Max Plan (00/mo) usage limits significantly reduced compared to 2 weeks ago

Status Closed — not planned
Maintainer reply None cached
Activity 14 comments · opened Mar 30, 2026 · closed May 12, 2026

Description

I'm on the Max plan ($100/month) and my usage limit is being hit much faster than approximately 2 weeks ago. Same workflow, same usage patterns, but sessions are now cut short significantly earlier.

Impact

As a power user relying on Claude Code for daily professional work, this regression severely impacts productivity. I'm hitting "You've hit your limit!" within a few hours of focused work, whereas previously I could work through much longer sessions.

Environment

  • Plan: Claude Max ($100/mo)
  • Model: Claude Opus 4.6
  • Platform: Linux (Ubuntu)
  • Usage: Daily professional development workflows

Request

  1. Transparency: What changed in the limit calculations / token budgets?
  2. Restore previous limits or offer a higher tier for power users who need extended sessions
  3. Consider separate limits for /fast mode vs full Opus, since fast mode should cost less

Thank you for building an amazing tool — I just need more of it!

View original on GitHub ↗

14 Comments

github-actions[bot] · 5 months ago

Found 3 possible duplicate issues:

  1. https://github.com/anthropics/claude-code/issues/38335
  2. https://github.com/anthropics/claude-code/issues/37394
  3. https://github.com/anthropics/claude-code/issues/38350

This issue will be automatically closed as a duplicate in 3 days.

  • If your issue is a duplicate, please close it and 👍 the existing issue instead
  • To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

Michota · 5 months ago

Same issue. But I guess that's not a bug.

owlivion-tech · 5 months ago

I actually want the full potential that I am paying for. If it's a bug or not, does not matter. I and bunch of users I think want to be heard!

TheAuditorTool · 5 months ago

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...
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...

kolynan · 5 months ago

I’m seeing the same problem on Claude AI / web, not just Claude Code.

My usage runs out much faster than before, even with similar prompt size and similar workflow. It feels like the quota depletes disproportionately fast for normal use.

What makes this especially frustrating is that it’s hard to predict how much usage a session will consume before starting. Please improve:

  1. transparency of usage calculation,
  2. visibility of remaining quota,
  3. consistency across Claude web / desktop / code,
  4. overall value of paid plans when limits are reached this quickly.

This is affecting real work and makes the subscription feel unreliable.

ArkNill · 5 months ago

Confirming. Max 20 ($200/mo), v2.1.89, April 1: 100% in ~70 min. Limits have clearly been reduced without notice.

Full report: #41788
Related: #38335, #38239, #22435, #41663, #40790

ArkNill · 5 months ago

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_URL env 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

TheAuditorTool · 5 months ago

<img width="583" height="360" alt="Image" src="https://github.com/user-attachments/assets/2cea7f11-1d83-4a8b-8301-7f9456da7905" />

Done in ~3 days and i slowed down the last day and i was on .88. and .89...
Zero difference for me... Thats about HALF my usage this week...

This is max20... 200 usd per month... Unacceptable....

Everyone should cancel their sub, even if you intend to resume it in x weeks? Cancel it... If 10-100k of us do it? It will be statistically big enough to force their hand... Its the only way at this point...

weilhalt · 5 months ago

Same here. Max 20x plan, hit 100% after ~2 hours of normal work today (April 1st). 5 commits, no agents, no excessive sessions. This started around March 23 and hasn't improved. Paying $200/mo for a fraction of the advertised capacity.

ArkNill · 5 months ago

Follow-up — precautions (April 2, 2026)

The "limits reduced compared to 2 weeks ago" observation is correct. There appear to be two factors: a client-side cache bug (fixable) and a server-side limit recalculation (not fixable from our end).

To stretch whatever budget remains:

  • Avoid: --resume, /dream, /insights, v2.1.89
  • Careful with: sub-agents (Haiku = 0% cache read), multiple terminals
  • Use: v2.1.81 (fixed) + fresh sessions + proxy monitoring

Ref: https://github.com/ArkNill/claude-code-cache-analysis

ArkNill · 5 months ago

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:

  1. Update: claude update (or npm install -g @anthropic-ai/claude-code)
  2. Pin the version: add "DISABLE_AUTOUPDATER": "1" to ~/.claude/settings.json env section
  3. Avoid --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

ArkNill · 5 months ago

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

github-actions[bot] · 3 months ago

Closing for now — inactive for too long. Please open a new issue if this is still relevant.

github-actions[bot] · 2 months ago

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.