AWS bedrock documentation change
Summary
Updated terminology from 'cross-region' to 'cross-Region' for consistency and corrected a link reference. Added clarification about Global inference profile regions.
Security assessment
Changes are capitalization corrections and terminology consistency updates. No security vulnerabilities, weaknesses, or incidents are addressed. The mention of SCPs and IAM policies remains unchanged from previous content.
Diff
diff --git a/bedrock/latest/userguide/inference-profiles-support.md b/bedrock/latest/userguide/inference-profiles-support.md index eeb9150cd..e9f6e225c 100644 --- a//bedrock/latest/userguide/inference-profiles-support.md +++ b//bedrock/latest/userguide/inference-profiles-support.md @@ -30 +30 @@ You can carry out [cross-Region inference](./cross-region-inference.html) with c -Cross-region (system-defined) inference profiles are named after the model that they support and defined by the Regions that they support. To understand how a cross-region inference profile handles your requests, review the following definitions: +Cross-Region (system-defined) inference profiles are named after the model that they support and defined by the Regions that they support. To understand how a cross-Region inference profile handles your requests, review the following definitions: @@ -45 +45 @@ The destination Regions in a cross-Region inference profile can include _opt-in -Service Control Policies (SCPs) and AWS Identity and Access Management (IAM) policies work together to control where cross-Region inference is allowed. Using SCPs, you can control which Regions Amazon Bedrock can use for inference, and using IAM policies, you can define which users or roles have permission to run inference. If any destination Region in a cross-Region inference profile is blocked in your SCPs, the request will fail even if other Regions remain allowed. To ensure efficient operation with cross-region inference, you can update your SCPs and IAM policies to allow all required Amazon Bedrock inference actions (for example, `bedrock:InvokeModel*` or `bedrock:CreateModelInvocationJob`) in all destination Regions included in your chosen inference profile. To learn more, see [Enabling Amazon Bedrock cross-Region inference in multi-account environments.](https://aws.amazon.com/blogs/machine-learning/enable-amazon-bedrock-cross-region-inference-in-multi-account-environments/) +Service Control Policies (SCPs) and AWS Identity and Access Management (IAM) policies work together to control where cross-Region inference is allowed. Using SCPs, you can control which Regions Amazon Bedrock can use for inference, and using IAM policies, you can define which users or roles have permission to run inference. If any destination Region in a cross-Region inference profile is blocked in your SCPs, the request will fail even if other Regions remain allowed. To ensure efficient operation with cross-Region inference, you can update your SCPs and IAM policies to allow all required Amazon Bedrock inference actions (for example, `bedrock:InvokeModel*` or `bedrock:CreateModelInvocationJob`) in all destination Regions included in your chosen inference profile. To learn more, see [Enabling Amazon Bedrock cross-Region inference in multi-account environments.](https://aws.amazon.com/blogs/machine-learning/enable-amazon-bedrock-cross-region-inference-in-multi-account-environments/) @@ -53 +53 @@ To check the source and destination Regions for an inference profile, you can do - * Expand the corresponding section in the [list of supported cross-region inference profiles](./inference-profiles-support.html). + * Expand the corresponding section in the [list of supported cross-Region inference profiles](./inference-profiles-support.html). @@ -64 +64 @@ Global cross-Region inference profile for a specific model can change over time -The Global cross-region inference profile is currently only supported on Anthropic Claude Sonnet 4 model for the following source Regions: US West (Oregon), US East (N. Virginia), US East (Ohio), Europe (Ireland), and Asia Pacific (Tokyo). The destination Regions for Global inference profile include all commercial AWS Regions. +The Global cross-Region inference profile is currently only supported on Anthropic Claude Sonnet 4 model for the following source Regions: US West (Oregon), US East (N. Virginia), US East (Ohio), Europe (Ireland), and Asia Pacific (Tokyo). The destination Regions for Global inference profile include all commercial AWS Regions.