Cost and usage issues on VS Code
Issues the maintainers labelled both platform:vscode and area:cost.
203 issues · 40 open · 163 resolved (80%) · first seen Feb 26, 2026
Is this getting better or worse?
This class of problem is converging. 80 new reports in the last 90 days vs 118 in the 90 before — -32%. The open backlog peaked at 65 in 2026-04 and sits at 40 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
155 of these reports name the Claude Code build they were running, spanning 81 releases. Heaviest reporters:
- Claude Code v2.1.123
- Claude Code v2.1.92
- Claude Code v2.1.87
- Claude Code v2.1.104
- Claude Code v2.1.158
- Claude Code v2.1.126
- Claude Code v2.1.121
- Claude Code v2.1.119
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 35 days across 163 closures. Of the 163 closures with a recorded reason, 9% were closed as completed and 148 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
19 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Abnormal rate limit consumption — 1-2 prompts exhausting 5-hour window
- 1-2 prompts exhausting the limit sounds like the cache creation bug others have reported in 38350. The token accounting seems broken. While waiting for a fix, multi-model routing h
Found in the thread of #38345 · 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 - Max plan: usage exhausted abnormally fast, twice in one day (March 31)
- …o dropped to 4.3% (effectively ~20x token inflation). After workarounds it recovered to 89–99% . Full analysis + workarounds: Important caveat: All my testing was done in the CLI environment ( in terminal, Linux). Since…
Found in the thread of #41504 · still open - [BUG] Usage credits required for 1M context - Pro plan blocked despite 17% usage
- …ses, making --model flag and CLAUDE CODE DISABLE 1M CONTEXT workarounds ineffective. Versions tested: 2.1.104 (WinGet), 2.1.6 (npm), 2.0.0 (npm) — all produce the same error. To use Claude Code at all, I was forced to pu…
Found in the description of #65514 · still open - 93% rate limit consumed in ~3 minutes on fresh session (Max plan, v2.1.85)
- ….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 #39938 · 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).
- [BUG] Abnormal rate limit consumption — 1-2 prompts exhausting 5-hour window
- Claude Code changed default model to 1M context without notifying Pro users
- Max plan: usage exhausted abnormally fast, twice in one day (March 31)
- [BUG] VS Code extension blocks Fable 5 with "requires usage credits" while account has 20% of weekly Fable allowance remaining (Max plan)
- [Bug] Fable 5 incorrectly requires usage credits on Max 20x plan despite available weekly allowance
- [BUG] Usage credits required for 1M context - Pro plan blocked despite 17% usage
- You've hit your limit · resets 11am (America/Chicago)
- 93% rate limit consumed in ~3 minutes on fresh session (Max plan, v2.1.85)
- [Bug] Weekly usage limit reset occurring before scheduled reset time & new week ends in 5 days, not 7 days
- [BUG] Critical: Token consumption is 100x faster after v2.1.88 leak.
- [BUG] Weekly Limit Jumped From ~50% to 100% in less than an hour of usage on Max20x Plan
- Doing useless tool call wasting token
- Claude Code VS Code extension forces 1M context on Pro plan - Windows
- 🐛 [Bug] Credits drained continuously after closing Claude Code session — $39.07 lost overnight with auto-reload DISABLED
- [BUG] Rapid quota consumption in Claude Code with Opus 4.7 1M context — minutes-scale 90%+ burn from few prompts
- [BUG] Session randomly dies with "API Error: Rate limit reached" despite near-zero usage
- [BUG] MAX100 subscription - abnormal quota consumption and rate_limit_error with multi-session Claude Code
- [BUG] A user can do absolutely no coding and still use up all tokens in a session. Big fail.
- [Bug] Unexpected high usage consumption on Claude Max plan (using claude code)
- [Bug] Extended thinking hangs indefinitely, consuming all tokens without returning results
- [Bug] Prompt Caching Not Working - Rapid Token Usage Depletion
- [Critical] Background agents cannot be stopped, Claude lies about stopping, massive token waste (~1.4M tokens), inconsistent statements
- [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] Extreme token consumption in API requests
- [Bug] Excessive API usage consumption and degraded response performance
- [BUG] Repeated "image could not be processed" errors consumed ~60% of usage limit — 19 consecutive failures, each resending full 34MB context
- [BUG] Token limit drained in seconds due to repeated image processing error retries
- [Regression] Opus 4.7 delivers worse quality at higher token cost vs 4.6 for production coding workloads
- You've hit your limit · resets 2pm (America/Chicago)
- [BUG] API Error: Extra usage is required for 1M context · enable extra usage at claude.ai/settings/usage, or use --model to switch to standard context
- [BUG] VSCode extension model picker only offers 1M context variants — no way to select standard 200k
- Claude Code (VS Code extension) prompts for usage credits on Fable 5 despite Max plan showing full entitlement
- [BUG] VS Code extension resumes huge sessions without warning and rapidly exhausts Max usage
- Unexpected 5-hour limit consumption in Claude Code
- [Bug] Anthropic API Error: Usage credits required for 1M context window
- [BUG] VSCode extension forces 1M context on Sonnet 4.6 for Pro users with no way to opt out**
- [Bug] Prompt cache invalidation causing excessive token consumption on minor edits
- [BUG] New version burns through all tokens in minutes, doesn't allow Opus 4.6 use, doesn't allow downgrade.
- session usage jumped 30% per prompt in less then 1 minute of entering the prompt
- You've hit your limit · resets 9:10pm (Europe/Kiev)
- [Bug] Unexpected high token consumption rate
- [BUG] Claude Code over-consumes context by not delegating bulky operations to subagents
- You've hit your limit · resets 1am (Asia/Makassar)
- Cost estimation blind spots when building agent systems with Claude Code
- Extra usage being charged for Opus 4.6 1M on Max plan when session/weekly limits well <60%
- You've hit your limit · resets 11pm (America/Denver)
- [Bug] Sub-agents stuck in infinite loops consuming excessive tokens
- Unprocessable image in context burns credits with no recovery path
- [BUG] Workflow harness retries indefinitely on HTTP 429 rate_limit — 97 agents, 2M tokens burned in 34 seconds ()
- [Bug] Unexpected High Token Consumption Across Sessions
- [Bug] Unexpected high token consumption with non-Claude subagents and orchestrator models
- [Bug] Unexpected high token consumption with multi-agent Opus orchestrator spawning Sonnet agents
- [Bug] Claude Code 4.7 High Token Usage and Context Limitations
- [BUG] Claude Code extension causing abnormal background requests leading to rapid rate limit exhaustion
- Display API usage/rate limit status in VSCode UI
- [Bug] Credit usage calculation shows inaccurate percentage on Max plan
- [BUG] Prompt cache invalidated by rewrites of messages in long sessions
- [BUG] 5 hour usage limit reached - but I have not used Claude in over a day
- [Bug] API Error: Usage credits required for 1M context with standard model selected
- usage error on claude
- [BUG] Claude Code in VS Code consumes ~2x more weekly limit after May 6, 2026 changes
- [Bug] Anthropic API Error: Extra usage required despite MAX Plan subscription
- [Bug] Session limit reached prematurely at 47% usage despite 53% remaining quota
- Claude stuck, 40% of my token wasted but it did nothing. SOMETHING WRONG HERE.
- [BUG] Session limit reached far ahead of time compared to entire month of March.
- [BUG] Excessive unproductive use of credits on simple question
- [BUG] Image tool results can't be persisted, so budget eviction replaces them with a sentinel mid-history and invalidates the prompt cache
- [Bug] Excessive agent spawning causes token bloat for simple code analysis tasks
- [Bug] Security-guidance plugin bypasses subscription billing and uses expensive model without warning
- [BUG] Contradictory rate-limit messages shown together: server rate-limit error vs usage-limit banner
- VS Code Claude extension API usage limit reached
- [Bug] Infinite thinking loop consuming all tokens without tool execution
- [Bug] Session starts with unexplained high token usage (31% consumed on first message)
- [BUG] Deceptive usage metrics for Claude Pro in VSCode
- [BUG] Token counter under stats very off kilter input token 1/10th of output tokens, seems backwards
- Bug: Rate limit triggered despite 0% usage in /usage
- [BUG] Command /usage does not recognize subscription
- PDF documents silently inflate context past long-context threshold, causing unrecoverable 'Rate limit reached' with no actionable error
- [BUG] Loading a tool for the first time mid-session (e.g. skill, MCP, tool-search) invalidates cache
- You've hit your session limit · resets 3:30pm (Asia/Almaty)
- You've hit your session limit within one prompt on sonnet 4.6
- [BUG] This is frustating to get usage limit issue because of Anthropic capacity limitation
- [BUG] [BUG] Claude Code VS Code Extension v2.1.161 Forces 1M Context on Pro Plan Without Request — Blocks All Usage on macOS
- [BUG] Claude Code v2.1.160 forces 1M context on Windows VS Code, blocks session continuation after error
- [BUG] All tokens and the limit are spent in a couple of seconds
- [BUG] Max user, Claude unusable 3x issues - 1. 1M context error 2. repeated auto compaction after 1/2 messages 3. Single word prompt "too long"
- [BUG] Extra usage fully consumed despite dashboard showing 43% remaining — Claude Code for VS Code
- You've hit your limit · resets 1:40pm (America/Sao_Paulo)
- After compaction and subagent return, Main agent set's itself from Sonnet 4.6 to Opus 4.7 without user interaction
- [Bug] Excessive API calls causing unexpected billing on failed requests
- Usage allowance shared across two separate Anthropic accounts in parallel VS Code Claude Code sessions
- [BUG] 5-hour session quota is misleading — actual limit is token-based, not time-based
- [Bug] Unexpected increase in API token consumption rate
- [BUG] Idle time is included in session time
- [BUG] Account suspension triggered by abnormal usage likely caused by Claude Code extension background activity
- [Bug] Rapid API usage depletion in Claude Code CLI
- [BUG] /usage command incorrectly shows 'only available for subscription plans' for Pro subscribers #16646
- [BUG] - Endless loop and excessive tool calls by sub agents contributing to massive spike in token consumption (Max plan user)
- [BUG]