[BUG] Max5 plan hitting session limits daily (including off-peak hours)
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?
Summary
I am consistently hitting session limits while using Claude Code despite being on the Max5 plan. This happens every day and is not limited to peak usage hours.
Environment
Product: Claude Code
Plan: Max5
Platform: Windows
Interface: CLI
Approximate usage pattern: continuous coding sessions
What Should Happen?
Expected Behavior
Max5 plan should allow significantly extended usage without frequently hitting session limits, especially during off-peak hours.
Actual Behavior
Session limits are reached daily
Occurs even during off-peak hours
Interrupts normal workflow
No clear indication of what usage threshold is being exceeded
Frequency
100% reproducible
Happens daily
Impact
Blocks development work
Forces frequent interruptions
Reduces usefulness of paid Max5 plan
Additional Notes
This does not appear to correlate with peak system load
No visibility into remaining quota or why the limit is triggered
Would benefit from clearer usage metrics or rate limit transparency
Questions / Request
What exact limits apply to Max5 (sessions, tokens, time, etc.)?
Are limits dynamic or shared across users?
Is this expected behavior or a misconfiguration/bug?
Error Messages/Logs
You're out of extra usage · resets 2pm (America/Chicago)Steps to Reproduce
Steps to Reproduce
Start a normal Claude Code session
Use it for typical development tasks (code generation, edits, etc.)
Continue working over time (not excessive or unusual usage)
Hit session limit
Claude Model
Opus
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
2.1.86
Platform
Anthropic API
Operating System
Windows
Terminal/Shell
PowerShell
Additional Information
_No response_
14 Comments
It's definitely related to claude code.
X is filled with these problems apparently and guess what claude code directed me here. It identified too.
<img width="983" height="171" alt="Image" src="https://github.com/user-attachments/assets/699eeca5-8876-4857-821c-12510651e718" />
after waiting for my limit to reset, I gave it one command, which was: "sorry for the interruption, please continue"
4% GONE
<img width="452" height="62" alt="Image" src="https://github.com/user-attachments/assets/7f61914b-ac4b-4f94-af5d-1d3a22e5f7f9" />
still thinking. only 5k tokens used.
and just 15 minutes later.
<img width="961" height="170" alt="Image" src="https://github.com/user-attachments/assets/d1de0411-680f-43d2-8f56-53df7a832be0" />
already at 12 percent.
My 5 hour session was reset at 7pm and then closed at 9.30pm and won't restart until 1am tomorrow. Why only half of my session limit?
dont think i will renew my max subs again. Switching to codex, performance and rate limits are creating unnecessary hindrances
Same pattern on Max 20. April 1: 100% in ~70 min. Affects all Max tiers.
Full report: #41788
Related: #38335, #38239, #41663, #40652
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
Is this fixed? I have cancelled my max plan and i wanna know before I renew it
@melonrusk13 Honest answer: partially. v2.1.90 fixed the biggest client-side bug (cache regression), and my benchmarks showed dramatic improvement — from 100% drain in 70 min to 5% for the same workload.
However, several users on v2.1.90 still report faster-than-expected drain, pointing to additional issues (possible server-side accounting change, client-side rate limiter bug #40584). I'd suggest waiting until Anthropic officially acknowledges and addresses the full scope before re-subscribing, unless you're willing to monitor and work around the remaining issues.
Brief update (April 3): v2.1.91 is out and cache behavior is further improved — npm and standalone now perform identically (Sentinel gap closed). However, testing revealed two additional unfixed bugs: a 200K tool result budget cap that silently truncates older results, and a client-side false rate limiter generating
<synthetic>errors without API calls (151 entries confirmed). If you are still seeing drain after updating, these are the likely causes. Details: claude-code-cache-analysisClosing for now — inactive for too long. Please open a new issue if this is still relevant.
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.