編程工具全線接入新旗艦模型

Back to all posts Claude Opus 5.5 is available today across Kiro IDE, CLI, Crew, and Web.It is Anthropic's most capable Opus model yet, delivering Fable 5.1-level performance on most work at 40% lower cost than Opus 5.State-of-the-art on coding and knowledge work For agentic coding, Opus 5.

5 finds the root cause before it changes anything and checks its work as it goes, so its changes are easier to review and trust.Opus 5.5 also communicates more naturally than prior models and puts the most important information up front, which makes its writing clearer and easier to follow.

In our internal benchmarking, Opus 5.5 outperformed Opus 5 while making ~40% fewer tool calls and using half the tokens."Every call an agent makes is time and cost a developer feels.On a public benchmark of real command-line tasks, Opus 5.

5 solved more than Opus 5 while making about 40% fewer calls and using half the tokens.For developers building with Kiro, that means faster, more affordable agent sessions for routine tasks and complex challenges alike." — Deepak Singh, VP of Agentic AI at AWS A note on safeguards Opus 5.

5 is comparable to Claude Mythos 5.1 in biology and cybersecurity, and has safeguards similar to those on Claude Fable 5.1.Everyday coding, health, and educational questions work as usual, and some higher-risk requests are blocked.

If you hit a false positive on a benign task, switch to another model in Kiro.Availability Claude Opus 5.5 is gradually rolling out with experimental support to Kiro Pro, Pro+, Pro Max, and Power customers in us-east-1 (IAD) and eu-central-1(FRA).

It ships with a full 1M context window and a 2x credit multiplier.Download Kiro or restart the Kiro IDE, CLI, or Crew to check for the latest available models.Web users can refresh their browser to see Claude Opus 5.5 in the model selector.

{PREVIOUS}How we built a software factory with Kiro Crew to merge 1000 PRs in a week