AWS First Steps
LanguageEnglish
Region expansion

Amazon Bedrock expands API support and introduces Cross-Region Inferencing for OpenAI models in AWS GovCloud (US)

Amazon Bedrock now supports OpenAI GPT-5.6 models (Terra and Luna) on the bedrock-runtime endpoint and introduces Cross-Region Inference in AWS GovCloud (US), enabling customers to achieve higher throughput without managing capacity across multiple regions.

Amazon Bedrock extends API support in AWS GovCloud (US) for the OpenAI GPT-5.6 models (Terra and Luna), now supporting Responses, Converse, and Chat Completions APIs through the bedrock-runtime endpoint. It also supports cross-region inference within the AWS GovCloud (US) region, enabling customers to improve throughput without managing multi-region capacity automatically. Cross-region inference routes requests between both regions in AWS GovCloud (US), ensuring US data sovereignty while scaling to provide maximum throughput and Bedrock processing power during peak demand. This release also extends API support for OpenAI GPT models via the bedrock-runtime endpoint. These native OpenAI APIs operate with the same account-level controls as other Bedrock models, and usage is itemized in Bedrock model call logs (deliverable to Amazon S3 or Amazon CloudWatch Logs), Amazon CloudWatch metrics (invocations, tokens, latency, throttling, errors), AWS Cost Explorer, and AWS cost and usage reports, enabling per-model spend attribution. Cross-region inference for OpenAI models is available in all AWS regions where Amazon Bedrock offers OpenAI models. To get started, see the GPT-5.6 (Terra and Luna) model card in the Amazon Bedrock user guide.

Why it matters

This update affects users operating AI models in AWS GovCloud (US). Cross-Region Inference improves processing capacity and redundancy.

Read the original AWS announcement

Related articles and terms

Amazon BedrockA fully managed service that provides access to multiple large language models via API, with built-in customization using your own data and configurable guardrailsGenerative AI Platform - Building an Enterprise AI Foundation with Amazon BedrockLearn how to build generative AI applications using Amazon Bedrock. This guide covers foundation model selection, RAG pattern implementation, safety guardrails, and SageMaker integration for designing enterprise-grade AI infrastructure.The Layered Architecture of AWS AI/ML Services - Flexibility Through the Three Tiers of SageMaker, Bedrock, and API ServicesThis article organizes AWS AI/ML services into three layers - SageMaker (full control), Bedrock (managed generative AI), and Rekognition/Comprehend/etc. (API-based) - and explains AWS's flexibility through comparisons with GCP Vertex AI and Azure OpenAI Service, including custom silicon integration.Using Claude on Amazon Bedrock - Model Selection, Prompt Design, and Cost OptimizationCompares the Anthropic Claude models available on Amazon Bedrock, provides model selection guidelines by use case, and covers prompt design best practices and cost optimization.Amazon SageMakerA fully managed platform for building, training, and deploying machine learning models end-to-end, significantly boosting productivity for data scientists and ML engineers