Skip to content
TutujinAPI

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 724 models. Claude's native Messages API and Gemini's native generateContent work as well.

OpenAI-compatible base URL

https://open.tutujin.com/v1

For the native Claude and Gemini SDKs, use the site root https://open.tutujin.com as the base URL

Models
724
Groups
18
Endpoint families
10

Prices updated Nov 12, 2026, 8:17 PM

Your first request in three steps

  1. 1Sign up, add credit, create an API key in the console and pick a group for it.
  2. 2Set your SDK's base_url to the address above and api_key to the new key.
  3. 3Use a model name from the model hub and send the request; every charge shows up under Usage in the console.
Read the quickstart

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

EndpointMethod and pathStatusModels
Chat CompletionsPOST/v1/chat/completionsVerified681
ResponsesPOST/v1/responsesRelayed as-is5
Claude MessagesPOST/v1/messagesVerified49
Gemini generateContentPOST/v1beta/models/{model}:generateContentVerified63
Image generationPOST/v1/images/generationsRelayed as-is54
Image editingPOST/v1/images/editsRelayed as-is31
EmbeddingsPOST/v1/embeddingsVerified18
RerankPOST/v1/rerankRelayed as-is6
Text to speechPOST/v1/audio/speechRelayed as-is8
Speech to textPOST/v1/audio/transcriptionsRelayed as-is1

"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.