Cost and usage issues on Linux
Issues the maintainers labelled both platform:linux and area:cost.
341 issues · 75 open · 266 resolved (78%) · first seen May 8, 2025
Is this getting better or worse?
This class of problem is holding steady. 95 new reports in the last 90 days vs 124 in the 90 before — -23%. The open backlog peaked at 75 in 2026-10 and sits at 75 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
268 of these reports name the Claude Code build they were running, spanning 138 releases. Heaviest reporters:
- Claude Code v2.1.280
- Claude Code v2.1.119
- Claude Code v2.1.207
- Claude Code v2.1.126
- Claude Code v2.1.87
- Claude Code v2.1.92
- Claude Code v2.1.150
- Claude Code v2.1.123
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 266 closures. Of the 266 closures with a recorded reason, 19% were closed as completed and 216 as not-planned or duplicate. The most recent completed fix landed in 2026-10.
Workarounds reported by the community
43 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Conversation history invalidated on subsequent turns
- …put tokens, which can cause a massive spike in token usage. Workarounds to minimize cache invalidation: 1. Keep conversations shorter : Start new sessions for new tasks rather than continuing a single long session. Short…
Found in the thread of #40524 · resolved - CC v2.1.100+ inflates cache_creation by ~20K tokens vs v2.1.98 — same payload, server-side
- …r potentially degraded output, with no visibility into why. Workaround Downgrade to v2.1.98 or earlier. Check for available binaries, or use . Note: Auto-updates may overwrite older versions. v2.1.98 is no longer retaine…
Found in the description of #46917 · still open - [Bug] Excessive token usage in Claude Code 2.1.1 - 4x+ faster rate consumption than previous versions
- …-- but until that ships, parsing your own logs is the best workaround.
Found in the thread of #16856 · still open - [BUG] Prompt cache regression in --print --resume since v2.1.69(?): cache_read never grows, ~20x cost increase
- …advertently broken cache breakpoint placement for sessions. Workaround Pinned to v2.1.68 ( ). What Should Happen? Expected behavior (v2.1.68) grows as conversation accumulates, drops to a small delta (~800 tokens): Actua…
Found in the description of #34629 · resolved - Max Plan: Token usage increased ~3-5x without any configuration change (since ~March 28-29)
- ….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 #41506 · still open
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 341 matches; the statistics above cover all 341.
- [BUG] Conversation history invalidated on subsequent turns
- CC v2.1.100+ inflates cache_creation by ~20K tokens vs v2.1.98 — same payload, server-side
- [Bug] Excessive token usage in Claude Code 2.1.1 - 4x+ faster rate consumption than previous versions
- [BUG] Prompt cache regression in --print --resume since v2.1.69(?): cache_read never grows, ~20x cost increase
- Max Plan: Token usage increased ~3-5x without any configuration change (since ~March 28-29)
- Subscription usage jumping to 80% within minutes of reset
- [Bug] Anthropic API Error: Usage credits required for 1M context window with opus-plan model
- Excessive token consumption after recent updates (Max plan)
- Plugin skills don't support `disable-model-invocation` like user skills do
- [BUG] Inconsistent and Undisclosed Quota Accounting Changes in Claude Max Plan. Legal liability claim ready.
- [BUG] Bug: Extra Usage charged despite available plan capacity + false rate limit errors in Claude Code
- [BUG] /usage shows 47% weekly used in 3 hours of Opus. Max plan.. should be 40 hours per week
- [BUG] Sonnet 4.6 blocked by false "usage credits required" error
- [BUG] Claude Code (Pro) session limit reached after 20 minutes
- [BUG] Spurious Usage Spikes and 100% Weekly Limit Lockout After Plan Upgrade
- [Bug] Team Billing: Frequent Unexpected Usage Limit Resets
- Anthropic API: Unexpected Reduction in Claude Code MAX Plan Usage Limits
- [Bug] OPUS 4.7 IS DOWNGRADED JOKE
- [Bug] Inconsistent usage percentage display between /usage page and CLI
- [BUG] [Critical] Claude Code Quality Degradation - Ignoring Instructions, Excessive Token Usage
- [BUG] Claude Code uses API billing despite forceLoginMethod: claudeai setting
- [BUG] Task tool `model` parameter returns 404 - Blocks cost-optimized workflows (10-30x unnecessary spending)
- [Bug] Anthropic API Error: Usage credits required mid-session
- [Bug] Unexpected high token usage consumption on Claude Code Pro with Opus 4.6
- [Bug] Environment Variable CLAUDE_CODE_MAX_OUTPUT_TOKENS Not Respected
- Doing useless tool call wasting token
- [BUG] Max (20x) weekly limit depletes disproportionately — 51% mid-week, ~17% within minutes of session reset
- [BUG] Headless `claude -p` (entrypoint `sdk-cli`) uses ~1.8× more of the 5-hour window per token than interactive `cli`, same workload
- [Bug] /compact fails with "Usage credits required for 1M context" even after /model set to Sonnet 4.6
- [BUG] Not able to use extra usage
- [BUG] new sessions will **never** hit a (full)cache
- [BUG] Incorrect 5-h and weekly usage being recorded
- Fable 5.1 unreachable in Claude Code despite unused plan-included Fable allocation; credit-block dialog shows "not included in plan" copy with no affirmative action
- Expose `cache_control.ttl` (5m / 1h) as a user-configurable setting
- [Bug] Excessive token consumption spike since March 23rd
- [BUG] Usage is consumed just by opening Claude Code without sending any prompt
- Background sidechain agents consuming tokens without returning results
- [Bug] Excessive token consumption on Max plan - 15% rate limit after minimal usage
- Token counting ~2x inflated in 2.1.7 vs 2.1.2
- [BUG] Read tool falsely reports "file was modified" on large files, causing massive wasteful system reminders
- Claude AI usage limit reached|1748268000
- Max 20x plan drained in ~22 hours after Fable 5.1; 5.1 emits 2x the output per turn of Fable 5
- [BUG] Fable 5.1 burns tokens faster than 5.0 100% of limit in 20 mins.
- [Bug] Auto-compact triggers far below 1M window on Opus 4.7 [1M] — severe token burn regression on Max 5x (post-2.1.116)
- Phantom ~22K tokens per session on one account vs another — same machine, same project
- [BUG] 5 hour limit reached randomly, earlier and earlier
- You've hit your weekly limit · resets 8pm (America/Vancouver)
- [BUG] Streaming output tokens are incomplete in session.jsonl compared to /cost
- [BUG] 2.1.63 silently defaults to 1M context model without UI indication, causing excessive usage consumption and a BILLING issue.
- [BUG] Verified Evidence: Claude Code Delivers 10% of Requested Thinking Budget While Charging Full Price
- [BUG] Artifact tool loads ~12k tokens of schema into every claude.ai-backed session, eagerly, with no way to opt out except a deny rule
- [BUG] /model → Fable 5 blocks on usage credits, ignoring active promotional weekly allowance
- [BUG] I am getting out of usage error but already have tokens and limits API Error: 400 - Invalid Request You're out of extra usage. Add more usage credits at: https://claude.ai/settings/usage Then retry your request
- [BUG] How is this possible to be at 62% opus for a week when using for few hours with 5 code files - Max Plan 20x
- [Bug] Excessive Usage Depletion on Claude Pro/Enterprise Plans
- [BUG] Fable 5 [1m] prompts 'usage credits required' during active 1M promo window (Jul 17, promo extended to Jul 19)
- You've hit your session limit · resets 1pm (America/Los_Angeles)
- You've hit your limit · resets 1:40pm (America/New_York)
- [BUG] Agent team subagents do not honor 1-hour prompt cache TTL — main sessions show 100% 1h, every agent session shows 0% 1h
- claude -p with OAuth (no API key) bills as API usage, not Max subscription
- [FEATURE] Real-time Token Usage Indicator in CLI
- [Feature Request] Separate Token Tracking from Verbose Mode Logging
- claude_code_cost_usage_USD_total OTEL counter collides across parallel processes sharing the same session_id, producing oscillating values and inflating increase() queries by 100×+
- You've hit your limit · resets 11:20pm (Africa/Cairo)
- [Bug] Token usage limits exhausted prematurely in 5-hour sessions
- [Bug] Token consumption
- [BUG] Opus usage charged when using Haiku model
- OAuth expiration causes retry storm consuming 100% session usage (3.75M wasted tokens)
- [BUG] uncachable system prompt caused by includeGitInstructions / CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS -> `git status`
- [BUG] @agent-explore "Out of Credits" on $100 Max Plan
- Claude AI usage limit reached|1753113600
- [BUG] Irrecoverable Sessions if Toolcall canceled before completion
- [Removed by author]
- [BUG] VS Code extension resumes huge sessions without warning and rapidly exhausts Max usage
- [Bug] Anthropic API Error with skill model switch
- [BUG] VSCode extension forces 1M context on Sonnet 4.6 for Pro users with no way to opt out**
- [Bug] Weekly usage limit reset early, losing 36% of quota before scheduled reset time
- [Bug] Auto-Compact enters infinite loop causing excessive token consumption
- [BUG] Max x20 plan — 5-hour quota consumed in ~10 prompts (started March 14, 2026)
- [BUG] Session limit reached - reset time inconsistent with that shown on claude.ai
- [BUG] Grossly underreported input tokens count when running through Google Vertex AI, leading to actual cost 16x higher than reported in CLI
- [BUG] Resuming a fork forfeits its prompt cache: deterministic miss after any tool loop, fork 5m vs parent 1h TTL, full-context rewrites while the prefix is live
- [BUG] Silent model switch to Opus 4.7 [1M] mid-session caused ~4× quota burn
- Extended thinking generates duplicate .jsonl log entries with identical input tokens, causing ~2-3x token inflation in usage tracking
- Regression: increased per-turn token consumption vs previous versions
- [BUG] claude-code PLACEHOLDER IMPLIMENTATIONS, DESTROYS WORKING PIPELINES
- [Bug] Usage limits (weekly and session) depleting much faster than expected
- [BUG] Image Inputs via Read Tool or @ Reference Consume 7–10× More Tokens with On-Prem LLMs
- [Bug] Sub-agents stuck in infinite loops consuming excessive tokens
- [Bug] Parallel agent spawning causes excessive token consumption before crashing or hitting limits
- [Bug] Unexpected high token consumption rate
- [Bug] Excessive token consumption for simple requests
- [BUG] Max Plan 5x Phantom Consumption and Large Token Usage Increased Without Config Changes
- You've hit your limit · resets 4pm (Europe/Berlin)
- [Bug] Usage meter spike from 1% to 74% with concurrent Claude Code sessions
- [BUG] Claude 4 (or since its release) is BURNING USAGE LIMITS x10 TIMES FASTER
- [BUG] Resuming a background subagent misses its prompt cache: messages_changed, no thinking blocks
- [BUG] Unexpected session model tokens usage for opus
- [Perf/Cost] Tool catalog (~24k tokens) sent uncached on every API request — cache_control breakpoint missing
- [Bug Report] POWER USER PISSED OFF - CLAUDE IS BROKEN AND GETTING WORSE NOT BETTER - HELP PLEASE!