Developer docs
Tutujin API documentation
Tutujin API speaks the OpenAI API format: point base_url at the address below, use an sk- key from the console, and you can call 739 models. Claude's native Messages API and Gemini's native generateContent work as well.
OpenAI-compatible base URL
https://www.tutujin.com/v1For the native Claude and Gemini SDKs, use the site root https://www.tutujin.com as the base URL
739
Models
18
Groups
12
Endpoint families
Prices updated Nov 13, 2026, 5:48 PM
Your first request in three steps
Read the quickstart01
Create an API key
Sign up, add credit, create an API key in the console and pick a group for it.
02
Swap the base_url
Set your SDK's base_url to the address above and api_key to the new key.
03
Send a request
Use a model name from the model hub and send the request; every charge shows up under Usage in the console.
Get started
Start here: authentication, groups, billing and handling errors.
API reference
Headers, parameters, request and response examples for every endpoint.
Integration guides
Configure Tutujin API in the official SDKs and common frameworks and platforms.
API reference
| Endpoint | Method and path | Status | Models |
|---|---|---|---|
| Chat Completions | POST/v1/chat/completions | Verified | 681 |
| Responses | POST/v1/responses | Relayed as-is | 5 |
| Claude Messages | POST/v1/messages | Verified | 49 |
| Gemini generateContent | POST/v1beta/models/{model}:generateContent | Verified | 63 |
| Image generation | POST/v1/images/generations | Relayed as-is | 54 |
| Image editing | POST/v1/images/edits | Relayed as-is | 31 |
| Embeddings | POST/v1/embeddings | Verified | 18 |
| Rerank | POST/v1/rerank | Relayed as-is | 6 |
| Text to speech | POST/v1/audio/speech | Relayed as-is | 8 |
| Speech to text | POST/v1/audio/transcriptions | Relayed as-is | 1 |
| Midjourney | POST/mj/submit/imagine | Relayed as-is | 13 |
| Suno music | POST/suno/submit/music | Relayed as-is | 2 |
"Verified" means we have made real calls and checked billing on this site. "Relayed as-is" means requests are forwarded in their original format; parameters follow the model's official documentation. Model counts are the models in the current catalog that support the endpoint.