Cost and usage issues on macOS
Issues the maintainers labelled both platform:macos and area:cost.
1,037 issues · 177 open · 860 resolved (83%) · first seen May 11, 2025
Is this getting better or worse?
This class of problem is converging. 344 new reports in the last 90 days vs 464 in the 90 before — -26%. The open backlog peaked at 275 in 2026-04 and sits at 177 today.
Derived by counting each matching issue from its creation date until it closed. First-party
computation over the anthropics/claude-code tracker — the trend is not published
anywhere upstream.
Which builds report this
686 of these reports name the Claude Code build they were running, spanning 157 releases. Heaviest reporters:
- Claude Code v2.1.119
- Claude Code v2.1.92
- Claude Code v2.1.198
- Claude Code v2.1.114
- Claude Code v2.1.123
- Claude Code v2.1.118
- Claude Code v2.1.170
- Claude Code v2.1.201
Report volume, not a defect count: an issue can mention a build without that build having caused the failure. Versions come from the version string in the bug-report template, matched against real published tags.
Do these get fixed?
Median time to close is 37 days across 860 closures. Of the 860 closures with a recorded reason, 18% were closed as completed and 709 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
84 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Instantly hitting usage limits with Max subscription
- …communication that is inflating token usage significantly. Temporary fix for those on npm: npm install -g @anthropic-ai/claude-code@2.0.61 Hope this helps the devs pinpoint the regression.
Found in the thread of #16157 · still open - Need for dedicated .claudeignore file - .gitignore is insufficient for multi-platform projects
- …xclusion needs are context-dependent, not permanent Current Workaround Limitations The suggested solution of ["adding large build directories to your .gitignore file"]( doesn't work because: - These aren't build director…
Found in the description of #1304 · resolved - [BUG] API Error: Usage credits required for 1M context
- …session. Updating doesn't help (already on latest version). Workaround /model → standard context lets work continue, but 1M (included in Max) remains unusable.
Found in the thread of #63060 · still open - [BUG] 5-hour limit reached in less than 1h30
- ….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](
Found in the thread of #6457 · still open - [BUG] Opus usage limit reached unusually fast with Max 20x plan since Claude Code v2
- I found a workaround by manually setting Opus in plan mode in the settings, which seem to resolved the issue.(opusplan) Well.. i guess i have to contact support now...
Found in the thread of #8449 · resolved
Excerpts are quoted from the linked issue so you can judge relevance before opening it. Threads that only ask for a workaround, or report that there is none, are excluded. These are community suggestions, not official guidance from Anthropic — read the full thread before applying one.
Matching issues 1–100
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 1,037 matches; the statistics above cover all 1,037.
- [BUG] Instantly hitting usage limits with Max subscription
- HERMES.md in git commit messages causes requests to route to extra usage billing instead of plan quota
- Need for dedicated .claudeignore file - .gitignore is insufficient for multi-platform projects
- [BUG] Usage limits bugged after double limits expired on new years.
- [BUG] API Error: Usage credits required for 1M context
- Token and Time Counter Missing in Normal Mode 1.0.83
- [BUG] 5-hour limit reached in less than 1h30
- [BUG] Opus usage limit reached unusually fast with Max 20x plan since Claude Code v2
- [BUG] Claude Code defaults to 1M context on fresh session with no workaround on Pro plan
- [BUG] Abnormal / inflated rate limit / session usage
- [Bug] Max plan usage consumed at unusually high rate without workflow changes
- [BUG] Fable 5 prompts 'usage credits required' on Max plan from 2026-07-20, the day it became standard on Max (saved model claude-fable-5[1m])
- [BUG] Abnormal Usage Consumption on Claude Code Session Resume — Possible Bug
- [Bug] Anthropic API Error: Image processing failures causing conversation token waste
- [BUG] Plan upgraded but limit is not reset in sessions
- [BUG] Abnormal rate limit consumption — 1-2 prompts exhausting 5-hour window
- [BUG] Insanely rapid usage limit reached!
- [Bug] Anthropic API: Credit consumption rate increased 3-5x after January 1st
- [CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated subagent work.
- [BUG] Extreme token consumption — quota depleted in minutes with normal usage
- Claude Code API Usage Limit Unexpectedly Reduced on MAX Plan
- [BUG] Severe session limit reduction for Pro users (Hitting 100% in ~3 simple prompts)
- [BUG] Excessive token consumption since 2.1.88 — 66% usage in 2 questions (Max 5x, Opus 4.6)
- [BUG] Rate limit 429 errors despite dashboard showing available quota - Two Max accounts, documented inconsistencies
- [BUG] Local /cost doubles usage when parsing session JSONL (cache write & I/O tokens; ~2× total)
- [Bug] Excessive token consumption rate - usage depleting faster than expected
- [Bug] Unexpected high API usage consumption - 100% quota in 1-2 hours
- [Bug] Excessive token usage on new session initialization
- [BUG] Non-deterministic quota accounting: 65% of 5-hour session consumed with minimal actual token usage — Max $100 plan
- [Bug] Anthropic API Rate Limiting: Usage quota exceeded rapidly with minimal requests
- [Bug] Unexpected Rapid Usage Depletion on Claude Code 20x Plan
- "System reminder" content injection consuming excessive context tokens
- Cache read tokens consume 99.93% of usage quota - architectural scaling issue with CLAUDE.md re-reads
- [BUG] Claude hitting usage limits in no time, something broken for sure
- Bug: Claude Code current session limit reaches 100% despite low visible local session usage
- Max plan: usage exhausted abnormally fast, twice in one day (March 31)
- [Bug] Anthropic API Error: Usage credits required for 1M context window
- General-purpose sub-agents recursively spawn unbounded child agents, causing exponential fan-out and massive token burn
- [BUG] autoMemoryEnabled=false does not suppress the ~11-16k memory preamble (re: closed #44829)
- [BUG] Prompt Caching Works on Claude 3.7 But Not On Claude 4 Family (AWS Bedrock)
- [BUG] Usage limit decrease without Anthropic telling developers
- [Bug] Unexpected Weekly Usage Limit Tracking for Max Plan User
- [BUG] Claude Code all prompts are rejected with 400 invalid_request_error and a strange message
- [BUG] Usage limit erreicht trotz verfügbarer Weekly Quota (85% verbraucht laut claude.ai)
- [Bug] Sharp increase in token consumption since April 5-6 weekend — Max plan 5h limits hit in ~1-2h
- Anthropic API: Unexpected Opus Usage Limit Warnings on Pro Plan
- [BUG] CLI completely blocked by "out of extra usage" error despite Max 20x plan at only 10% usage
- [BUG] Claude Opus 4 limit reached, now using Sonnet 4
- Max 20x plan hitting daily limit with reduced usage — limits appear silently tightened (April 28-29, 2026)
- Token usage limit reached significantly earlier than in previous versions
- Weekly limit reached ∙ resets 6pm
- You've hit your limit · resets 11am (America/Chicago)
- Limit reached · resets 11:30am (Asia/Calcutta) · /upgrade to Max or turn on /extra-usage
- [Feature Request] Reduce verbosity in plan mode to minimize token consumption
- [Bug] Anthropic API: Unexpected Weekly Token Limit Depletion
- ultrareview crashed before producing findings — free credit consumed
- [BUG] Usage Concerns
- [Bug] Session limit reached prematurely on Pro Plan despite low usage
- [BUG] Haiku 4.5 usage being counted the same as Sonnet 4.5 despite 3x lower cost
- [Bug] Excessive token usage for short messages (4% usage for "hi")
- [BUG] Usage jumped from 80% to 100% for the week.
- 5-hour usage limit hits 100% instantly despite low context usage (11%)
- [BUG] 🛑 **INSTANTLY** Running out of Limits Because Claude Code Is Submitting Messages **TWICE**
- [BUG] $100 subscription is getting capped super fast compared to the experience that I had in the past 4-5 months.
- [Bug] deep-research workflow aborts entire run (and burns millions of tokens) when any schema-bound subagent fails to emit StructuredOutput
- [Bug] Weekly usage limit reset occurring before scheduled reset time & new week ends in 5 days, not 7 days
- [BUG] Billing: $50 credits disappeared after Claude Pro subscription renewal (Receipt XXXX-XXXX-7352)
- [Bug] Unexpectedly high token consumption rate since January 2026
- limit hit super quickly
- [Feature Request] Add automatic cost reporting on session exit
- [BUG] Agent Teams: lead session loops on idle notifications and duplicate task_assignment echoes, burns ~13–22% of input tokens on no-op acks
- [Bug] Excessive token consumption in API requests
- [BUG] Task tool `model` parameter returns 404 - Blocks cost-optimized workflows (10-30x unnecessary spending)
- [BUG] High usage while using Opus 4.6
- Prompt cache fully re-created after turns with many parallel tool calls (cache_read collapses to system+tools floor) — ~74% of cache writes wasted on Opus 4.8 / v2.1.15x
- [Bug] Weekly usage reset time displayed incorrectly for Pro plan users
- [Bug] Session token limit reached prematurely after upgrade to v2.0.64
- [BUG] Cost not calculated for LLM Gateway interactions
- /model shows Fable 5 as credits-only (€0.00) on Max plan, while /usage shows Fable covered by plan (5% of weekly limit)
- [BUG] Token consumption with Fable 5 is not matching with its description.
- [Bug] Anthropic API Error: Usage credits required for 1M context with 1M context disabled
- [Bug] Rate limiting too aggressive: 5-hour daily limit hit repeatedly with minimal usage
- [BUG] 2 PERCENT OF BUDGET USED BY ASKING ABOUT BUDGET USE
- [BUG] Claude Code Pro Quota Significantly Reduced: Limit Reached in ~20 Prompts per 5 Hours
- [BUG] Since mid-November, claude code is consuming ~5x tokens
- Model Mismatch: Max Plan Advertising Claude Opus 4 but Delivering Claude 3 Opus
- [BUG] Claude Code stating session limits hit and rejecting requests despite token quota being available
- [BUG] Hundreds of lines of modified file notes being injected into context on EVERY user message via <system-reminder>
- [BUG] Weekly Limit Jumped From ~50% to 100% in less than an hour of usage on Max20x Plan
- [BUG] Usage limits gone crazy
- [BUG] CLI-only "API Error: Rate limit reached" on every request despite 97% quota remaining (Max 20x plan)
- [Bug] Anthropic API Weekly Usage Limits Unexpectedly Low
- [BUG] 2.0.13 MASSIVE TOKEN USAGE DUE TO SYSTEM REMINDER
- Inefficient Tool Invocation Causing Significant Development Productivity Loss
- Abnormal token consumption rate on Opus 4.5 — 100% usage in ~1 hour
- Claude Code excessive limits usage in recent updates. Limits have either been reduced, or Claude Code is incorrectly counting tokens
- [BUG] OPUS TOKENS RUNNING WITHOUT OPUS BEING SELECTED
- [BUG] Opus 4.7/4.8 token usage regressed 2-3x after update; Opus 4.8 also disconnects frequently
- [BUG]Weekly Limits Are Draining Much Faster After the 5-Hour Limit Update
- You're out of extra usage · resets 2pm