Bedrock Thinking 26 Mar 2026

Enabling Thinking on Bedrock

If you're using Claude Code through AWS Bedrock and noticed the thinking steps have gone quiet, there's a fix for that.


The problem

As a Bedrock user, I noticed that thinking steps weren't showing up in Claude Code's output. No reasoning traces, no visibility into the model's thought process. I couldn't tell whether the model was still thinking behind the scenes or not. I was completely flying blind.

That's what prompted the dig into Claude Code's model configuration.

The fix

Claude Code recently added environment variables that let Bedrock users explicitly declare which capabilities their model supports. For Opus:

export ANTHROPIC_DEFAULT_OPUS_MODEL_SUPPORTED_CAPABILITIES='effort,max_effort,thinking,adaptive_thinking,interleaved_thinking'

The same pattern works for Sonnet:

export ANTHROPIC_DEFAULT_SONNET_MODEL_SUPPORTED_CAPABILITIES='effort,thinking,adaptive_thinking,interleaved_thinking'

You can also set these via the env block in Claude Code's settings file (~/.claude/settings.json):

{
  "env": {
    "ANTHROPIC_DEFAULT_OPUS_MODEL_SUPPORTED_CAPABILITIES": "effort,max_effort,thinking,adaptive_thinking,interleaved_thinking",
    "ANTHROPIC_DEFAULT_SONNET_MODEL_SUPPORTED_CAPABILITIES": "effort,thinking,adaptive_thinking,interleaved_thinking"
  }
}

What about Haiku?

There's no ANTHROPIC_DEFAULT_HAIKU_MODEL_SUPPORTED_CAPABILITIES variable yet. I'd expect support to land with Haiku 4.6, but for now it's Opus and Sonnet only.

The capabilities explained

The comma-separated values map to specific model features:

Further reading

The full model configuration docs cover all available environment variables, not just capabilities. See the model config documentation for the complete reference.