Skip to content

InvokeInferenceRouterAsyncOutput

Source code in docs_src/capo_sagemaker_inference_router_runtime/types/invoke_inference_router_async_output.py
class InvokeInferenceRouterAsyncOutput(TypedDict, closed=True):
    inference_id: NotRequired["str"]
    """<p>The identifier for the inference request. This is the <code>InferenceId</code> that you provided, or the one that SageMaker AI generated.</p>"""
    output_location: NotRequired["str"]
    """<p>The Amazon S3 URI where the inference response is written. The location doesn't change if the router moves the request to another destination.</p>"""
    failure_location: NotRequired["str"]
    """<p>The Amazon S3 URI where the failure details are written if the inference fails.</p>"""

failure_location instance-attribute

failure_location: NotRequired[str]

The Amazon S3 URI where the failure details are written if the inference fails.

inference_id instance-attribute

inference_id: NotRequired[str]

The identifier for the inference request. This is the InferenceId that you provided, or the one that SageMaker AI generated.

output_location instance-attribute

output_location: NotRequired[str]

The Amazon S3 URI where the inference response is written. The location doesn't change if the router moves the request to another destination.