Free Model

Free LLM API

OpenAI-compatible, running on your own provider keys and allowances. Point any OpenAI SDK at this base URL and use a Free Model key.

Base URL

https://staging.freemodel.io/api/v1
  1. 1

    Connect a provider

    API calls use the providers you've connected, with your own allowance.

  2. 2

    Create an API key

  3. 3

    Send a request

    curl https://staging.freemodel.io/api/v1/chat/completions \
  -H "Authorization: Bearer $FREEMODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

    Use "auto" or an exact model ID from Models

Endpoints

POST/api/v1/chat/completions
Chat completions, streaming supported
GET/api/v1/models
Models available to your key
  • Text input and output only for now.
  • Gateway limits: 6 upstream attempts/minute and 100/UTC day per user and provider key, with 2 concurrent requests per user. Limits come from your provider accounts. OpenRouter :free models are zero-priced; Groq and Cerebras use your account's allowance and a paid account can be billed. Auto moves to another connected model when one is rate-limited.
  • 429 responses include Retry-After when the wait is known.