Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [BUG] Max plan usage at 100% with zero requests — claude.ai (not Claude Code) [4 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#46946•Fetched 2026-04-12 13:28:59
View on GitHub
Comments
4
Participants
2
Timeline
10
Reactions
0
Author
gadgarciagadgarcia
Participants
Codename-404Codename-404gadgarciagadgarcia
Timeline (top)
commented ×4labeled ×2renamed ×1subscribed ×1

Error Message

Error Messages/Logs

Root Cause

This is a claude.ai billing issue, NOT a Claude Code bug. Filing here because support chat (Fin AI Agent) gave automated responses and no escalation path exists. Related: #38335, #41930, #41788, #38029, #16157.

Code Example

“Claude AI usage limit reached, please try again after [time]”
RAW_BUFFERClick to expand / collapse

Preflight Checklist @claude

  • 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?

My Max plan hit 100% usage with zero requests sent. Yesterday (April 11), usage jumped to 100% without any interaction. This morning, a single “hello” consumed ~1% and I hit the limit in under 5 minutes. I’m using claude.ai web/mobile only — NOT Claude Code. I have multiple connectors (Supabase, Netlify, Gmail, Google Calendar, Figma, Canva) and a Project with ~40 knowledge files. The system context appears to consume the entire quota before any user interaction. Support chatbot gave a generic response and closed without escalation.

What Should Happen?

Usage should not reach 100% with zero user requests. A single “hello” should consume a negligible fraction of quota. Max plan subscribers should have access to human support for billing anomalies.

Steps to Reproduce 1. Have a Max plan with multiple connectors enabled (Supabase, Netlify, Gmail, etc.) 2. Have a Project with ~40 knowledge files 3. Do NOT send any message 4. Observe usage meter reaching 100% 5. After reset, send “hello” — observe ~1% consumed per message 6. Limit reached within 5 minutes

Error Messages/Logs

“Claude AI usage limit reached, please try again after [time]”

Steps to Reproduce

  1. Have a Max plan with multiple connectors enabled (Supabase, Netlify, Gmail, etc.) 2. Have a Project with ~40 knowledge files 3. Do NOT send any message 4. Observe usage meter reaching 100% 5. After reset, send “hello” — observe ~1% consumed per message 6. Limit reached within 5 minutes

Claude Model

None

Is this a regression?

No, this never worked

Last Working Version

No response

Claude Code Version

Claude web

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

This is a claude.ai billing issue, NOT a Claude Code bug. Filing here because support chat (Fin AI Agent) gave automated responses and no escalation path exists. Related: #38335, #41930, #41788, #38029, #16157.

<!-- Failed to upload "IMG_5863.mov" -->

extent analysis

TL;DR

The issue may be resolved by contacting human support for billing anomalies, as the current usage pattern appears to be incorrect.

Guidance

  • Review the list of enabled connectors (Supabase, Netlify, Gmail, etc.) to ensure they are not consuming the quota without user interaction.
  • Verify that the Project with ~40 knowledge files is not causing excessive system context consumption.
  • Check if there are any known issues or limitations with the Max plan or the Anthropics API that could be contributing to the problem.
  • Consider reaching out to human support again, providing detailed steps to reproduce the issue, to escalate the matter.

Notes

The issue seems to be related to the billing and usage of the Claude AI service, rather than a bug in the Claude Code. The provided information suggests that the system context is consuming the entire quota before any user interaction, which may indicate a problem with the service's usage tracking or billing mechanism.

Recommendation

Apply workaround: Contact human support for billing anomalies, as the current usage pattern appears to be incorrect, and provide detailed steps to reproduce the issue to help resolve the matter.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#agent setup#task chaining#parallel task#integration issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING