[BUG] MAX100 subscription - abnormal quota consumption and rate_limit_error with multi-session Claude Code
Status Closed — not planned
Reported on v2.1.81
Maintainer reply None cached
Activity 11 comments · opened Mar 22, 2026 · closed May 2, 2026
Description
MAX100 subscriber experiencing abnormal 5-hour quota consumption and rate_limit_error when running multiple Claude Code sessions simultaneously.
Environment
- Plan: Claude MAX100
- Claude Code version: 2.1.81
- OS: Windows 11 Pro
- Sessions: 5 concurrent Claude Code sessions (VS Code terminals)
Issue 1: Abnormal Quota Consumption
- Previous 5-hour quota period: 45% consumed in 45 minutes
- Current 5-hour quota period: 23% → 32% within minutes of starting sessions, with NO active work being done
- Sessions were idle (no prompts submitted, no tool calls)
Issue 2: Rate Limit Error on /usage
Error: Failed to load usage data:
{"error":{"type":"rate_limit_error","message":"Rate limited. Please try again later."}}This occurred immediately after session startup, with no active work.
Expected Behavior
- Idle sessions should not consume significant quota
- 5 concurrent sessions should be supported for MAX100 plan
- /usage should not return rate_limit_error
Steps to Reproduce
- Open 5 Claude Code sessions in VS Code (different project directories)
- Run
/start-agent-chat-loopin each (registers agent + starts background watcher) - Observe quota rapidly increasing without any work
- Run
/usage→ rate_limit_error
Additional Context
- Each session has MCP servers (agent-chat, memory, supabase, context7)
- Background watcher (watch.py) polls SQLite locally, not API
- This pattern worked fine in previous quota periods with similar setup
11 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
I'm having the same issue. After a recent forced reauthorization, my consumption rate is at least 4x what it was. I almost never approached my 5 hr limit, but now limit out in 1.5-2 hrs every time. I tried killing everything because it was showing me using API (though I have API off) instead of MAX. That made it show me using MAX again, but the burn rate is still massive. I'm getting phantom windows flash now too, as well as a terminal window opening at times for up to about 10 seconds before closing.
In the Terminal that pops up:
___________________________________
'wmic' is not recognized as an internal or external command,
operable program or batch file.
2026/03/21 19:50:01 ERROR 123 (0x0000007B) Accessing Destination Directory C:\Users\[FILE PATH]-~0,4%datetime:~4,2%datetime:~6,2datetime:~8,2%datetime:~10,2%datetime:~12,2\
The filename, directory name, or volume label syntax is incorrect.
_________________________________
When I start Claude Code, I also see this. I don't use API billing, so I'm not sure how this applies.
Claude Code v2.1.70
▝▜█████▛▘ Sonnet 4.6 · API Usage Billing
▘▘ ▝▝ ~\GraceHaven\gracehaven-latest
It used to say:
▐▛███▜▌ Claude Code v2.1.70
▝▜█████▛▘ Opus 4.6 · Claude Max
▘▘ ▝▝ ~\GraceHaven\gracehaven-latest
That was before I started seeing my usage ramp up massively.
After completely shutting down and logging out, it says Claude Max again, but the issue persists.
I've made sure everything is up to date.
Since yesterday, token/usage consumption has become severely abnormal. Simple instructions that previously consumed 2-4% of the 5-hour limit are now consuming 10-15%.
Max 100 plan here
Same here. Fresh 5 hour session, fresh weekly quota. Resumed existing session, and typed one prompt: run node front end. Few seconds later 75% of 5 hour quota consumed with opus.
I am using claude daily and up until last Friday, this never happened before
Latest version claude code cli, Windows.
My five hour limit was just used up in less than one hour (about 45 min). I've never had it come close to that, even though the usage has increased disproportionately to productivity. At this rate even the 20x plan wouldn't keep up. The problem appears to be getting worse. After a week, I can't get support to respond. What can we do?
Yeh, im hitting abnormal usage too...
Normally 1x 5 hour limit is 8% for my total week.. During promo it was 5-6%...
Today? Its 14 fking percent... Thats HALF my usage per week...
What the actual fk is going on here???????
Max20 here...
I just updated to Max20 as well, so I could keep working. I guess throttling me worked? Support is non-responsive after over a week. I'm close to using my 5hr limit even with the upgrade. This is insane. I pay twice as much for 20x, and might get 10x. Shut down again. Can anyone get any support from Anthropic?
Now im also getting this...
Ive always, for over a year worked in 10+ terminals without a single issue...
Its also not consistent, sometimes its on 7 terminals sometimes on 10... the only thing that is consistent is that it kills ALL MY terminals AND ALL my work.... blanket on every single client...
"API Error: Rate limit reached".... Cant even find info on it...
Closing for now — inactive for too long. Please open a new issue if this is still relevant.
It's totally relevant. But nothing is being done about it.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.