Home icon

Amazon SageMaker AI now supports cross-Region inference routing

News



This article announces cross-Region inference routing for Amazon SageMaker AI, enabling inference applications to remain available during regional capacity constraints.

  • Automatically routes requests to healthy endpoints in other AWS Regions and accounts when local capacity is exceeded
  • Developers create an inference router and register existing real-time endpoints, asynchronous endpoints, and inference components
  • Router prioritizes local endpoints, shifts traffic to healthy destinations as errors increase, and gradually returns traffic after recovery
  • Endpoint owners control access via policies and can set optional cross-Region traffic caps to reserve local capacity
  • Available for real-time inference in 32 commercial AWS Regions and asynchronous inference in 25 Regions
  • No additional charge; customers pay standard SageMaker AI and CloudWatch pricing

Cross-Region inference routing eliminates the need for teams to build and maintain custom routing, health checks, and retry logic across Regions.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Nov 18
2026
How Salesforce is advancing global-scale model serving with cross-Region inference routing in Amazon SageMaker AI
Nov 17
2026
Amazon SageMaker AI now supports KV cache-aware routing for real-time inference endpoints
Nov 17
2026
Amazon SageMaker AI real-time endpoints now support KV cache aware routing
Oct 30
2026
Amazon SageMaker AI inference now supports GPU partitioning for real-time endpoints

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.