v1

latestOpenAPI 3.0.0Apache 2.0 License2026-07-1442519.0 KB

Sends a streaming inference request to the model during a job execution. Returns the response as a stream of payload chunks. Each turn is captured for later use.

post/sample-with-response-stream#X-Amzn-SageMaker-Job-Arn&X-Amzn-SageMaker-Trajectory-Id

Headers

X-Amzn-SageMaker-Job-Arnstring required

The job ARN that identifies which model session to route the inference request to.

X-Amzn-SageMaker-Trajectory-Idstring required

The trajectory ID for grouping turns into a single rollout. Each turn is captured for later use.

Request body

Bodystring password required

Sensitive binary payload containing customer inference data.

Response

Success

Bodystring password required

The streaming response body, delivered as a series of PayloadPart events.