Claude Sonnet 5.5 and Opus 5.5 now available in Kiro for AWS GovCloud (US)

What changed

Source summary

Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 are now available in the Kiro IDE and CLI for AWS GovCloud (US) Regions. Both models offer a 1-million-token context window; Opus 5.5 carries a 2.0x credit multiplier and Sonnet 5.5 a 1.3x multiplier.

Why it matters to your work

Practical interpretation

If your organisation works with AWS GovCloud for compliance reasons, your developers can now use Anthropic's latest Claude Opus 5.5 and Sonnet 5.5 models directly inside AWS's Kiro coding tool, with a much larger 1-million-token context window for handling bigger codebases. This mainly matters if you run regulated government or defence workloads on AWS; general commercial AWS customers access these models elsewhere already.

When this could help

Relevant when a GovCloud-based engineering team is choosing which model to run long agentic coding sessions on inside Kiro and wants the latest Claude models rather than staying on Opus 5.

Claude Opus 5.5 and Claude Sonnet 5.5 are now selectable models inside Kiro for GovCloud users, giving them Anthropic's newer coding-focused models (1M-token context, improved tool-call and token efficiency over the prior Opus 5) without leaving their GovCloud environment.

How to get started

1. Update Kiro (IDE or CLI) to the latest version and restart it.

   Provider guidance ↗

2. Select Claude Opus 5.5 or Claude Sonnet 5.5 from Kiro's model selector.

   Provider guidance ↗

What to check

• Claude Opus 5.5 carries a 2.0x credit multiplier (down from Opus 5's 2.2x) and Claude Sonnet 5.5 a 1.3x multiplier — both heavier on usage credits than a standard-rate model, a cost factor to weigh for high-volume agentic coding. Source ↗
• The announcement states no general-availability date, end date, or other restriction beyond availability being scoped to AWS GovCloud (US) Regions. Source ↗