POST
/v1/chat/completions
Chat completion requests with optional streaming, tools, temperature, and output limits.
Change the SDK base URL and supply a project key. Chat completions and streaming use the standard OpenAI request shape.
https://router-us.knowledgeops.io/v1curl https://router-us.knowledgeops.io/v1/chat/completions \ -H "Authorization: Bearer sk-..." \ -H "Content-Type: application/json" \ -d '{ "model": "chat-default", "messages": [{"role":"user","content":"Hello"}], "max_tokens": 200 }'
Chat completion requests with optional streaming, tools, temperature, and output limits.
List the model names available to the supplied project key.
Check gateway availability before sending production traffic.