[BUG] max_tokens must be greater than thinking.budget_tokens

[solace-rcampbell]

Preflight Checklist

• I have searched existing issues and this hasn't been reported yet
• This is a single bug report (please file separate reports for different bugs)
• I am using the latest version of Claude Code

What's Wrong?

Occasionally, when I'm running prompts, I get this error message:

  ⎿ API Error: 400 {"error":{"message":"{\"message\":\"`max_tokens` must be greater than `thinking.budget_tokens`. Please consult our
    documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking#max-tokens-and-context-window-size\"}.
    Received Model Group=bedrock-claude-4-5-sonnet\nAvailable Model Group Fallbacks=None","type":"None","param":"None","code":"400"}}

Running the request a second time often resolves the problem.

What Should Happen?

I expect no errors.

Error Messages/Logs

Steps to Reproduce

I don't have a recipe for this. I've seen this maybe 4 times since upgrading to Claude v2.x. Some other people in my team have also seen this.

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.0.2 (Claude Code)

Platform

AWS Bedrock

Operating System

Other Linux

Terminal/Shell

Other

Additional Information

No response

[andreweskeclarke]

I've seen the same problem, as have many of my teammates. Often happens with ultrathink and plan mode combined.

When I used TCP dump to see the settings, I found this JSON snippet:

"max_tokens":21333,"thinking":{"budget_tokens":31999,"type":"enabled"}

It seems that Claude Code is specifying an incorrect max_token value in some code paths.

edit: Confirmed from the json that the model is claude-sonnet-4-5-20250929 and that the Plan Mode <system-reminder> is present.

[jimutt]

We are noticing the same error with Claude Code 2.0 in our configuration that uses Vertex AI. It seems like it surfaces just about any time I enable thinking mode now.

  ⎿  Error reading file
  ⎿  API Error: 400 {"error":{"message":"{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"`max_tokens` must be greater than `thinking.budget_tokens`. Please consult our
     documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking#max-tokens-and-context-window-size\"},\"request_id\":\"req_vrtx_011CTiayeKcKJKi4Bsnp7EPE\"}. Received Model
     Group=claude-sonnet-4-5-20250929\nAvailable Model Group Fallbacks=None","type":"None","param":"None","code":"400"}}

[solace-rcampbell]

This used to only happen about once per day, but it's happened to me 6 times in the past hour. This is becoming a real problem for me.

[KhaiHuynhVN]

Same problem

[JasperBraun]

Restarting claude code fixes it temporarily. But after a while it comes back. Based on the error message and behavior I suspect that the thinking budged is accumulated with each query over time and not reset/reassigned for each query, i.e. thinking_budged += new_thinking_budget instead of thinking_budget = new_thinking_budget.

[andreweskeclarke]

Not quite, the problem is that their code decides to reduce max_tokens by 1/3 without adjusting the thinking.budget_tokens a similar amount. If you record the tcp traffic, you'll normally see:

{..., "max_tokens":32000,"thinking":{"budget_tokens":31999,"type":"enabled"}, ...}

Then, seemingly randomly, you'll see these JSON values and a failure:

{..., "max_tokens":21333,"thinking":{"budget_tokens":31999,"type":"enabled"}, ...}

[emilmahler]

I also have this problem on Vertex AI. Do we have to cross our fingers and hope that Anthropic will fix this bug? Or is there something we can change in our configuration (e.g. environment variables)?

[pluo]

I have to temporarily apply thinking_budget_tokens := min(thinking_budget_tokens, max_tokens) to the anthropic/v1/messages requests in my local anthropic proxy. Hopefully the claude-code team can fix it soon.

[frederick-wang]

‌‌Encountered the same issue, hope it gets fixed soon.