Geo-Aware Routing for Anthropic

LLM requests for Anthropic on AWS Bedrock are routed to the nearest AWS data center where a model endpoint is available.

Required Editions

Available in: Enterprise, Performance, and Unlimited Editions with an Einstein for Sales, Einstein for Platform, Einstein for Service, Einstein 1 Service, or Einstein GPT Service add-on. To purchase add-ons, contact your Salesforce account executive.

Inference Profiles

Some models are accessible in particular AWS Regions only as a cross-region inference profile. Cross-region inference requests are kept within the AWS regions that are part of the geography where the request originates. For example, a request made within the United States to Claude Haiku 4.5 is kept within the AWS Regions in the United States.

For more information, see Amazon Bedrock documentation:

Claude Haiku 4.5 Routing

This table shows geo-aware routing for Claude Haiku 4.5 requests. The columns are:

  • Salesforce Org Region: The region where a Salesforce org is hosted
  • AWS Inference Profile: The AWS cross-region inference profile used to service requests
Salesforce Org Region AWS Inference Profile
Australia au.anthropic.claude-haiku-4-5-20251001-v1:0
Brazil us.anthropic.claude-haiku-4-5-20251001-v1:0
Canada us.anthropic.claude-haiku-4-5-20251001-v1:0
France eu.anthropic.claude-haiku-4-5-20251001-v1:0
Germany eu.anthropic.claude-haiku-4-5-20251001-v1:0
India us.anthropic.claude-haiku-4-5-20251001-v1:0
Indonesia us.anthropic.claude-haiku-4-5-20251001-v1:0
Italy eu.anthropic.claude-haiku-4-5-20251001-v1:0
Japan jp.anthropic.claude-haiku-4-5-20251001-v1:0
South Korea us.anthropic.claude-haiku-4-5-20251001-v1:0
Singapore us.anthropic.claude-haiku-4-5-20251001-v1:0
Sweden eu.anthropic.claude-haiku-4-5-20251001-v1:0
Switzerland eu.anthropic.claude-haiku-4-5-20251001-v1:0
United Kingdom eu.anthropic.claude-haiku-4-5-20251001-v1:0
United States us.anthropic.claude-haiku-4-5-20251001-v1:0
Note
Note The geo-aware routing rules are different for other Anthropic models. To find information about the inference profiles used by other models, see Large Language Model Support.