diff --git a/api-reference/api-spec.mdx b/api-reference/api-spec.mdx index 7bb65301..18428808 100644 --- a/api-reference/api-spec.mdx +++ b/api-reference/api-spec.mdx @@ -266,7 +266,7 @@ While Venice maintains high compatibility with the OpenAI API specification, the 1. **venice_parameters**: Additional configurations like `enable_web_search`, `character_slug`, and `strip_thinking_response` for extended functionality 2. **System Prompts**: Venice appends your system prompts to defaults that optimize for uncensored responses (disable with `include_venice_system_prompt: false`) -3. **Model Ecosystem**: Venice offers its own [model lineup](/overview/models) including uncensored and reasoning models - use Venice model IDs rather than OpenAI mappings +3. **Model Ecosystem**: Venice offers its own [model lineup](/models/overview) including uncensored and reasoning models - use Venice model IDs rather than OpenAI mappings 4. **Response Headers**: Unique headers for balance tracking (`x-venice-balance-usd`, `x-venice-balance-diem`), model deprecation warnings, and content safety flags 5. **Content Policies**: More permissive policies with dedicated uncensored models and optional content filtering diff --git a/api-reference/endpoint/models/list.mdx b/api-reference/endpoint/models/list.mdx index 19a971f2..00c90347 100644 --- a/api-reference/endpoint/models/list.mdx +++ b/api-reference/endpoint/models/list.mdx @@ -5,6 +5,53 @@ openapi: 'GET /models' "og:description": "Documentation covering Venice's model list API." --- +## Example Response + +A trimmed example showing two text models (the full response includes every field in the schema below): + +```json +{ + "object": "list", + "type": "text", + "data": [ + { + "id": "venice-uncensored", + "object": "model", + "created": 1699000000, + "context_length": 131072, + "model_spec": { + "availableContextTokens": 131072, + "privacy": "private", + "capabilities": { + "optimizedForCode": false, + "supportsFunctionCalling": true, + "supportsReasoning": false, + "supportsVision": false, + "supportsWebSearch": true + } + } + }, + { + "id": "qwen3-235b", + "object": "model", + "created": 1709000000, + "context_length": 256000, + "model_spec": { + "availableContextTokens": 256000, + "privacy": "private", + "capabilities": { + "optimizedForCode": true, + "supportsFunctionCalling": true, + "supportsReasoning": true, + "supportsVision": false, + "supportsWebSearch": true + } + } + } + ] +} +``` + ## Quality-Tier Pricing For image models that accept the optional `quality` parameter (currently `gpt-image-2` and `gpt-image-2-edit`), the response exposes a per-quality price matrix under `model_spec.pricing.quality`. Each top-level key is a resolution tier (`1K`, `2K`, `4K`) and each nested key is a quality level (`low`, `medium`, `high`) carrying its own `usd` and `diem` price: diff --git a/ar/api-reference/api-spec.mdx b/ar/api-reference/api-spec.mdx index 3c3f6633..8cf0fad4 100644 --- a/ar/api-reference/api-spec.mdx +++ b/ar/api-reference/api-spec.mdx @@ -266,7 +266,7 @@ if (deprecationWarning) { 1. **venice_parameters**: تكوينات إضافية مثل `enable_web_search` و `character_slug` و `strip_thinking_response` لوظائف ممتدة 2. **System Prompts**: تضيف Venice system prompts الخاصة بك إلى الافتراضات التي تُحسِّن للاستجابات بدون قيود (عطّل بـ `include_venice_system_prompt: false`) -3. **منظومة النماذج**: تقدم Venice [قائمة نماذجها](/overview/models) الخاصة بما في ذلك النماذج بدون قيود ونماذج الاستدلال - استخدم معرّفات نماذج Venice بدلًا من تعيينات OpenAI +3. **منظومة النماذج**: تقدم Venice [قائمة نماذجها](/models/overview) الخاصة بما في ذلك النماذج بدون قيود ونماذج الاستدلال - استخدم معرّفات نماذج Venice بدلًا من تعيينات OpenAI 4. **رؤوس الاستجابة**: رؤوس فريدة لتتبع الرصيد (`x-venice-balance-usd` و `x-venice-balance-diem`)، وتحذيرات إيقاف النماذج، وأعلام أمان المحتوى 5. **سياسات المحتوى**: سياسات أكثر تسامحًا مع نماذج بدون قيود مخصصة وتصفية محتوى اختيارية diff --git a/ar/guides/features/reasoning-models.mdx b/ar/guides/features/reasoning-models.mdx index 7f0648bb..d9ce82c4 100644 --- a/ar/guides/features/reasoning-models.mdx +++ b/ar/guides/features/reasoning-models.mdx @@ -9,7 +9,7 @@ description: "استخدام نماذج التفكير المنطقي مع ال
-اطلع على القائمة الكاملة للنماذج والأسعار وحدود السياق في [صفحة النماذج](/overview/models). لا تدعم جميع نماذج التفكير المنطقي معامل [`reasoning_effort`](#reasoning-effort). انظر [دعم النموذج](#model-support) للتفاصيل. +اطلع على القائمة الكاملة للنماذج والأسعار وحدود السياق في [صفحة النماذج](/models/overview). لا تدعم جميع نماذج التفكير المنطقي معامل [`reasoning_effort`](#reasoning-effort). انظر [دعم النموذج](#model-support) للتفاصيل. ## قراءة المخرجات diff --git a/ar/guides/features/tee-e2ee-models.mdx b/ar/guides/features/tee-e2ee-models.mdx index 794225e3..24d3dc25 100644 --- a/ar/guides/features/tee-e2ee-models.mdx +++ b/ar/guides/features/tee-e2ee-models.mdx @@ -22,7 +22,7 @@ description: "ذكاء اصطناعي معزّز للخصوصية مع بيئاkimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+
Developer guides
++ Start with an OpenAI-compatible API call, then add Venice-specific privacy, tools, media generation, and wallet-funded agent workflows. +
+Start fast
+The shortest path from account setup to a working integration.
+Build paths
+Follow the path that matches your app, then jump deeper when you need a specific capability.
+Developer journey
+Keep learning
+kimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+
+ Use any OpenAI-compatible client, point it at Venice, then turn on Venice-native tools like server-side web search with venice_parameters.
+
export VENICE_API_KEY="your-api-key"
+ npm install openai
+ {`import OpenAI from "openai";
-const client = new OpenAI({
+const venice = new OpenAI({
apiKey: process.env.VENICE_API_KEY,
baseURL: "https://api.venice.ai/api/v1",
});
-const res = await client.chat.completions.create({
+const response = await venice.chat.completions.create({
model: "zai-org-glm-5-1",
- messages: [{ role: "user", content: "Build without permission." }],
+ messages: [
+ {
+ role: "system",
+ content: "You are a private research agent. Cite sources and be concise.",
+ },
+ {
+ role: "user",
+ content: "Find the latest private AI agent patterns and summarize the tradeoffs.",
+ },
+ ],
+ // @ts-expect-error - Venice-specific parameter
+ venice_parameters: {
+ enable_web_search: "auto",
+ enable_web_citations: true,
+ },
});
-```
-
-```python Python
-import os
-from openai import OpenAI
-client = OpenAI(
- api_key=os.environ["VENICE_API_KEY"],
- base_url="https://api.venice.ai/api/v1",
-)
-
-res = client.chat.completions.create(
- model="zai-org-glm-5-1",
- messages=[{"role": "user", "content": "Build without permission."}],
-)
-```
-
+console.log(response.choices[0].message.content);`}
+ Explore agent workflows →
+Endpoints
@@ -145,7 +155,7 @@ res = client.chat.completions.create(kimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+
kimi-k2-6
-
+
claude-opus-4-7
-
+