Cost and usage issues on VS Code — page 3
Issues the maintainers labelled both platform:vscode and area:cost.
248 issues · 59 open · 189 resolved (76%) · first seen Feb 26, 2026
Is this getting better or worse?
This class of problem is converging. 70 new reports in the last 90 days vs 124 in the 90 before — -44%. The open backlog peaked at 65 in 2026-04 and sits at 59 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
193 of these reports name the Claude Code build they were running, spanning 101 releases. Heaviest reporters:
- Claude Code v2.1.123
- Claude Code v2.1.92
- Claude Code v2.1.87
- Claude Code v2.1.158
- Claude Code v2.1.59
- Claude Code v2.1.263
- Claude Code v2.1.104
- Claude Code v2.1.270
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 189 closures. Of the 189 closures with a recorded reason, 8% were closed as completed and 174 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
21 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 201–248
Ranked by community engagement (reactions weighted over comments).
- Model selector reverts to Sonnet after "Fable 5 requires usage credits" dialog, despite Max plan including Fable 5 and `/model` reporting success
- [Bug] Team Plan 50% Weekly Limit Promotion Not Applied to Account
- Closed by author
- [BUG] Session (5hr) usage limit not decrementing after idle period
- [Bug] Inconsistent Fable subscription end dates between Claude Code and Claude App
- [withdrawn]
- (withdrawn)
- [BUG] Too faxt usage
- You've hit your session limit · resets 8pm (America/Mexico_City)
- You've hit your session limit · resets 4:30pm (Africa/Nairobi)
- You've hit your session limit · resets 2pm (Europe/Budapest)
- [Bug] Session timeout occurring prematurely within minutes of activity
- [Bug] Prompt caching not functioning correctly, causing excessive token consumption
- Setting that enables always showing weekly usage limit in the status bar
- [BUG] Five-hour session quota immediately shows 100% at reset across VS Code and mobile
- [Bug] Excessive review loop iterations without scope limitation or early simplification recommendation
- [Feature Request] Built-in plugin missing from /plugin list and /usage cost tracking
- [Bug] Separate weekly limit not charged independently, deducts from main limit instead
- Credit balance is too low
- [BUG] using cloud session credit
- [BUG] Fork subagent transcript duplicates the parent's last response (same requestId and usage), so per-file usage counts it twice
- [Bug] Child agents continue running after parent agent termination, causing excessive token consumption
- You've hit your session limit · resets 3:10pm (Asia/Makassar)
- [Bug] Insufficient token allocation after upgrading from Claude Max x5 to x20
- [BUG] incorrect usage credit limit used in VSCode - blocking work
- Model pads delegated subagent prompts with unrequested work, wasting tokens despite explicit memory rules
- 🐛 [Bug] Archived API key continued charging $20.86 after deletion — CSV proof attached (#29108, #53292)
- [Bug] Excessive token consumption due to model hallucinations and unreliable code generation
- [Feature Request] Usage limits and rate limiting communication
- VS Code extension: a single prompt submission was dispatched into 3 separate sessions (duplicated token usage)
- [Bug] Unexpected high token consumption with delegated sub-agents in Fable
- You've hit your session limit · resets 4:20am (Europe/Rome)
- [BUG] Prompt cache expires during active session, causing massive token spikes on next prompt
- [Bug] Conversation restart requires excessive token reuse after API-forced session termination
- You've hit your monthly spend limit - EXCEPT IT IS NOT MONTHLY IT IS DAILY - I did NOT agree to this
- [Bug] Session-based usage limits not disclosed in service terms
- [Bug] Fable 5.1 incorrectly blocked by usage credits prompt on Claude Max plan
- [Feature Request] Optimize token usage for simple code changes with well-documented context
- You've hit your monthly spend limit ·
- monthly spend limit
- are you kidding...
- [BUG] Usage limit discrepancy between claude.ai web and VS Code extension (5-hour session window) — still occurring, related to #9156
- [BUG] Max 20x: one full 5-hour session consumes ~20% of the weekly limit — about 5 sessions per week
- [BUG] "an image in the conversation could not be processed and was removed" is NOT removed from the transcript - poisons the prompt cache, every later turn billed as cache-creation (~12x), drains a session in ~3 turns [root cause + fix identified]
- Repeated injection of content-policy reminder text unrelated to conversation context (wasting tokens)
- You've hit your session limit · resets 5:50am (Asia/Seoul)
- You've hit your session limit · resets 9:10pm (Asia/Calcutta)
- [BUG] Different usage for the same task in CC vscode extension & CC Desktop (linux beta)