OpenAI-compatible

API documentation

One base URL, standard OpenAI request shapes, streaming with usage counts.

Base URL

https://inference.chessurge.org/v1

Authentication

Authorization: Bearer sk-...

List models

curl https://inference.chessurge.org/v1/models

Chat completion

curl https://inference.chessurge.org/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"chessurge/deepseek-v4.1-flash","messages":[{"role":"user","content":"hello"}],"stream":true}'

Streaming

Server-sent events, terminated by data: [DONE]. Usage is returned once in the final chunk.

Errors

Standard HTTP status codes with an OpenAI-shaped error object: 400 invalid request, 401 bad key, 402 budget exhausted, 404 unknown model, 429 rate limited, 5xx upstream.

OpenRouter providers

Provider metadata is public at /v1/models in schema 2.4, and at /v1/models?format=legacy for integrations built against the legacy format.