Mistral GLM Bridge
A small proxy that translates OpenAI-compatible chat requests into Mistral's native /v1/conversations endpoint, letting the 9router gateway reach a GLM-5.2 model through Mistral without hitting the rate limits on Mistral's OpenAI-compatible endpoint.
Mistral exposes both an OpenAI-compatible /v1/chat/completions endpoint, which is often rate-limited for third-party models, and a native /v1/conversations endpoint that is not. This bridge receives OpenAI-format requests from the 9router gateway, translates them to /v1/conversations, and translates the response back to OpenAI format, so a GLM-5.2 model can be used through Mistral without hitting the rate limit.
It runs as a local FastAPI server on a configurable port (default 8090) and host, started, stopped, checked and watched, with auto-restart on crash, through a control script. It is plugged into 9router as a regular provider and requires the user's own Mistral API key, set through an environment variable rather than committed to the repository.
Built with Python and FastAPI. MIT licensed; documentation is provided in English, Indonesian, Chinese, Japanese and Korean.