[BUG] Rate limit 429 errors despite dashboard showing available quota - Two Max accounts, documented inconsistencies
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?
Receiving persistent HTTP 429 rate limit errors while the dashboard shows available quota on multiple metrics.
Account: [thesage2412@gmail.com](mailto:thesage2412@gmail.com) (Max $100/month)
At time of 429 errors, dashboard showed:
Current session: 72% used (not 100%)
Weekly limits: 6% used (not 100%)
Claude Code: 0% used (not 100%)
Yet API returned:
HTTP 429: rate_limit_error: This request would exceed your account's rate limit.
Paradoxically, I could use claude.ai web interface on the same account while API returned 429s.
Request IDs demonstrating the issue:
req_011CXmMeQYEgck2Xmq78hGEw
req_011CXmS53VctxC2L8gCV1sjG
req_011CXmbcu6Xxi8WyYRtNkLDp
req_011CXmcB77V8XH8BoTcatsZd
req_011CXjjPpsr44MDCs6XAhpba
req_011CXjjRvsJzZrvBifd7bU7X
req_011CXjjTzWtjSDSjAyNzxQcc
req_011CXjjVz6u3AcrRKapZTeY5
What Should Happen?
What Should Happen?
If dashboard shows available quota (session, weekly, Claude Code all below 100%), API should not return 429
All rate limits that can trigger 429s should be visible in the dashboard
Rate limiting behavior should be consistent and predictable
Error Messages/Logs
HTTP 429: rate_limit_error: This request would exceed your account's rate limit. Please try again later. (request_id: req_011CXmbcu6Xxi8WyYRtNkLDp)
HTTP 429: rate_limit_error: This request would exceed your account's rate limit. Please try again later. (request_id: req_011CXmcB77V8XH8BoTcatsZd)
Also experienced 500 errors during the same debugging session:
API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"},"request_id":"req_011CXmPE58F6DVFELUrLQGBY"}Steps to Reproduce
Steps to Reproduce
Subscribe to Claude Max ($100 or $200 plan)
Use Claude Code or API via OAuth authentication
Send messages until session usage reaches ~70%
Observe dashboard showing available quota on all metrics
Continue sending messages
Receive 429 errors despite dashboard showing available capacity
Attempt same account on claude.ai web interface - works fine
Return to API/Claude Code - still 429
Claude Model
Opus
Is this a regression?
I don't know
Last Working Version
Unknown - I've only recently started using Max at this intensity. Other users report this started January 2026.
Claude Code Version
2.1.29 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Terminal.app (macOS)
Additional Information
Financial Impact
I spent ~$160 today trying to diagnose what I believed was a configuration issue:
~$40 in extra usage burned on primary account
$20 for new Pro subscription
$100 upgrade to Max on second account (*Pro Rated to $80 because it was an upgrade)
Two Accounts Affected
Account 1 ([spendino@gmail.com](mailto:spendino@gmail.com) - Max $200):
Weekly: 100% used
Session: 0% used
Extra usage: $33.93 spent, $11.06 remaining
Burned through extra usage rapidly (possibly related to #22297 infinite loop bug which may have burned this all in the first place spawning claude code sessions via the agent)
Account 2 ([thesage2412@gmail.com](mailto:thesage2412@gmail.com) - Max $100):
Weekly: 6% used
Session: 72% used
Getting 429s despite available quota
Related Issues
#22297 - /rate-limit-options infinite loop bug
#22435 - Inconsistent quota accounting on Max plan
#22439 - Usage limit reached despite available quota
#17084 - Opus 4.5 limits reduced since January 2026
Use Case
I run an AI agent via OpenClaw gateway using Claude Code OAuth. The agent performs legitimate work (meeting analysis, document processing). The rate limiting inconsistencies make it impossible to predict or budget actual usage.
Request
Refund for extra usage charges incurred debugging platform inconsistencies
Transparency on hidden rate limits not shown in dashboard
Dashboard fix to display ALL limits that can trigger 429s
Notes:
Using the sage account I can still talk to Claude Opus 4.5 with no issues.,. yet through openclaw i get 429s?; Opus helped write this with appropriate context from debugging it in the first place
11 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
Same issue here...paying the $100 per month plan and well within my hourly and weekly rate limits:
<img width="703" height="662" alt="Image" src="https://github.com/user-attachments/assets/2d9da04c-f2c8-4b7c-bcbb-41ef4cafb90d" />
The task is to basically perform OCR on a bunch of documents and summarize them for me to know what all I have in general.
Same Problem
429 {"type":"error","error":{"type":"rate_limit_error","message":"Extra usage is required for long context
requests."},"request_id":"req_011CZWzPEU2y5mvdxzMuJ2y7"}
Mine stopped giving it after awhile - nothing to do with the actual rate limit - it just somehow stopped giving it....Over the last month it occurred about twice though...just creating a record for Anthropic in case it's helpful.
Same issue on my side, bought extra credit yet not even able to submit a prompt today... please fix your bugs
[{"error":"Error: 429 {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your account's rate limit. Please try again later.\"},\"request_id\":\"req_011CZbPBPi21Psk7FCXkupR2\"}\n at generate (/$bunfs/root/src/entrypoints/cli.js:205:286312)\n at makeRequest (/$bunfs/root/src/entrypoints/cli.js:244:5435)\n at processTicksAndRejections (native:7:39)","timestamp":"2026-03-31T15:19:42.789Z"},{"error":"SyntaxError: JSON Parse error: Unexpected identifier \"You\"\n at <parse> (:0)\n at parse (unknown)\n at <anonymous> (/$bunfs/root/src/entrypoints/cli.js:98:1120)\n at R (/$bunfs/root/src/entrypoints/cli.js:96:27632)\n at <anonymous> (/$bunfs/root/src/entrypoints/cli.js:98:1237)\n at Fv_ (/$bunfs/root/src/entrypoints/cli.js:7499:16938)\n at processTicksAndRejections (native:7:39)","timestamp":"2026-03-31T15:19:42.790Z"},{"error":"Error: 429 {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your account's rate limit. Please try again later.\"},\"request_id\":\"req_011CZbPBPx9gxm27pjgRrjAh\"}\n at generate (/$bunfs/root/src/entrypoints/cli.js:205:286312)\n at makeRequest (/$bunfs/root/src/entrypoints/cli.js:244:5435)\n at processTicksAndRejections (native:7:39)","timestamp":"2026-03-31T15:19:42.911Z"},{"error":"Error: 429 {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your account's rate limit. Please try again later.\"},\"request_id\":\"req_011CZbPbv4onQdxZLNtFzts6\"}\n at generate (/$bunfs/root/src/entrypoints/cli.js:205:286312)\n at makeRequest (/$bunfs/root/src/entrypoints/cli.js:244:5435)\n at processTicksAndRejections (native:7:39)","timestamp":"2026-03-31T15:25:15.509Z"}]I've been experiencing the same issue on Max 20 ($200/mo) — rate limit 100% exhausted in ~70 minutes.
After setting up a monitoring proxy using the official
ANTHROPIC_BASE_URLenv var, I identified two cache bugs as the root cause (#40524, #34629) and measured the impact: cache read ratio dropped to 4.3%, meaning ~20x token inflation per turn. After applying workarounds it stabilized at 89-99%.Full analysis with per-request measured data, safe workarounds, and community references (including cc-cache-fix): https://github.com/ArkNill/claude-code-cache-analysis
Update (April 2): v2.1.90 has significantly improved cache efficiency — benchmark shows 95-99% cache read in stable sessions (both npm and standalone installations).
If you're still affected:
claude update(ornpm install -g @anthropic-ai/claude-code)"DISABLE_AUTOUPDATER": "1"to~/.claude/settings.jsonenv section--resume(still broken)Note: server-side quota issues (org-level pool sharing, accounting mismatches) remain unresolved — the above fixes the client-side cache drain only.
Benchmark data: https://github.com/ArkNill/claude-code-cache-analysis
April 3 update: v2.1.91 fixes the cache regression that caused the worst drain. If you are still hitting limits after updating, there are additional unfixed mechanisms: a 200K tool result budget cap, a client-side false rate limiter, and silent context stripping — all confirmed via proxy testing. Anthropic acknowledged peak-hour tightening on X (Lydia Hallie) but stated "none were over-charging you." Measured data and analysis: claude-code-cache-analysis
Same issue here
I came back from a week-end where I haven't touch Claude Caude at all for several days
It shows session 5hr with 19% used instead of 0
Weekly 3% used instead of 0
And it's saying "You've hit usage limit"
While I'm paying for claude max 20x
And should be able to use it...
So tired of this bs. I have Gemini fallback and Claude Max-failures. I need reliability. Either we down grade to 4.5 and I hate that option, or Anthropic needs to take their role seriously because I'm serious about switching fully. 4.6 is 2% better output, 9000% more likely to fail when we need it. Google is one benchmark away from taking lead.
News on this ?