Chat completions (OpenAI-compatible)
OpenAI Chat Completions-compatible endpoint. Point your OpenAI SDK's base_url at
https://api.routemux.com/v1; the request body is passed through unchanged.
With stream: true chunks arrive as SSE. RouteMux never buffers the whole response,
and bills actual usage once the upstream finishes.
Authorization
bearerAuth Authorization: Bearer <your RouteMux API key>.
Create keys at https://routemux.com/console/keys. New keys use the sk- prefix;
the legacy rmx_live_ prefix is still accepted.
The Anthropic SDK's x-api-key and the Google SDK's x-goog-api-key are accepted too.
Sending several key headers with different values returns 400 AMBIGUOUS_API_KEY.
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Request and response bodies match the upstream provider's official format verbatim —
RouteMux passes them through untouched. See the provider's own docs for field definitions;
the gateway itself only reads model and stream.
Response Body
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://example.com/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-5.5", "messages": [ { "role": "user", "content": "Explain prepaid billing in one line." } ] }'{ "model": "string", "stream": true}