Amazon SageMaker AI now supports cross-Region inference routing

Published
November 18, 2026
https://aws.amazon.com/about-aws/whats-new/2026/11/sagemaker-cross-region-routing/

Amazon SageMaker AI Cross-Region Inference Routing

Amazon SageMaker AI now offers cross-Region inference routing to maintain application availability during regional capacity shortages by distributing requests across multiple regions and accounts.

What to do

  • Create an inference router in SageMaker AI.
  • Register existing real-time endpoints, asynchronous endpoints, and inference components.
  • Direct applications to the router for improved availability.
  • Availability: 32 commercial AWS Regions for real-time inference and 25 Regions for asynchronous inference.
  • Pricing: No additional charge for cross-Region inference routing. Pay standard SageMaker AI pricing for endpoints and standard Amazon CloudWatch rates for metrics.

Source: AWS release notes




If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.

Follow our blog

Get the latest insights and advice on AWS services from our experts.

By clicking Sign Up you're confirming that you agree with our Terms and Conditions.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.