Predict Sync And Async

Client POSTs to https://model-<id>.api.baseten.co/production/predict with the model's documented input JSON. The deployment is warm. Response is the model's raw output JSON (not wrapped in {data:...}).

Parse the response as the model's output schema directly — do not assume a Baseten-injected envelope. Status 200 means inference succeeded; non-2xx means the request failed at the platform layer (queueing, autoscaler, replica crash) and the response body carries an error object with code + message.

Client POSTs to /production/async_predict with body containing the model input and webhook_endpoint. Response is immediate with request_id and status=QUEUED.

Persist request_id with the operator's job-tracking key BEFORE 200 is returned to the caller, so a crash between POST and webhook delivery does not orphan the request. Use either webhook delivery or GET /async_request/{request_id} polling as the result channel — pick one and document it.

Baseten POSTs the async-predict result to the operator's webhook_endpoint with an HMAC-SHA256 signature header. The operator's handler stores results without checking the signature.

Verify the HMAC signature against the shared webhook secret BEFORE parsing the body or persisting results. Reject mismatched signatures with 401 and log for security review. The webhook endpoint must be idempotent because Baseten retries on non-2xx.