Posted On: May 19, 2021

Amazon SageMaker Autopilot automatically builds, trains, and tunes the best machine learning models based on your data, while allowing you to maintain full control and visibility. Starting today, you have a convenient option to auto deploy the best trained model after running an experiment to create models. With auto deploy option enabled, SageMaker Autopilot will automatically create an endpoint and deploy your best model, enabling you to run real time inference on your endpoint. You can modify or delete the endpoint at anytime to meet your changing inference needs.

The automatic deployment option is available in all AWS regions where SageMaker Autopilot is currently supported. The deployment endpoint created for inference will incur inference charges on your AWS account. For more details on auto deploy, see documentation. For pricing, see Amazon SageMaker pricing.