Routix puts a single, OpenAI-compatible API in front of the models you rely on. Same client code you already have, one key, one endpoint to point at.
curl https://routix.tech/v1/chat/completions \ -H "Authorization: Bearer $ROUTIX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "glm-5.3-flash", "messages": [{"role": "user", "content": "Hello"}] }'
No new SDK, no new concepts. If your code already talks to the OpenAI API, it already talks to Routix.
Change the base URL and the key. The request body and the response shape stay exactly the same.
Server-sent events pass straight through, token by token. Nothing waits in a buffer.
Pin a name and we handle what sits behind it. Your integrations don't break when the routing changes.