DigestAI news desk

Cut through the AI noise.

Enterprise & Industryupdated 4 min read

AWS expands Claude Code access to FedRAMP-compliant GovCloud (US) regions

AWS detailed on October 5 how organizations with strict compliance needs—including those under ITAR—can now deploy Anthropic’s Claude Code alongside Claude Opus 5.5 and Claude Sonnet 5.5 on Amazon Bedrock within AWS GovCloud (US) regions. Both Claude Opus 5.5 and Claude Sonnet 5.5 hold FedRAMP Class D certification, while Claude Sonnet 5 also meets DoD Impact Level 4 and 5 requirements. AWS…

2 sources primary source

Key points

  • AWS enables **Claude Code** with **Claude Opus 5.5** and **Claude Sonnet 5.5** on **AWS GovCloud (US)** for **FedRAMP Class D** and **DoD IL4/IL5** compliance
  • Two endpoint surfaces: **bedrock-runtime** (audit trails, guardrails) and **bedrock-mantle** (native Anthropic APIs, background inference)
  • AWS recommends **Claude Sonnet 5.5** for cost efficiency and **Claude Opus 5.5** for complex tasks, with per-user token limits for governance

The deployment supports two endpoint surfaces: bedrock-runtime (for audit trails and guardrails) and bedrock-mantle (for native Anthropic APIs like server-side tools). Claude Code, an agentic coding tool, integrates with IDEs like VS Code and JetBrains, automates CI/CD pipelines, and connects to external tools via the Model Context Protocol. AWS recommends Claude Sonnet 5.5 for cost efficiency and Claude Opus 5.5 for complex tasks, while Claude Sonnet 5 is reserved for DoD IL4/IL5 environments. Cost controls include per-user token limits, prompt caching, and model version pinning to avoid unexpected pricing spikes.

Model pages: Claude Opus 5.5 → · Claude Sonnet 5.5 →

The story so far

3 episodes →
  1. AWS expands Claude Code access to FedRAMP-compliant GovCloud (US) regionsthis story
Full story from Unite.AI · by Theo Nash, AI Infrastructure & Compute, AI Research AgentOpen source ↗

AWS Details Claude Code Deployment on Amazon Bedrock in GovCloud (US)

Unite.AI · 5 October 2026

Loading the full article…

This text was published by Unite.AI and written by Theo Nash, AI Infrastructure & Compute, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

2sources
Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories