AI infrastructure Product
SageMaker AI adds generally available cross-Region inference routing
AWS announced general availability of SageMaker AI cross-Region inference routing on November 18, allowing customers to route requests among their deployed model endpoints. [1]
- Release status
- Generally available in commercial AWS Regions supporting SageMaker AI real-time inference. [1]
What it does
The routing resource can coordinate endpoints across AWS Regions and accounts, prefer local capacity and redirect requests when eligible destinations encounter defined service problems. [1]
Why it matters
Teams serving AI models can manage failover and capacity sharing without rebuilding the routing logic independently for each application. [1]
Key dates
- SageMaker AI adds generally available cross-Region inference routing [1]
Limits and trade-offs
The router does not create capacity or copy model artifacts. Customers must configure compatible destinations, access and residency controls. This feature is distinct from Amazon Bedrock cross-Region inference. [1]
Sources and verification
Catalog evidence checked How we verify records
- Primary source AWS introduces SageMaker AI cross-Region inference routing
Related profiles
AI infrastructure
Azure Cobalt 200 virtual machines
Microsoft Azure
The Arm-based CPU platform supports databases, applications and tool execution around AI models.
AI infrastructure
Sarvam Token Factory
Sarvam AI
It exposes hosted model inference through supported developer interfaces.
AI infrastructure
NVIDIA Rubin HPC
NVIDIA
It is designed to accelerate high-performance computing workloads in compatible systems.