Update AWS Bedrock models list with working models

[gsinghyk]

Summary

Updates the AWS Bedrock models list to include the latest working models and removed models that have compatibility issues with the AWS Bedrock Converse API.

Changes Made

Updated Model List (12 total)

AI21 Labs (2):

• ai21.jamba-1-5-large-v1:0
• ai21.jamba-1-5-mini-v1:0

Anthropic Claude (1):

• anthropic.claude-3-haiku-20240307-v1:0

Meta Llama (2):

• meta.llama3-8b-instruct-v1:0
• meta.llama3-70b-instruct-v1:0

Mistral (4):

• mistral.mistral-large-2402-v1:0
• mistral.mistral-small-2402-v1:0
• mistral.mixtral-8x7b-instruct-v0:1
• mistral.mistral-7b-instruct-v0:2

Removed Models

Removed models that have compatibility issues with the AWS Bedrock Converse API:

These model requires an inference profile ARN instead of direct model ID invocation

Anthropic Claude (7):

• anthropic.claude-3-5-haiku-20241022-v1:0
• anthropic.claude-haiku-4-5-20251001-v1:0
• anthropic.claude-sonnet-4-20250514-v1:0
• anthropic.claude-sonnet-4-5-20250929-v1:0
• anthropic.claude-sonnet-4-6
• anthropic.claude-opus-4-5-20251101-v1:0
• anthropic.claude-opus-4-6-v1

Amazon Nova (2):

• amazon.nova-premier-v1:0
• amazon.nova-2-lite-v1:0

Meta Llama (6):

• meta.llama3-1-8b-instruct-v1:0
• meta.llama3-1-70b-instruct-v1:0
• meta.llama3-2-1b-instruct-v1:0
• meta.llama3-2-3b-instruct-v1:0
• meta.llama4-scout-17b-instruct-v1:0
• meta.llama4-maverick-17b-instruct-v1:0

Mistral (1):

• mistral.pixtral-large-2502-v1:0

Writer (2):

• writer.palmyra-x4-v1:0
• writer.palmyra-x5-v1:0

Models not supporting stopSequences parameter:

Google Gemma 3 (3):

• google.gemma-3-4b-it
• google.gemma-3-12b-it
• google.gemma-3-27b-it

Meta Llama (2):

• meta.llama3-2-90b-instruct-v1:0
• meta.llama3-2-11b-instruct-v1:0
• meta.llama3-3-70b-instruct-v1:0

MiniMax (2):

• minimax.minimax-m2
• minimax.minimax-m2.1

Mistral (8):

• mistral.ministral-3-3b-instruct
• mistral.ministral-3-8b-instruct
• mistral.ministral-3-14b-instruct
• mistral.mistral-large-3-675b-instruct
• mistral.magistral-small-2509
• mistral.devstral-2-123b
• mistral.voxtral-small-24b-2507
• mistral.voxtral-mini-3b-2507

Moonshot (2):

• moonshot.kimi-k2-thinking
• moonshotai.kimi-k2.5

NVIDIA Nemotron (3):

• nvidia.nemotron-nano-3-30b
• nvidia.nemotron-nano-12b-v2
• nvidia.nemotron-nano-9b-v2

OpenAI GPT OSS (4):

• openai.gpt-oss-20b-1:0
• openai.gpt-oss-120b-1:0
• openai.gpt-oss-safeguard-20b
• openai.gpt-oss-safeguard-120b

Qwen (5):

• qwen.qwen3-32b-v1:0
• qwen.qwen3-coder-30b-a3b-v1:0
• qwen.qwen3-next-80b-a3b
• qwen.qwen3-vl-235b-a22b
• qwen.qwen3-coder-next

Z.AI (2):

• zai.glm-4.7
• zai.glm-4.7-flash

These models return errors when invoked through the standard Converse API due to parameter incompatibilities.

Legacy/deprecated models (16 models)

Older model versions that have been superseded:

• anthropic.claude-v2
• anthropic.claude-v2:1
• anthropic.claude-instant-v1
• anthropic.claude-3-sonnet-20240229-v1:0
• anthropic.claude-3-opus-20240229-v1:0
• meta.llama2-13b-chat-v1
• meta.llama2-70b-chat-v1
• cohere.command-text-v14
• cohere.command-light-text-v14
• cohere.command-r-v1:0
• cohere.command-r-plus-v1:0
• ai21.j2-mid-v1
• ai21.j2-ultra-v1
• amazon.titan-text-lite-v1
• amazon.titan-text-express-v1
• mistral.mistral-7b-instruct-v0:1

Files Modified

• packages/components/models.json

[gemini-code-assist]

Code Review

This pull request updates the AWS Bedrock model list by adding AI21 Jamba and Amazon Nova models. A review comment highlights that removing Claude 3.5 Sonnet, Claude 3.7 Sonnet, and Claude 3 Opus is a regression and suggests re-adding them with correct pricing.

[gemini-code-assist]

Several essential models (Claude 3.5 Sonnet, Claude 3.7 Sonnet, and Claude 3 Opus) have been removed from the list. These models are fully compatible with the AWS Bedrock Converse API and are among the most widely used models on the platform. Removing them would be a significant regression in functionality. When re-adding these models, ensure their pricing is accurately reflected based on official documentation.

                },
                {
                    "label": "anthropic.claude-3-7-sonnet-20250219-v1:0",
                    "name": "anthropic.claude-3-7-sonnet-20250219-v1:0",
                    "description": "Claude 3.7 Sonnet - Most intelligent model, multimodal",
                    "input_cost": 0.000003,
                    "output_cost": 0.000015
                },
                {
                    "label": "anthropic.claude-3-5-sonnet-20241022-v2:0",
                    "name": "anthropic.claude-3-5-sonnet-20241022-v2:0",
                    "description": "Claude 3.5 Sonnet (v2) - High intelligence and speed, multimodal",
                    "input_cost": 0.000003,
                    "output_cost": 0.000015
                },
                {
                    "label": "anthropic.claude-3-opus-20240229-v1:0",
                    "name": "anthropic.claude-3-opus-20240229-v1:0",
                    "description": "Claude 3 Opus - Powerful model for complex tasks, multimodal",
                    "input_cost": 0.000015,
                    "output_cost": 0.000075
                }

References

1. When adding new models, ensure their pricing (input_cost and output_cost) is accurately reflected based on official documentation, rather than using placeholder or copied values.