Amazon SageMaker AI Async Inference now supports inline request payloads | Amazon Web Services

Today, we’re announcing inline payload support for Amazon SageMaker AI Async Inference. Customers can now send inference payloads directly in the request body of the InvokeEndpointAsync API, removing the need to upload input data to Amazon Simple Storage Service (Amazon S3) before each invocation.

Raccontata daaws.amazon.com