Uncensored AI API: OpenAI-compatible endpoints, models and limits
The uncensored AI API reference in one page: base URL, auth, 17 text models with prices, image generation, streaming, limits and per-key budgets. Works with the OpenAI SDKs.
Short answer
Base URL https://tryunrestrictedai.com/v1, Bearer API key, OpenAI-compatible /chat/completions (with SSE streaming), /models and /images/generations. Text from $1 per million input tokens; images from $0.01. Plans from $19/month include the same amount of usage; a one-time $0.50 API trial is available (checked 9 Nov 2026).
First request
curl https://tryunrestrictedai.com/v1/chat/completions \
-H "Authorization: Bearer $UNCENSORED_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"venice-uncensored-1-2","messages":[{"role":"user","content":"Hello"}],"max_tokens":256}'Endpoints
| Endpoint | Purpose |
|---|---|
GET /v1/models | Enabled model IDs and limits |
POST /v1/chat/completions | Chat, streaming with stream: true |
POST /v1/images/generations | Text-to-image, OpenAI images shape |
GET /api/catalog | Public JSON catalog with prices |
Limits
Most chat models take 32,768 tokens of context with up to 4,096 output tokens; the agent and coder routes take 262,144. Each key can have a lifetime budget. Full details: limits, errors, OpenAPI.
FAQ
Where do I get an API key?
Create one in the console. The base URL is https://tryunrestrictedai.com/v1 and model IDs are listed in the catalog.
Do I need to be 18?
Yes. Our terms require users to be at least 18.