Inference Profile
A cross-region inference feature of Amazon Bedrock that binds a model ID to endpoints in multiple regions and automatically routes requests to improve throughput and reduce latency.
Timeline (last 90 days)
Inference Profile is a cross-region inference capability of Amazon Bedrock that allows the same model ID to be bound to endpoints in multiple regions, with Bedrock automatically routing requests based on real-time capacity and latency.
Inference Profiles are divided into two types, system-defined and application-defined; the former is maintained by AWS, and the latter is assembled by users themselves across regions.
When a model is discontinued in some regions, an Inference Profile pointing to that model may lose the underlying capacity in those regions, or even fail entirely.
Amazon Bedrock's inference profiles are an AWS-provided cross-region model invocation abstraction layer where users reference models via logical ARNs, and AWS automatically selects the actual physical endpoint based on regional load and availability.
All Facts (4)
Inference Profile is a cross-region inference capability of Amazon Bedrock that allows the same model ID to be bound to endpoints in multiple regions, with Bedrock automatically routing requests based on real-time capacity and latency.
50%UnverifiedInference Profiles are divided into two types, system-defined and application-defined; the former is maintained by AWS, and the latter is assembled by users themselves across regions.
50%UnverifiedWhen a model is discontinued in some regions, an Inference Profile pointing to that model may lose the underlying capacity in those regions, or even fail entirely.
50%UnverifiedAmazon Bedrock's inference profiles are an AWS-provided cross-region model invocation abstraction layer where users reference models via logical ARNs, and AWS automatically selects the actual physical endpoint based on regional load and availability.
50%