Calling the API

Last updated: October 27, 2026

The API is OpenAI-compatible. Most OpenAI SDKs and tools work by changing the base URL and the API key.

  • Base URL. Your provider's API address for catalog models, or the base URL of your dedicated deployment.

  • Authentication. Authorization: Bearer <your API key>.

  • List models. GET /v1/models returns the models your key can use.

  • Chat completions. POST /v1/chat/completions with model and messages.

  • Streaming. Set "stream": true to receive tokens as they are generated.

  • Structured output and tool calling. Supported on models that support them; check the model's capabilities first.

curl https://<api-address>/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "<model-name>", "messages": [{"role": "user", "content": "Hello"}]}'

Every response carries a request ID. Keep it: it is the fastest way to get help.