Cost and usage issues on Windows
Issues the maintainers labelled both platform:windows and area:cost.
415 issues · 90 open · 325 resolved (78%) · first seen Jul 26, 2025
Is this getting better or worse?
This class of problem is converging. 133 new reports in the last 90 days vs 225 in the 90 before — -41%. The open backlog peaked at 125 in 2026-04 and sits at 90 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
264 of these reports name the Claude Code build they were running, spanning 110 releases. Heaviest reporters:
- Claude Code v2.1.126
- Claude Code v2.1.87
- Claude Code v2.1.119
- Claude Code v2.1.123
- Claude Code v2.1.114
- Claude Code v2.1.81
- Claude Code v2.1.247
- Claude Code v2.1.104
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 325 closures. Of the 325 closures with a recorded reason, 12% were closed as completed and 286 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
50 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Extremely rapid token consumption. There appears to be a critical issue with token calculation and quota management. Users, including myself, are experiencing an unusually high rate of token consumption
- ….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 #38239 · still open - [BUG] Error: Error during compaction: API Error: Usage credits required for 1M context · turn on usage credits at claude.ai/settings/usage, or use --model to switch to standard context
- …runs /clear. This is a new behavior as of a day or so ago. Workaround Running /clear restores the session. The error message suggests using --model to switch to standard context, but this requires hardcoding a model nam…
Found in the description of #63896 · still open - Claude Code changed default model to 1M context without notifying Pro users
- …overnight. I lost hours trying to debug the issue, applying workarounds (environment variables, settings.json), and ultimately had to downgrade to a smaller context model — losing functionality I was already using and pa…
Found in the description of #62199 · still open - Add --max-context flag to cap context window usage
- …access to current context token count, so can't build this as a workaround Environment - Claude Code on Windows (MSYS2/Git Bash) - Opus 4.6 with 1M context - Previously worked well with 200K limit
Found in the description of #34650 · resolved - Opus 1M context on Max plan requires extra usage despite docs saying 'included with subscription'
- …t yesterday. Upgraded from Max 5x → Max 20x today to try to work around this. Still rate-limited at 0% usage. Total spend now exceeds £300 across plan upgrades and erroneous extra-usage charges. /bug report submitted — F…
Found in the thread of #39841 · 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 415 matches; the statistics above cover all 415.
- [BUG] Extremely rapid token consumption. There appears to be a critical issue with token calculation and quota management. Users, including myself, are experiencing an unusually high rate of token consumption
- [BUG] Usage explosion
- [BUG] Hitting much faster usage limits than before
- [BUG] Error: Error during compaction: API Error: Usage credits required for 1M context · turn on usage credits at claude.ai/settings/usage, or use --model to switch to standard context
- Claude Code changed default model to 1M context without notifying Pro users
- Add --max-context flag to cap context window usage
- [BUG] Weekly Usage Limits Making Claude Subscriptions Unusable - This IS a bug.
- [BUG] Weekly usage jumps +2% in ~5 minutes; /settings/usage shows “Missing permissions” banner
- [BUG] Silent billing change in v2.1.51: 1M context moved to extra-usage-only without notice — JSONL data proves identical workload billed differently
- [Bug] Rate Limit Error persists after increasing plan limits and adding funds and Max plan only at 33% used
- [Bug] Anthropic API Error: credit_balance_too_low despite sufficient account credits
- [BUG] Sonnet model consuming both "All models" AND "Somente Sonnet" limits
- Opus 1M context on Max plan requires extra usage despite docs saying 'included with subscription'
- [BUG] VS Code extension blocks Fable 5 with "requires usage credits" while account has 20% of weekly Fable allowance remaining (Max plan)
- [BUG] /usage command fails with rate_limit_error when checking usage data
- [Bug] Fable 5 incorrectly requires usage credits on Max 20x plan despite available weekly allowance
- Usage limit reached repeatedly without active use — Pro plan
- [BUG] Claude Code shows 'Usage limit reached' despite session at 2% and weekly at 32%
- [BUG] Usage credits required for 1M context - Pro plan blocked despite 17% usage
- [BUG] 5h token usage massivly outstripping actual context (issue started about 8:45pm BST)
- Claude Max + Claude Code rate limits exhausting abnormally fast / possible metering bug
- 93% rate limit consumed in ~3 minutes on fresh session (Max plan, v2.1.85)
- Opus 4.6 (Max $100) — Quota reaches 93% after minimal prompting in a single session
- [BUG] Critical: Token consumption is 100x faster after v2.1.88 leak.
- [BUG] Claude Code usage limit hit after 7 minutes on new session
- Opus 4.7 regression vs 4.6: ~2x token burn, mid-session stalls, no quality gain
- [BUG] Excessive token usage (~20k–30k tokens) for trivial prompts in Claude Code CLI
- [BUG] claude limit reached in less than one hour on opus 4.1, windows, v2.0.1
- [BUG] Usage Spike
- Misleading "Usage limit reached" error when selecting Sonnet — actually a 1M context tier gate
- [BUG] Unexpected token usage spike and continued consumption while Claude Code is inactive
- [BUG] Single README.md edit burns entire 5-hour Max 5x window in 9m 39s (Opus 4.7 1M, resumed session, v2.1.126, JetBrains, Windows)
- [BUG] TodoWrite re-stamps a front-of-context block on every update, invalidating the entire prompt cache (full ~900k-token rewrite per todo update)
- Claude Code VS Code extension forces 1M context on Pro plan - Windows
- System prompt size grew ~70K tokens between v2.1.89 and v2.1.96, making sessions unusable without frequent manual /compact
- 🐛 [Bug] Credits drained continuously after closing Claude Code session — $39.07 lost overnight with auto-reload DISABLED
- [CRITICAL BUG] Claude Code Web: Archived sessions reappear as ACTIVE RUNNING sessions, potentially consuming tokens
- [BUG] Claude Code uses entire 5 hour token limit in one prompt with zero feedbacks or results
- [BUG] MAX100 subscription - abnormal quota consumption and rate_limit_error with multi-session Claude Code
- [BUG] Regression v2.1.74: ~3% quota consumed per 20k token session — Max20 plan
- [BUG] Max 20x plan — Claude Code reports 100% usage while dashboard shows 73%, charged $53 in extra usage
- [BUG] Typing /context adds 2000 tokens to the context
- [BUG] Autocompacting Loop Causing Massive Token Usage Spikes OCT 15 2025
- Bug: Desktop app shows "Usage Limit Reached" incorrectly
- [BUG] Rate Limit Reached without typing anything, and /insights causes insane token usage
- [Bug] Usage credits required for 1M context on Max 5x plan — standard model selected, Cowork + Claude Code
- [BUG] Max 20x plan ($200/mo) — quota exhausted in ~1h, making the product unusable for our team
- [BUG] Usage limit discrepancy: Claude Code blocked at 100% while claude.ai shows 73% on the same account
- [Critical] Background agents cannot be stopped, Claude lies about stopping, massive token waste (~1.4M tokens), inconsistent statements
- [BUG] Is the weekly quota for the Pro version only 20 hours?
- [BUG] Not even doing real work and we're at 40% Fix the rate limits (Max x5)
- [BUG] Parabolic Usage Spike June 20, 2026 7pm PT
- [BUG] Historical user-message content drift invalidates prompt cache prefix (trailing \n on </system-reminder>)
- [Bug] Unexpected increase in token consumption rate
- [Bug] Rapid token usage spikes with Opus model in Claude Code sessions
- [Bug] Excessive API usage consumption and degraded response performance
- [BUG] Claude Code usage increases immediately upon launch without user input
- [MODEL] Fable 5 Ultracode spawns excessive parallel agents for single refactoring task
- [BUG] Repeated "image could not be processed" errors consumed ~60% of usage limit — 19 consecutive failures, each resending full 34MB context
- Skill invocation fails with '1M context extra usage required' even when already on 1M model
- [BUG] Extra usage enabled but Claude Code is fully locked (no input box) after weekly limit
- [BUG] Token limit drained in seconds due to repeated image processing error retries
- [BUG] Paying $200 a month to watch you guys reduce what I get For that $200 EVERY SINGLE UPDATE
- [BUG] Credit balance being deducted despite "Extra Usage" disabled
- You've hit your limit · resets 2pm (America/Chicago)
- [BUG] Unable to cancel subscription
- [BUG] Unauthorised launch of extremely inefficient subagents that wasted tokens - I want a refund
- Opus 4.8 burns 5h limit in ~30min on operational work; no signal to downgrade to Sonnet
- [BUG] Rate limit error (429) triggers unexpected plan usage consumption in Claude Code (Windows)
- BUG: Max 20x subscription ignored - Claude Code ONLY bills to Extra Usage
- Max Plan subscribers billed through API key when subagents dispatch - $152 unexpected charges
- [BUG] Opus weekly limit reached within 5 hours.
- Claude Code (VS Code extension) prompts for usage credits on Fable 5 despite Max plan showing full entitlement
- Model switched to Opus without consent or disclosure — five process failures, seven cost amplifiers, $1,050 overcharge on May 5-7
- [Max 20x] Weekly limits counter resets on a ~24-hour cycle instead of the documented 7-day cycle
- [BUG] New version burns through all tokens in minutes, doesn't allow Opus 4.6 use, doesn't allow downgrade.
- [Bug] Daily usage limit reduced prematurely before reset period
- [BUG] Persistent 5-hour reset loop / 100% usage exhaustion with zero activity
- [BUG] Sonnet 4.6 blocked by forced 1M context mode requiring additional credits on Pro plan
- session usage jumped 30% per prompt in less then 1 minute of entering the prompt
- [BUG] Weekly quota consumption is disproportionately higher than 5-hour session usage
- You've hit your limit · resets 9:10pm (Europe/Kiev)
- [BUG] Prompt cache expires during active session, causing massive token spikes on next prompt
- [BUG] Claude Code over-consumes context by not delegating bulky operations to subagents
- [Bug] Prompt Cache causes excessive token consumption (10-20x inflation)
- [BUG] Critical Bug: Claude Code Spontaneously Executes Commands and Repeats Responses in Infinite Loop
- [BUG] v2.1.19: Unable to consume "Extra Usage" credits despite active balance | Unknown skill: rate-limit-options
- [BUG] 5-hour limit breaks Claude Code in many ways
- 5-hour limit reached ∙ but only worked for 2 hours!
- [Bug] Fable model inaccessible despite included in max plan and available usage credits
- Error: 'usage credits required for 1M context' when session grows long on non-1M model
- [BUG] Pro plan — 1M context error blocks all requests
- Session cut mid-task by credit limit — no warning, context lost, costly model switch
- [BUG] /context command output appends to conversation history, causing immediate context inflation (~5k+ tokens)
- [BUG] LIMIT calculation is broken - Weekly Limit reached, resetted 10pm -> 11pm weekly reached again
- [BUG] Billing between claude.ai and claud code is confusing.
- [Bug] Session token limit appears too restrictive for extended coding workflows
- [BUG] Rate limit blocks all commands including /status after upgrading to Max plan
- VSCode Extension: File modification reminders consume excessive context
- [Bug] Excessive token consumption in multi-turn conversations causing premature rate limit exhaustion