Adoption and implementation of generic AI inference has increased with organizations creating more operational workloads that use AI capabilities in large-scale production. To help customers achieve scale for their generic AI applications, Amazon Bedrock offers cross-region inference (CRIS) profiles. CRIS is a powerful feature that organizations can use to seamlessly distribute estimate processing across multiple AWS regions. This capability helps you achieve higher throughput when you’re building at scale and helps keep your Generator AI applications responsive and reliable even under heavy load.
We are excited to introduce global cross-region penetration to Amazon Bedrock and bring the Anthropic Cloud model to India. Amazon Bedrock now offers Anthropic’s Cloud Opus 4.6, Cloud Sonnet 4.6, and Cloud Haiku 4.5 through Amazon Bedrock Global Cross-region Ingress (CRIS) for customers operating in India. These Frontier models provide a massive 1 million token context window and advanced agentive capabilities, allowing your applications to process huge datasets and complex workflows with unprecedented speed and intelligence. With this launch, customers using AP-South-1 (Mumbai) and AP-South-2 (Hyderabad) can access Anthropic’s latest cloud models on Amazon Bedrock, while benefiting from global inference capacity and highly available inference managed by Amazon Bedrock. With Global CRIS, customers can seamlessly scale predictive workloads, improve resiliency and reduce operational complexity. In this post, you will learn how to use Amazon Bedrock’s global cross-region inference to model the cloud in India. We’ll guide you through the capabilities of each cloud model version and how to get started with a code example to help you quickly start building generic AI applications.
Core functionality of global cross-region estimation
Global cross-region estimation helps organizations manage unplanned traffic bursts by using compute resources in estimation capacity Commercial AWS Regions (regions other than the AWS GovCloud (US) Region and China Region) Globally. This section explains how the global cross-region estimation feature works and the technical mechanisms that power its functionality.
Understanding Estimate Profiles
Global cross-region estimation is introduced through Estimate Profile. Estimate profiles work on two key concepts:
- source area – the region from which the API request is made
- destination area – An area where Amazon can send requests for bedrock estimates
To use the anthropic model, Amazon Bedrock provides out-of-the-box global inference profiles. For example:
- Composition 4.6:
- Sonnet 4.6:
- Composition 4.5:
<0/> <0/><0/>
‘
’
—
’
