Cannot specify "S3FailurePath" in SageMaker create_endpoint_config

[kblissett]

Describe the bug

The create_endpoint_config method of the SageMaker client does not allow specifying the "S3FailurePath" in AsyncInferenceConfig as specified in the documentation https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker/client/create_endpoint_config.html#create-endpoint-config.

Expected Behavior

I can specify the "S3FailurePath" in the AsyncInferenceConfig.

Current Behavior

---------------------------------------------------------------------------
ParamValidationError                      Traceback (most recent call last)

...

ParamValidationError: Parameter validation failed:
Unknown parameter in AsyncInferenceConfig.OutputConfig: "S3FailurePath", must be one of: KmsKeyId, S3OutputPath, NotificationConfig

Reproduction Steps

import boto3

sm = boto3.client("sagemaker")
response = sm.create_endpoint_config(
    EndpointConfigName="my-endpoint-config",
    ProductionVariants=[
        {
            "VariantName": "my-variant",
            "ModelName": "my-model",
            "InitialInstanceCount": 1,
            "InstanceType": "ml.m5.large"
        }
    ],
    AsyncInferenceConfig={
        "OutputConfig": {
            "S3OutputPath": "s3://my-bucket/out",
            "S3FailurePath": "s3://my-bucket/failures"
        }
    }
)

Possible Solution

No response

Additional Information/Context

No response

SDK version used

1.34.64

Environment details (OS name and version, etc.)

macOS Sanoma 14.4

[kblissett]

This seems to have been an issue with my local jupyter notebook kernel configuration.

[github-actions]

This issue is now closed. Comments on closed issues are hard for our team to see.
If you need more assistance, please open a new issue that references this one.