Inference

Run inference against the models in the catalog and review the requests you have made. These endpoints cover OpenAI-compatible chat completions and the audit records of your third-party inference requests.

Endpoints

---

POST

Create chat completion

Sends a chat prompt to a model and returns a completion. Supports both streaming and non-streaming response modes.

GET

List audit logs

Returns an audit record for each third-party inference request you made within a time window, newest first.