[BUG] €450 consumed in under 24 hours - €50 exhausted creating 4-5 markdown files in a clean empty workspace (2.1.139)
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
In under 24 hours (May 10-12, 2026), €450 were consumed across three charges:
Weekly quota on Max plan (€200/month equivalent) - exhausted in less than one day.
€200 extra usage purchased after quota ran out - exhausted within approximately 2 hours.
€50 extra usage purchased after that - nearly entirely consumed (~€44) in a brand new, empty workspace by a session that only created 4-5 short markdown files.
The third charge is the clearest evidence of a bug: a clean workspace, no agents, no background tasks, no large files - just a planning conversation resulting in 4-5 small markdown files - consumed nearly €50.
I have been using Claude Code for months on far larger projects (hundreds of documents, agents, complex workflows, full websites) without this level of consumption.
What Should Happen?
Creating 4-5 markdown files in a short session should cost a few euros at most. Prior usage on significantly larger workloads was proportionally priced.
Error Messages/Logs
Steps to Reproduce
Steps to Reproduce
Open Claude Code in VS Code, claude-opus-4-7 (1M context), Max plan
Open a brand new empty workspace with no prior history
Have a short planning conversation resulting in creating 4-5 small markdown files
Observe ~€44 consumed
Session ID: c6867737-ed37-4b5f-b5b4-d45bf59665b5
Dates: May 11-12, 2026
Version: 2.1.139
Claude Model
None
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
2.1.139
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
VS Code integrated terminal
Additional Information
Platform: macOS (darwin), VS Code extension
Model: claude-opus-4-7, 1M context
Plan: Max + Extra Usage
Related issues:
#42272 - 66% quota in 2 questions (regression since 2.1.88)
#17740 - 68% quota in one conversation (regression Dec 30, 2025)
#13569 - Token consumption spiked after 2.0.64
#11716 - Background processes cause infinite token exhaustion
This issue has 5 comments on GitHub. Read the full discussion on GitHub ↗