Cost and usage issues on macOS — page 2
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 101–200
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 1,037 matches; the statistics above cover all 1,037.
- Usage limits hit significantly faster since v2.1.53–v2.1.59 (Feb 25–26) — auto-memory & system prompt bloat
- [Suspicious Behavior]: Hidden <system-reminder> 10,000+ injections consuming 15%+ of context window without user knowledge or consent
- [Bug] Ultrareview quota consumed on server-side rate limit failures
- claude -p suggested to Max subscriber — caused unintended API billing ($1,800+ in two days)
- [BUG] Claude Code for Desktop always shows "Claude API Account" instead of subscription account (NOT caused by API key)
- [Bug] A new Claude code sessions already takes 80K token (40%)
- PRO account shows - Credit balance is too low
- [Bug] Opus 4.7 performance degradation and excessive token consumption
- [Bug] Opus 4.7 metering: cache_read_input_tokens consuming 5-hour bucket at input-token rate (Max $100)
- [Bug] Claude Code token quota consumption increased significantly for Claude MAX subscribers
- [BUG] Max 20x: Usage meter climbing abnormally fast since ~March 23 — 1-2% per simple message exchange
- [BUG] print mode (-p) doesn't seem to be using my claude max subscription, instead pulling an API key from the environment
- [BUG] Opus 4.8 medium effort spends 46k output tokens on hidden thinking for a simple coding turn
- [FEATURE] Bandwidth-aware mode for metered connections (mobile hotspot, cellular tethering)
- [BUG] Model picker shows Opus 4.7 (200K) but session silently runs in 1M context — burned 18% of 5-hour Max limit on a small prompt
- [BUG] Rapid quota consumption in Claude Code with Opus 4.7 1M context — minutes-scale 90%+ burn from few prompts
- [Bug] Excessive token consumption on minor code updates
- [Bug] Session/weekly token limits deplete disproportionately fast with Opus orchestrator + Haiku subagents
- [BUG] Usage limit reached - while still having 93% weekly limit and 100% 5-hour limit
- [BUG] Weekly usage limit reset 4+ hours before scheduled reset time
- [Bug] Unexpectedly High API Usage and Rate Limit Hits
- [BUG] Session randomly dies with "API Error: Rate limit reached" despite near-zero usage
- [Bug] Pro plan usage limits consuming excessive tokens for simple tasks
- I used $10.63 of Claude Code, and have set my account...
- [Bug] Excessive API token consumption during Claude Code sessions (12% in 49 sec - Max 5x plan)
- [BUG] A user can do absolutely no coding and still use up all tokens in a session. Big fail.
- [Bug] Usage cost displayed for fixed seat pricing model
- [BUG] High Token Burn Due to Redundant Context Resubmission & Compaction Loops
- Weekly limit depletes disproportionately to 5h-session limit on Max 20x — quantified telemetry shows ~5x drift vs historical baseline
- [Bug] Unexpected high usage consumption on Claude Max plan (using claude code)
- [BUG] Massive discrepancy between actual token usage and subscription usage metering (26% of Teams Premium for ~$4 of tokens)
- WebSearch and subagents fail with 'Extra usage required for 1M context' on Max plan
- [Bug] Excessive token usage and over-researching file context
- [BUG] Compaction death spiral - 211 compactions consuming all tokens with zero progress
- [Bug] Rate limit consumed faster than expected with Sonnet-only usage across all models
- [URGENT] Account Disabled Immediately After Payment - No Service Access, No Refund, No Support Response (Invoice: DFON03V2-0005)
- You've hit your session limit · resets 11:50am (Europe/Budapest)
- [BUG] Something went wrong Try sending your message again. If it keeps happening, share feedback so we can investigate. API Error: Usage credits required for 1M context · turn on usage credits at claude.ai/settings/usage, or use
- Fast mode toggle has no billing warning for Max subscribers
- Bug Report - Extreme usage limit drain on Max Plan with Claude Code (one prompt consumes huge amounts)
- [Bug] Extended thinking hangs indefinitely, consuming all tokens without returning results
- [BUG] Re-open - Not able to use extra usage #17694
- [Bug] Rate limit errors with unexplained session quota consumption
- [Bug] Prompt Caching Not Working - Rapid Token Usage Depletion
- [BUG] Multi-Account Usage Limits overlap - Deadlock in #3857 and #5001
- [BUG] Prompt Cache TTL Reduced from ~5 to ~3 Minutes Without Documentation (Mid-December 2025)
- [BUG] Opus subagents are being billed as Fable usage
- [Bug] Excessive token consumption rate with two Claude Code CLI instances
- [Bug] claude.ai and Claude Code show different usage data for the same account
- [BUG] Claude CLI -p Parameter Ignores Max Subscription
- [BUG]b"Usage limit reached" triggered after weekly usage jumped from ~35% to blocked in ~12 minutes
- Auto-compaction: two compounding cost bugs — stale precompute keeps ~200k tokens verbatim, and that prefix is repeatedly cache-created instead of cache-read
- [BUG] /ultrareview crashes before producing findings, but consumes quota
- [BUG] Claude Code Opus 4.6 has become extremely dumb and expensive for serious programming tasks
- [Bug] Session quota consumed without user action
- [Bug] 1M context window incorrectly shown as extra billable usage on Max plan
- [Bug] Rate limit consumption exceeds expected rate on 20x max plan
- [Bug] Subagent Skills Leak into Main Context After Compaction - extremely costly bug that breaks everything
- [BUG] MCPSearch not activating despite meeting 10% threshold (40k/200k tokens, 20%)
- [BUG] Multiple duplicate warmup agents spawning causes idle token consumption
- API Error: 401 {"type":"error","error":{"type":"authenticati...
- [BUG] incorrect timezone name in limit usage message
- Critical Bug: Claude Code CLI is making excessive background API calls, ignoring model configuration, and console reporting inconsistencies
- [BUG] Weekly usage bumped from 60% to 95% in a few hours without any active sessions or me using Claude Code
- [Bug] Weekly usage limit unexpectedly increased without API calls
- [BUG] Usage credits required for 1M context" blocks all requests on Pro plan — first use of the day, quota available, Sonnet selected
- Workflow tool: one invocation spawned 46 Opus subagents (~3M tokens) with no cost confirmation
- [BUG] Weekly Sonnet limit non-functional — blocked despite 78% Sonnet quota remaining
- [Bug] Extreme token consumption in API requests
- [BUG] Context Limit reached, when only 27% is used
- [Bug] /usage command not displaying actual token usage data
- [BUG] v2.1.111 with Opus 4.7 consumes ~1.7–2x more context tokens than v2.1.110 on a fresh session
- You've hit your limit · resets 7pm (Europe/Berlin)
- Session resume (--continue) invalidates entire prompt cache, causes massive rate limit consumption
- Max plan (/mo) runs out of quota before completing single feature — GPT-4.5 at finishes same task
- [Bug] Usage percentage mismatch between Claude Code CLI and website dashboard
- Sessions spanning 5-hour rate-limit windows cause inflated usage attribution at window start
- [Bug] Unexpected Weekly Usage Limit Exceeded Without High Activity
- Claude Code used my API key instead of my Max plan
- [Bug] Rate limits reached prematurely with 5x max plan tier
- [BUG] Abnormal session consumption on Max 5x plan — 17% usage drop on single small prompt, support tickets closed without human response
- [Bug] Excessive token consumption on single document read
- [BUG] 16% of 5-hour usage limit consumed by simple investigation prompt.
- Resume of long sessions loads disproportionate tokens from opaque thinking signatures
- [BUG] Token burn is increasingly high since Opus 4.6
- VSCode extension consumes excessive tokens in background
- [BUG] First observed Dec 10, ur bot is chewing up tokens at >2x the rate of previous days, and I use it daily
- [BUG] Usage Limit major leap to 17 from 4 hours gap!
- [Bug] Anthropic API: Rapid Usage Limit Exhaustion with Claude Opus
- [Feature Request] Session Token Tracking and Usage Limit Expansion for Claude Code
- Credit balance is too low
- [Feature Request] Increase weekly session limits for Max plan users
- [BUG] Weekly usage limit not updated after upgrade from Pro to Max 20x — account still behaves as Pro/5x
- Billing: /ultrareview consumed 2 free runs on server-side rate-limit error
- [Regression] Opus 4.7 delivers worse quality at higher token cost vs 4.6 for production coding workloads
- [BUG] /usage weekly usage bar missing — only daily bar renders
- [BUG] [AGENT_TEAMS] Parallel Agent dispatch: 90min stall silently burns ~15M cache_read tokens, resets subagent context
- [Bug] Excessive context consumption on initial Opus startup (5% of pro plan limit)
- [BUG] Paid usage on max20 - limit reached within one command... WTF?!
- Usage Limit Reset Inconsistency with Documented 5-Hour Interval