JA EN
shiichan

Claude Opus 5.5 and Sonnet 5.5 arrive in Kiro on GovCloud!

AWS What's New ★★★★ View Markdown
#aws#anthropic#ai

Hi everyone, it's Shii-chan! Two new Anthropic models have arrived in Kiro on GovCloud.

AWS What's New aws.amazon.com

What was announced?

AWS What's New announced that Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 are now available in the Kiro IDE and CLI for the AWS GovCloud (US) Regions.

What changes

Teams using Kiro in GovCloud can now pick the latest Claude models. You get a cost-performance dial: Opus 5.5 for maximum capability, Sonnet 5.5 for higher throughput.

Dive Deep

What each model offers:

  • Claude Opus 5.5: Anthropic's most capable Opus model yet, a step up from Opus 5 on long-running agentic coding work. It thinks adaptively on every request. In Kiro's internal benchmarking it completes tasks with roughly 40% fewer tool calls and about half the tokens of Opus 5. It has a 1M context window and a 2.0x credit multiplier, down from Opus 5's 2.2x
  • Claude Sonnet 5.5: Anthropic's fastest Sonnet model to date. Output is more than 30% faster, and real-world coding and knowledge work approaches Opus 5.5 performance. Clearer writing makes it a stronger collaborator. It has a 1M context window and a 1.3x credit multiplier, and is a natural upgrade for teams already on Sonnet 5

To get started, update your IDE or CLI to the latest version, restart it, and pick the new models from the model selector. Details are in the GovCloud documentation and the monitoring and tracking guide.

Wrap-up

  • Opus 5.5 and Sonnet 5.5 are available in Kiro IDE and CLI in GovCloud (US)
  • Credit multipliers are 2.0x for Opus 5.5 (down from 2.2x for Opus 5) and 1.3x for Sonnet 5.5
  • Both have a 1M context window
  • Update and restart, and they show up in the model selector

It's a good fit for development teams doing AI-assisted coding in GovCloud.

Related posts