Sign in

v1

latestOpenAPI 3.0.0Apache 2.0 License2026-07-143021,9861.6 MB

Returns a list of the subtasks for an Inference Recommender job.

The supported subtasks are benchmarks, which evaluate the performance of your model on different instance types.

post/#X-Amz-Target=SageMaker.ListInferenceRecommendationsJobSteps

Query parameters

MaxResultsstring

Pagination limit

NextTokenstring

Pagination token

Headers

X-Amz-Target'SageMaker.ListInferenceRecommendationsJobSteps' required

Request body

JobNamestring required

The name for the Inference Recommender job.

Status'PENDING' | 'IN_PROGRESS' | 'COMPLETED' | 'FAILED' | 'STOPPING' | 'STOPPED'

A filter to return benchmarks of a specified status. If this field is left empty, then all benchmarks are returned.

StepType'BENCHMARK'
<p>A filter to return details about the specified type of subtask.</p> <p> <code>BENCHMARK</code>: Evaluate the performance of your model on different instance types.</p>
MaxResultsinteger

The maximum number of results to return.

NextTokenstring

A token that you can specify to return more results from the list. Specify this field if you have a token that was returned from a previous request.

Response

Success

NextTokenstring

A token that you can specify in your next request to return more results from the list.