The AI platform that doesn’t spy on you

Build AI with no data retention, permissionless access, and compute you permanently own.

OpenAI Compatibility

Use your existing OpenAI code with just a base URL change.
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "venice-uncensored",
    "messages": [{"role": "user", "content": "Hello World!"}]
  }'

Build with Venice APIs

Access chat, image generation (generate/upscale/edit), audio (TTS), and characters. View all API endpoints → Copy a Model ID and use it as model in your requests.

Venice Large 1.1

Flagship model for deep reasoning and production agents.Model ID: qwen3-235b Base: Qwen 3 235B (Venice‑tuned) Context: 131k • Modalities: Text → TextUse cases
  • Agent planning and tool use
  • Complex code & system design
  • Long‑context reasoning
{"model":"qwen3-235b","messages":[{"role":"user","content":"Plan a zero‑downtime DB migration in 3 steps"}]}

Venice Uncensored

Unfiltered generationModel ID: venice-uncensoredBase model: Venice Uncensored 1.1Context: 32k • Best for: uncensored creative, red‑team testing
{"model":"venice-uncensored","messages":[{"role":"user","content":"Write an unfiltered analysis of content moderation policies"}]}

Venice Medium 3.1

Vision + toolsModel ID: mistral-31-24bBase model: Mistral 3.1 24BContext: 131k • Supports: Vision, Function calling, image analysis
{"model":"mistral-31-24b","messages":[{"role":"user","content":"Describe this image"}]}

Venice Small

Fast and cost‑efficientModel ID: qwen3-4bBase model: Qwen 3 4BContext: 40k • Best for: chatbots, classification, light reasoning
{"model":"qwen3-4b","messages":[{"role":"user","content":"Summarize:"}]}

Venice SD35

Image generationModel ID: venice-sd35Base model: SD3.5 LargeBest for: Text‑to‑image, photorealism, product shots, light upscaling
{"model":"venice-sd35","prompt":"a serene canal in venice at sunset"}
View all models →

Extend models with built‑in tools

Toggle on compatible models using venice_parameters or model suffixes

Web Search

Real‑time web results

Reasoning Mode

Advanced reasoning

Vision Processing

Image understanding

Function Calling

Tool use / APIs

Available Parameters

ParameterOptionsDescription
enable_web_searchoff, on, autoEnable real-time web search
enable_web_citationstrue, falseInclude citations in web search results
strip_thinking_responsetrue, falseHide reasoning steps from response
disable_thinkingtrue, falseDisable reasoning mode entirely
include_venice_system_prompttrue, falseInclude Venice system prompts
character_slugstringUse a specific AI character
Additional parameters available for advanced use cases like streaming search results and LangChain integration. View all parameters →

Pricing Options

Start building today

Get your API key and make your first request.
Venice’s API is rapidly evolving. Join our Discord to provide feedback and request new features. Your input shapes our development roadmap.

These docs are open source and can be contributed to on Github. For additional guidance, see our blog post: “How to use Venice API”