FIM Gate Documentation

FIM Gate is an LLM API aggregation and forwarding service: with a single API key and a single endpoint, you can call models from OpenAI, Claude, Gemini, and other providers. For most existing projects, all you need to do is change the base URL to https://api.gate.fim.ai — the rest of your code stays the same.

Core capabilities

• OpenAI API compatibility: standard endpoints such as /v1/chat/completions work out of the box, so any SDK, framework, or client that supports a custom base URL can connect directly.
• Native multi-provider protocols: beyond the OpenAI format, FIM Gate also forwards native Claude Messages API and Gemini GenerateContent API requests, so you can keep using each provider's official SDK.
• Unified key management: create and disable API keys and review usage details in the Console — all models share a single key system.
• Pure forwarding architecture: the service only forwards requests and meters usage; it does not store conversation content.
• Streaming output: all endpoints support SSE streaming responses, ideal for building real-time chat experiences.

Get started in three steps

1. Sign up and create an API key in the Console.
2. Change your request URL to https://api.gate.fim.ai/v1 (OpenAI-compatible format).
3. Include Authorization: Bearer $FIM_API_KEY in the request headers and make calls as usual.

curl https://api.gate.fim.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $FIM_API_KEY" \
  -d '{
    "model": "gpt-4.1",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence"}]
  }'

Documentation guide