InferenceGetting started
Overview
What the Yenisei API is, which methods it offers, and where to start.
The Yenisei API gives your program access to the models over HTTP. The request and response format is the same as in the OpenAI API, so any OpenAI SDK will work: you change the address and the key and leave the rest of your code as it is. All requests go to a single address:
Text
https://api.yenisei.ru/v1
Methods
| Method | Purpose |
|---|---|
POST /v1/chat/completions | Model reply to a conversation |
POST /v1/embeddings | Text vectors for semantic search |
GET /v1/models | List of models available on your plan |
The model catalog and prices are collected on the Models page, and the plans are on the Pricing page.
Where to start
- Create an API key in the console.
- Send your first request.
- If you already have code written for OpenAI, switch it over by following Migrating from OpenAI.
How the API differs from the chat
Yenisei Chat, Yenisei Agent and Yenisei CLI are ready-made products for a person. The API is for your program: you decide what to send to the model and what to do with the reply. The account is the same, and credits are spent from the shared pool of your plan.