Supercharge regulated workloads with Claude Code and Amazon Bedrock

AWS published a post describing how to use Anthropic's Claude Code agentic coding tool with Claude Opus 5.5, Claude Sonnet 5.5, and Claude Sonnet 5 on Amazon Bedrock in AWS GovCloud (US) Regions. AWS states the availability of Claude Opus 5.5 and Claude Sonnet 5.5 in those regions introduces an on-ramp for AI-assisted development for workloads with regulatory or compliance requirements, including International Traffic in Arms Regulations (ITAR).

According to the post, Claude Sonnet 5 holds FedRAMP Class D (formerly High) certification and DoD Impact Level 4 and 5 (IL4/IL5) authorization, while Claude Opus 5.5 and Claude Sonnet 5.5 hold FedRAMP Class D certification on Amazon Bedrock. AWS advises verifying current model certification status.

AWS GovCloud (US) Regions are described as designed specifically for US customers with elevated compliance needs. Amazon Bedrock's listed features include built-in data protection where customer content is not stored, logged, used to train AWS models, or shared with third parties, plus FedRAMP Class D certification and DoD Cloud Service Provider SRG IL4/IL5 authorization pathways.

Amazon Bedrock in AWS GovCloud (US) supports two endpoint surfaces, bedrock-runtime and bedrock-mantle, both powered by the same Mantle inference engine with Zero Operator Access (ZOA) architecture. The bedrock-runtime endpoint uses the AWS SDK (InvokeModel and Converse APIs) and supports Guardrails, Knowledge Bases, Agents, and invocation logging. The bedrock-mantle endpoint supports the Anthropic Messages API natively and offers capabilities currently available only on that surface, such as server-side tools, background inference, and Projects. Both endpoints are available for Claude Opus 5.5, Claude Sonnet 5.5, and Claude Sonnet 5, with bedrock-runtime in both AWS GovCloud (US) Regions (US-West and US-East) and bedrock-mantle in AWS GovCloud (US-West).

The post outlines prerequisites including an AWS GovCloud (US) account with Amazon Bedrock access, IAM roles and permissions, model access to the three models, and AWS CLI configured with valid credentials. Setup options include an interactive wizard, manual environment variables such as CLAUDE_CODE_USE_BEDROCK, AWS_REGION, and ANTHROPIC_MODEL, or routing through the Mantle endpoint.

Enterprise considerations cited by AWS include central identity governance with AWS IAM Identity Center, automated environment variable configuration, service quota review for tokens and requests per minute, model version pinning, and per-user token guardrails. AWS notes Guardrails and invocation logging are available exclusively through the bedrock-runtime endpoint, and recommends a thorough security assessment before deployment because Claude Code runs on local developer machines and requires separate evaluation and risk management. The post carries a disclaimer that it is for informational purposes only and may not suit all organizations or compliance programs.