Getting started

Quick start

Make your first request in under a minute.

Base URL

All model endpoints are served from:

text

https://rutoken.ai

The API is compatible with the official OpenAI, Anthropic Claude and Google Gemini SDKs — point the SDK at this base URL and use your RuToken key.

Authentication

Create a key in the console under API Keys, then send it with every request:

Format	Header
OpenAI	`Authorization: Bearer sk-xxxx`
Claude	`x-api-key: sk-xxxx`
Gemini	`x-goog-api-key: sk-xxxx` or `?key=sk-xxxx`

Keep your key secret. Never ship it in front-end code or commit it to a public repository.

First request

cURL

curl https://rutoken.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://rutoken.ai/v1", api_key="sk-xxxx")
resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://rutoken.ai/v1", apiKey: "sk-xxxx" });
const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Choosing a model

Browse available models and their prices in the Model Square. Use the exact model ID shown there in the model field.

Streaming