + "reasoning": { + "mandatory": false, + "default_enabled": true + } + }, + { + "id": "z-ai/glm-5.2", + "canonical_slug": "z-ai/glm-5.2-20260616", + "hugging_face_id": "zai-org/GLM-5.2", + "name": "Z.ai: GLM 5.2", + "created": 1781631930, + "description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...", + "context_length": 1048576, + "architecture": { + "modality": "text->text", + "input_modalities": ["text"], + "output_modalities": ["text"], + "tokenizer": "Other", + "instruct_type": null + }, + "pricing": { + "prompt": "0.000000308", + "completion": "0.000000968", + "input_cache_read": "0.0000000572" + }, + "top_provider": { + "context_length": 1024000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "default_parameters": { + "temperature": 1, + "top_p": 0.95, + "top_k": null, + "frequency_penalty": null, + "presence_penalty": null, + "repetition_penalty": null + }, + "supported_voices": null, + "knowledge_cutoff": null, + "expiration_date": null, + "links": { + "details": "/api/v1/models/z-ai/glm-5.2-20260616/endpoints" + }, + "benchmarks": { + "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1184, + "win_rate": 48.8, + "rank": 10 + }, + { + "arena": "agents", + "category": "androidnative", + "elo": 1209, + "win_rate": 54.9, + "rank": 16 + }, + { + "arena": "agents", + "category": "fullstack", + "elo": 1271, + "win_rate": 61.8, + "rank": 9 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 40.1, + "rank": 18 + }, + { + "arena": "agents", + "category": "htmlslides", + "elo": 1194, + "win_rate": 49.4, + "rank": 10 + }, + { + "arena": "agents", + "category": "mobileapps", + "elo": 1211, + "win_rate": 52.2, + "rank": 15 + }, + { + "arena": "agents", + "category": "python-pptxslides", + "elo": 1196, + "win_rate": 47.5, + "rank": 11 + }, + { + "arena": "agents", + "category": "webapps", + "elo": 1261, + "win_rate": 56.8, + "rank": 10 + }, + { + "arena": "models", + "category": "3d", + "elo": 1361, + "win_rate": 59, + "rank": 5 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1254, + "win_rate": 52, + "rank": 11 + }, + { + "arena": "models", + "category": "codecategories", + "elo": 1329, + "win_rate": 58.3, + "rank": 5 }, { - "arena": "agents", - "category": "htmlslides", - "elo": 1206, - "win_rate": 52.6, + "arena": "models", + "category": "dataviz", + "elo": 1331, + "win_rate": 56.2, "rank": 7 }, { - "arena": "agents", - "category": "mobileapps", - "elo": 1231, - "win_rate": 55, - "rank": 8 + "arena": "models", + "category": "gamedev", + "elo": 1333, + "win_rate": 56.6, + "rank": 9 }, { - "arena": "agents", - "category": "pptxslides", - "elo": 1241, - "win_rate": 53.5, - "rank": 4 + "arena": "models", + "category": "svg", + "elo": 1253, + "win_rate": 55.6, + "rank": 13 }, { - "arena": "agents", - "category": "python-pptxslides", - "elo": 1258, - "win_rate": 54.2, - "rank": 3 + "arena": "models", + "category": "uicomponent", + "elo": 1334, + "win_rate": 56.9, + "rank": 7 }, { - "arena": "agents", - "category": "webapps", - "elo": 1246, - "win_rate": 55.1, - "rank": 10 + "arena": "models", + "category": "website", + "elo": 1320, + "win_rate": 58.8, + "rank": 5 } ], "artificial_analysis": { - "intelligence_index": 40.2, - "coding_index": 55.8, - "agentic_index": 29.9 + "intelligence_index": 52.6, + "coding_index": 68.8, + "agentic_index": 45.7 } }, "reasoning": { "mandatory": false, - "default_enabled": true + "default_enabled": true, + "supported_efforts": ["xhigh", "high"], + "default_effort": "high" } }, { - "id": "z-ai/glm-5.2", + "id": "z-ai/glm-5.2:batch", "canonical_slug": "z-ai/glm-5.2-20260616", "hugging_face_id": "zai-org/GLM-5.2", - "name": "Z.ai: GLM 5.2", + "name": "Z.ai: GLM 5.2 (batch)", "created": 1781631930, "description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...", - "context_length": 1048576, + "context_length": 512000, "architecture": { "modality": "text->text", "input_modalities": ["text"], @@ -25439,13 +34833,13 @@ "instruct_type": null }, "pricing": { - "prompt": "0.00000093", - "completion": "0.000003", - "input_cache_read": "0.00000018" + "prompt": "0.0000007", + "completion": "0.0000022", + "input_cache_read": "0.00000013" }, "top_provider": { - "context_length": 1048576, - "max_completion_tokens": 32768, + "context_length": 512000, + "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, @@ -25453,23 +34847,19 @@ "frequency_penalty", "include_reasoning", "logit_bias", - "logprobs", "max_tokens", "min_p", - "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", - "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", - "top_logprobs", "top_p" ], "default_parameters": { @@ -25488,95 +34878,123 @@ }, "benchmarks": { "design_arena": [ + { + "arena": "agents", + "category": "agenticgamedev", + "elo": 1184, + "win_rate": 48.8, + "rank": 10 + }, { "arena": "agents", "category": "androidnative", - "elo": 1253, - "win_rate": 57.1, - "rank": 6 + "elo": 1209, + "win_rate": 54.9, + "rank": 16 }, { "arena": "agents", "category": "fullstack", - "elo": 1295, - "win_rate": 63.6, - "rank": 3 + "elo": 1271, + "win_rate": 61.8, + "rank": 9 + }, + { + "arena": "agents", + "category": "godotgamedev", + "elo": 1142, + "win_rate": 40.1, + "rank": 18 }, { "arena": "agents", "category": "htmlslides", - "elo": 1202, - "win_rate": 52.3, - "rank": 8 + "elo": 1194, + "win_rate": 49.4, + "rank": 10 }, { "arena": "agents", "category": "mobileapps", - "elo": 1238, - "win_rate": 53.8, - "rank": 6 + "elo": 1211, + "win_rate": 52.2, + "rank": 15 }, { "arena": "agents", "category": "python-pptxslides", - "elo": 1218, - "win_rate": 50.4, - "rank": 5 + "elo": 1196, + "win_rate": 47.5, + "rank": 11 }, { "arena": "agents", "category": "webapps", - "elo": 1284, - "win_rate": 57.5, - "rank": 3 + "elo": 1261, + "win_rate": 56.8, + "rank": 10 }, { "arena": "models", "category": "3d", - "elo": 1377, - "win_rate": 62.7, - "rank": 1 + "elo": 1361, + "win_rate": 59, + "rank": 5 + }, + { + "arena": "models", + "category": "asciiart", + "elo": 1254, + "win_rate": 52, + "rank": 11 }, { "arena": "models", "category": "codecategories", - "elo": 1360, - "win_rate": 61.8, - "rank": 1 + "elo": 1329, + "win_rate": 58.3, + "rank": 5 }, { "arena": "models", "category": "dataviz", - "elo": 1327, - "win_rate": 59.9, - "rank": 3 + "elo": 1331, + "win_rate": 56.2, + "rank": 7 }, { "arena": "models", "category": "gamedev", - "elo": 1357, - "win_rate": 61.3, - "rank": 2 + "elo": 1333, + "win_rate": 56.6, + "rank": 9 + }, + { + "arena": "models", + "category": "svg", + "elo": 1253, + "win_rate": 55.6, + "rank": 13 }, { "arena": "models", "category": "uicomponent", - "elo": 1339, - "win_rate": 59.6, - "rank": 4 + "elo": 1334, + "win_rate": 56.9, + "rank": 7 }, { "arena": "models", "category": "website", - "elo": 1356, - "win_rate": 61.5, - "rank": 1 + "elo": 1320, + "win_rate": 58.8, + "rank": 5 } ], "artificial_analysis": { - "intelligence_index": 51.1, + "intelligence_index": 52.6, "coding_index": 68.8, - "agentic_index": 43.1 + "agentic_index": 45.7 } }, "reasoning": { @@ -25642,9 +35060,9 @@ { "arena": "agents", "category": "agenticgamedev", - "elo": 1124, - "win_rate": 41.1, - "rank": 11 + "elo": 1102, + "win_rate": 41.4, + "rank": 18 }, { "arena": "agents", @@ -25684,30 +35102,30 @@ { "arena": "agents", "category": "fullstack", - "elo": 1212, - "win_rate": 54.4, - "rank": 12 + "elo": 1185, + "win_rate": 52, + "rank": 22 }, { "arena": "agents", "category": "godotgamedev", - "elo": 1221, - "win_rate": 53.6, - "rank": 5 + "elo": 997, + "win_rate": 26.8, + "rank": 30 }, { "arena": "agents", "category": "htmlslides", - "elo": 1139, - "win_rate": 42.1, - "rank": 10 + "elo": 1145, + "win_rate": 43.5, + "rank": 18 }, { "arena": "agents", "category": "mobileapps", - "elo": 1216, - "win_rate": 52.2, - "rank": 13 + "elo": 1187, + "win_rate": 50.5, + "rank": 25 }, { "arena": "agents", @@ -25719,72 +35137,72 @@ { "arena": "agents", "category": "python-pptxslides", - "elo": 1168, - "win_rate": 51.5, - "rank": 8 + "elo": 1165, + "win_rate": 51.9, + "rank": 14 }, { "arena": "agents", "category": "webapps", - "elo": 1192, - "win_rate": 46.3, - "rank": 16 + "elo": 1165, + "win_rate": 44.6, + "rank": 26 }, { "arena": "models", "category": "3d", - "elo": 1288, - "win_rate": 55.1, - "rank": 22 + "elo": 1264, + "win_rate": 54, + "rank": 32 }, { "arena": "models", "category": "asciiart", - "elo": 1143, - "win_rate": 42.7, - "rank": 41 + "elo": 1141, + "win_rate": 43.2, + "rank": 46 }, { "arena": "models", "category": "codecategories", - "elo": 1278, - "win_rate": 52.5, - "rank": 24 + "elo": 1248, + "win_rate": 51.4, + "rank": 36 }, { "arena": "models", "category": "dataviz", - "elo": 1244, - "win_rate": 49.4, - "rank": 32 + "elo": 1221, + "win_rate": 48, + "rank": 44 }, { "arena": "models", "category": "gamedev", - "elo": 1287, - "win_rate": 54.6, - "rank": 21 + "elo": 1255, + "win_rate": 52.9, + "rank": 32 }, { "arena": "models", "category": "svg", - "elo": 1204, - "win_rate": 51, - "rank": 30 + "elo": 1184, + "win_rate": 50.8, + "rank": 33 }, { "arena": "models", "category": "uicomponent", - "elo": 1269, - "win_rate": 51.9, - "rank": 26 + "elo": 1243, + "win_rate": 50.2, + "rank": 38 }, { "arena": "models", "category": "website", - "elo": 1271, - "win_rate": 51, - "rank": 24 + "elo": 1242, + "win_rate": 50.3, + "rank": 36 } ] }, diff --git a/scripts/vercel-gateway.models.json b/scripts/vercel-gateway.models.json index 4a0198ed57..8096914de9 100644 --- a/scripts/vercel-gateway.models.json +++ b/scripts/vercel-gateway.models.json @@ -1502,6 +1502,39 @@ ] } }, + { + "id": "alibaba/qwen3.8-2.4t-a95b", + "object": "model", + "created": 1755815280, + "released": 1785715200, + "owned_by": "alibaba", + "name": "Qwen3.8 2.4T A95B", + "description": "Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only.", + "context_window": 262144, + "max_tokens": 131072, + "type": "language", + "tags": ["reasoning", "tool-use", "implicit-caching"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "pricing": { + "input": "0.000002", + "output": "0.000006", + "input_cache_read": "0.00000025" + } + }, { "id": "alibaba/qwen3.8-max", "object": "model", @@ -4758,6 +4791,39 @@ } } }, + { + "id": "deepseek/deepseek-v4-pro-0813", + "object": "model", + "created": 1755815280, + "released": 1786492800, + "owned_by": "deepseek", + "name": "DeepSeek V4 Pro 0813", + "description": "This is the 8/13 updated weights version of DeepSeek V4 Pro.", + "context_window": 1000000, + "max_tokens": 384000, + "type": "language", + "tags": ["reasoning", "tool-use", "implicit-caching"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "pricing": { + "input": "0.00000132", + "output": "0.00000396", + "input_cache_read": "0.000000132" + } + }, { "id": "fish-audio/s1", "object": "model", @@ -5754,12 +5820,13 @@ "vision", "tool-use", "web-search", - "implicit-caching" + "implicit-caching", + "video-input" ], "regions": ["eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -5828,12 +5895,13 @@ "implicit-caching", "file-input", "vision", - "web-search" + "web-search", + "video-input" ], "regions": ["eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -5895,12 +5963,13 @@ "tool-use", "vision", "implicit-caching", - "web-search" + "web-search", + "video-input" ], "regions": ["eu", "us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -5933,14 +6002,68 @@ }, "regional": { "eu": { - "input": "0.0000015", - "output": "0.0000075", - "input_cache_read": "0.00000015" + "input": "0.00000165", + "output": "0.00000825", + "input_cache_read": "0.000000165" }, "us": { - "input": "0.0000015", - "output": "0.0000075", - "input_cache_read": "0.00000015" + "input": "0.00000165", + "output": "0.00000825", + "input_cache_read": "0.000000165" + } + } + } + }, + { + "id": "google/gemini-3.7-flash", + "object": "model", + "created": 1755815280, + "released": 1786579200, + "owned_by": "google", + "name": "Gemini 3.7 Flash", + "description": "", + "context_window": 1000000, + "max_tokens": 65536, + "type": "language", + "tags": [ + "reasoning", + "file-input", + "vision", + "tool-use", + "web-search", + "implicit-caching", + "video-input" + ], + "regions": ["eu", "us"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image", "pdf", "video"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "pricing": { + "input": "0.00000075", + "output": "0.00000375", + "input_cache_read": "0.000000075", + "regional": { + "eu": { + "input": "0.000000825", + "output": "0.000004125", + "input_cache_read": "0.0000000825" + }, + "us": { + "input": "0.000000825", + "output": "0.000004125", + "input_cache_read": "0.0000000825" } } } @@ -6071,7 +6194,7 @@ "owned_by": "google", "name": "Gemma 4 31B IT", "description": "Gemma 4 31B is engineered to tackle the most demanding enterprise workloads and complex reasoning tasks. With an expansive 256K-token context window, the 31B model can effortlessly ingest entire codebases, and massive sets of images in a single prompt.", - "context_window": 256000, + "context_window": 262144, "max_tokens": 131072, "type": "language", "tags": ["file-input", "reasoning", "tool-use", "vision"], @@ -6636,35 +6759,6 @@ "input_cache_read": "0.000000012" } }, - { - "id": "inclusionai/ling-3.0-tiny-free", - "object": "model", - "created": 1755815280, - "released": 1785974400, - "owned_by": "inclusionai", - "name": "Ling 3.0 Tiny (Free)", - "description": "Ling-3.0-tiny is an efficient 7.9B-parameter MoE model with only 1.3B active parameters per token. It is designed for responsive AI agents, reliable instruction following, and natural multi-turn conversations. The model features a 256K context window, native function calling, prompt caching, and switchable Thinking and Instant modes. It supports long-context, tool-using workflows with lower active-compute requirements.", - "context_window": 256000, - "max_tokens": 32000, - "type": "language", - "tags": ["reasoning", "implicit-caching", "tool-use", "free"], - "supported_specifications": ["v2", "v3", "v4"], - "modalities": { - "input": ["text"], - "output": ["text"] - }, - "supported_parameters": [ - "max_tokens", - "temperature", - "stop", - "tools", - "tool_choice", - "reasoning", - "include_reasoning" - ], - "temperature": true, - "pricing": {} - }, { "id": "interfaze/interfaze-beta", "object": "model", @@ -7352,7 +7446,7 @@ "context_window": 128000, "max_tokens": 8192, "type": "language", - "tags": ["tool-use", "implicit-caching"], + "tags": ["tool-use"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { "input": ["text"], @@ -8586,10 +8680,16 @@ "context_window": 262114, "max_tokens": 262114, "type": "language", - "tags": ["reasoning", "vision", "tool-use", "implicit-caching"], + "tags": [ + "reasoning", + "vision", + "tool-use", + "implicit-caching", + "video-input" + ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text", "image", "video"], "output": ["text"] }, "supported_parameters": [ @@ -8626,11 +8726,17 @@ "context_window": 262000, "max_tokens": 262000, "type": "language", - "tags": ["implicit-caching", "reasoning", "tool-use", "vision"], + "tags": [ + "implicit-caching", + "reasoning", + "tool-use", + "vision", + "video-input" + ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image"], + "input": ["text", "image", "video"], "output": ["text"] }, "supported_parameters": [ @@ -8678,12 +8784,13 @@ "tool-use", "implicit-caching", "file-input", - "vision" + "vision", + "video-input" ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -8731,11 +8838,12 @@ "tool-use", "implicit-caching", "file-input", - "vision" + "vision", + "video-input" ], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -8771,12 +8879,13 @@ "tool-use", "implicit-caching", "file-input", - "vision" + "vision", + "video-input" ], "regions": ["us"], "supported_specifications": ["v2", "v3", "v4"], "modalities": { - "input": ["text", "image", "pdf"], + "input": ["text", "image", "pdf", "video"], "output": ["text"] }, "supported_parameters": [ @@ -13172,7 +13281,20 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + } } }, { @@ -13323,7 +13445,20 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + } } }, { @@ -13463,7 +13598,20 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + } } }, { @@ -13617,7 +13765,20 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.0000025", + "output": "0.000005", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000005", + "output": "0.00001", + "input_cache_read": "0.0000008" + } + } + } } }, { @@ -13697,7 +13858,100 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.000004", + "output": "0.000012", + "input_cache_read": "0.0000006", + "long_context": { + "threshold": 200001, + "input": "0.000008", + "output": "0.000024", + "input_cache_read": "0.0000012" + } + } + } + } + }, + { + "id": "xai/grok-4.6", + "object": "model", + "created": 1755815280, + "released": 1786492800, + "owned_by": "xai", + "name": "Grok 4.6", + "description": "Grok 4.6 builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. It stays with complex tasks across many steps, whether researching a topic, analyzing information, working across a codebase, or turning an idea into a polished application or work artifact.", + "context_window": 500000, + "max_tokens": 500000, + "type": "language", + "tags": ["reasoning", "tool-use", "implicit-caching", "vision"], + "supported_specifications": ["v2", "v3", "v4"], + "modalities": { + "input": ["text", "image"], + "output": ["text"] + }, + "supported_parameters": [ + "max_tokens", + "temperature", + "stop", + "tools", + "tool_choice", + "reasoning", + "include_reasoning" + ], + "temperature": true, + "pricing": { + "input": "0.000002", + "input_tiers": [ + { + "cost": "0.000002", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000004", + "min": 200001 + } + ], + "output": "0.000006", + "output_tiers": [ + { + "cost": "0.000006", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000012", + "min": 200001 + } + ], + "input_cache_read": "0.0000005", + "input_cache_read_tiers": [ + { + "cost": "0.0000005", + "min": 0, + "max": 200001 + }, + { + "cost": "0.000001", + "min": 200001 + } + ], + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.000004", + "output": "0.000012", + "input_cache_read": "0.000001", + "long_context": { + "threshold": 200001, + "input": "0.000008", + "output": "0.000024", + "input_cache_read": "0.000002" + } + } + } } }, { @@ -13770,7 +14024,20 @@ "min": 200001 } ], - "web_search": "5" + "web_search": "5", + "service_tiers": { + "priority": { + "input": "0.000002", + "output": "0.000004", + "input_cache_read": "0.0000004", + "long_context": { + "threshold": 200001, + "input": "0.000004", + "output": "0.000008", + "input_cache_read": "0.0000008" + } + } + } } }, {