Search docs...

Start typing to search documentation

Platform Guide

Quickstart

From zero to a working API call in about five minutes.

How UnoRouter works

UnoRouter puts 200+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen and 50+ other providers behind one OpenAI-compatible endpoint. Integrate once, then swap models by changing a single string. Many models are completely free, no credit card required.

You can also skip the API entirely: the built-in chat runs free models without signup, and your conversations stay in your browser.

Base URL

Point any OpenAI-compatible client at these two values:

VariableValue
BASE_URLhttps://api.unorouter.com/v1
API_KEYThe key you create on the Tokens page

Tools that speak a native wire protocol use the bare domain instead: Claude Code sets ANTHROPIC_BASE_URL and Gemini CLI sets GOOGLE_GEMINI_BASE_URL without the /v1 suffix. Each integration guide shows the exact value.

Create an API key

Sign up, then open the Tokens page and create a key. Give it a name; you can also set an expiry date, a spending limit, allowed models and an IP allowlist. The key is shown once, store it safely.

Without a key you can still use the built-in chat as a guest on free models. API requests always need a key.

Make your first request

Replace YOUR_API_KEY with the key you just created (if you are logged in, it is already filled in below):

bash
curl https://api.unorouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-oss-120b:free",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Sign in to auto-fill your API key

Models with the :free suffix cost nothing. Pick any other model from the catalog to use your balance.

Use the official SDKs

Any OpenAI SDK works unchanged, just set the base URL and your key:

Python

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.unorouter.com/v1",
    api_key="YOUR_API_KEY",
)

completion = client.chat.completions.create(
    model="gpt-oss-120b:free",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Sign in to auto-fill your API key

Node.js

typescript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.unorouter.com/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await client.chat.completions.create({
  model: "gpt-oss-120b:free",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);

Sign in to auto-fill your API key

Next steps

The Integrations tab has copy-paste setup for 30+ apps: SillyTavern, JanitorAI, Claude Code, Cline and more. The Chat tab documents the built-in roleplay chat.

Browse all models and live prices on the Models page, community-tested free-model reliability on Rankings, and provider health on Status.

Quickstart: your first request in 5 minutes