1 min read AI-generated

Claude Code 2.1.158: Auto Mode Now Available on AWS Bedrock and Google Vertex

Copy article as Markdown

Claude Code's Auto Mode now works on AWS Bedrock, Google Vertex AI, and Azure AI Foundry. If you're running Opus 4.7 or 4.8 through these platforms, you can opt in now.

Featured image for "Claude Code 2.1.158: Auto Mode Now Available on AWS Bedrock and Google Vertex"

Quick update for anyone running Claude Code through a cloud provider: version 2.1.158 brings Auto Mode to AWS Bedrock, Google Vertex AI, and Azure AI Foundry — for both Opus 4.7 and Opus 4.8.

What’s Auto Mode?

Auto Mode lets Claude Code decide how much effort a task requires. Instead of manually switching between quick and thorough responses, Claude adjusts processing depth automatically. Simple questions get fast answers, complex problems get more time and thought.

What changed

Until now, Auto Mode was only available through the direct Anthropic API. If you were running Claude Code through Bedrock, Vertex, or Foundry — which most enterprise teams do — you were locked out. That’s no longer the case.

To enable it, set the environment variable CLAUDE_CODE_ENABLE_AUTO_MODE=1. After that, Auto Mode works with Opus 4.7 and 4.8.

Why it matters

For enterprise teams using Claude Code through their existing cloud infrastructure, the missing Auto Mode was a noticeable gap compared to the direct API experience. This update closes it. Not a revolution, but an important step toward feature parity across all access methods.

Version 2.1.159 followed a day later with internal infrastructure improvements and no user-facing changes.


Sources: