Rate limit errors — page 2
Issues 201–400 of the 3,738 matching this topic. The trend chart and topic overview are on page 1.
- [Bug] Weekly usage reset time displayed incorrectly for Pro plan users
- Desktop app: session history lost when switching accounts
- [Bug] Unexpected high token usage consumption on Claude Code Pro with Opus 4.6
- [BUG] Connection-level errors (ECONNRESET, EPIPE, ETIMEDOUT) are never retried — immediate failure with zero recovery
- [Bug] Rate limiting too aggressive: 5-hour daily limit hit repeatedly with minimal usage
- Sonnet model returns 'Rate limit reached' despite 0% usage
- Feature: Expose account usage/quota data to statusline
- [BUG] Claude Code Pro Quota Significantly Reduced: Limit Reached in ~20 Prompts per 5 Hours
- [BUG] Since mid-November, claude code is consuming ~5x tokens
- Claude Code login fails with service unavailability and rate limit errors
- [BUG] claude limit reached in less than one hour on opus 4.1, windows, v2.0.1
- [BUG] Missing API key · Run /login - Invalid API key · Please run /login
- Bug: Image API error triggers infinite loop, rapidly exhausting session tokens
- [Bug] SSE stream stalls in long-running sessions without message_stop event
- [BUG] Literal "HERMES.md" in git commit messages triggers 400 "out of extra usage" on Max OAuth (content filter false-positive misclassified as quota error)
- [BUG] Max (20x) weekly limit depletes disproportionately — 51% mid-week, ~17% within minutes of session reset
- Feature request: --wait-on-usage-limit flag for non-interactive / remote-control sessions
- Opus 4.6 on Max plan: usage seems disproportionately high per prompt
- [BUG] Opus 4.6 (1M context) model variant causes immediate "API Error: Rate limit reached" on Pro plan via /model selector
- Max plan Extra Usage charges during usage reporting outage — 1M context billing change undocumented
- Expose plan usage quota in statusLine JSON
- [BUG] Claude Code stating session limits hit and rejecting requests despite token quota being available
- 100% CPU usage while idle awaiting user input
- [BUG] Hundreds of lines of modified file notes being injected into context on EVERY user message via <system-reminder>
- [FEATURE] Add API usage quota information to statusline JSON data
- Misleading "Usage limit reached" error when selecting Sonnet — actually a 1M context tier gate
- [BUG] Usage limits gone crazy
- [BUG] API Error: Extra usage is required for 1M context when invoking skill with model: frontmatter from Opus 4.6 [1m] session on Max plan
- [BUG] CLI-only "API Error: Rate limit reached" on every request despite 97% quota remaining (Max 20x plan)
- [BUG] Max x20: CLI still shows Rate limit reached after weekly reset time passed
- OAuth refresh token not used when credentials are copied to remote/headless machines
- Add weekly and session usage percentages to status line JSON input
- [BUG] Version 2.0.61 is extremely slow and causes rapid, excessive token consumption/rate limits
- Weekly Limits Penalize Honest Paying Users
- [Bug] Anthropic API Weekly Usage Limits Unexpectedly Low
- /logout /login missing
- [BUG] Claude Desktop crashes when browser preview renders Cloudflare Turnstile — reproducible across multiple machines/GPUs, app becomes unlaunchable
- [FEATURE] Cowork: allow switching model mid-conversation (model is locked after the first message)
- Persistent HTTP 429 on auto-mode classifier (xml_s1), account-side config
- Bad System prompt effects
- [BUG] Client-side rate limiter blocks requests with zero API calls when conversation transcript is large (~74MB) — false rate_limit error with synthetic model and 0 input/output tokens
- Expose plan usage limits in statusline JSON input
- [BUG] Opus 4.7/4.8 token usage regressed 2-3x after update; Opus 4.8 also disconnects frequently
- [BUG]Weekly Limits Are Draining Much Faster After the 5-Hour Limit Update
- [BUG] Rate Limit Bug
- [BUG] Rate limit reached without any usage spent
- Usage limits hit significantly faster since v2.1.53–v2.1.59 (Feb 25–26) — auto-memory & system prompt bloat
- Unclear how 1M context billing works on Max subscription
- [Bug] Anthropic API Error: Rate limit reached despite low session usage on Max 20x plan
- Add rate limit information to statusline data
- [BUG] Claude usage limit reached. Your limit will reset at 3pm
- [BUG] CLAUDE HALLUCINATING AND LIES since 2 days
- Two separate claude accounts [Work, Personal] used for development on two different remote servers, use the same usage limit.
- [BUG] Exponential backoff is broken
- [Bug] Ultrareview quota consumed on server-side rate limit failures
- [BUG] Claude for Windows desktop app does not switch to extra usage when 5-hour limit is reached, while Claude Code CLI on the same account does
- [Feature Request] /buddy feature should not consume user token quota or provide compensatory credits
- [BUG] Cowork VM disk full on session start - ENOSPC blocks all Bash commands
- [Bug] Context limit reached without automatic compaction triggering
- [BUG] Chrome MCP screenshots accumulate in context, causing extreme token drain on session resume (17% of Max plan for 5 trivial turns)
- Expose rate limit utilization in statusLine JSON input
- [Bug] Anthropic API rate limit error in Xcode while other Claude clients unaffected
- [Bug] A new Claude code sessions already takes 80K token (40%)
- PRO account shows - Credit balance is too low
- [BUG] Max 20x upgrade not reflected in weekly limits — depleting at Max 5x rate or worse (upgraded July 16, 2026)
- [BUG] TodoWrite re-stamps a front-of-context block on every update, invalidating the entire prompt cache (full ~900k-token rewrite per todo update)
- [Bug] Claude Code token quota consumption increased significantly for Claude MAX subscribers
- [BUG] Incorrectly calculated usage limits
- [BUG] Usage limit reached in 10 minutes
- [Bug] Excessive token consumption on simple prompts
- [BUG] Max 20x: Usage meter climbing abnormally fast since ~March 23 — 1-2% per simple message exchange
- Usage Limit Tracking: Implement Precise Remaining Token/Request Quota Display
- claude code not working on Mac Os with Bedrock
- [BUG] Opus 4.8 medium effort spends 46k output tokens on hidden thinking for a simple coding turn
- Feature request: include thinking_tokens in API usage response
- [Bug] Excessive token consumption on Max plan - 15% rate limit after minimal usage
- Status line: show current effort/reasoning level
- [Feature Request] Add opt-in toggle for 1M context in Cowork — Max users lost access after feature flag rollback
- [BUG] API Error: Rate Limit when using claude code (vscode) on max plan
- [FEATURE] Usage limits display in VSCode extension / status bar
- feat: expose rate limit data in statusline JSON
- Internal /rate-limit-options command leaking into user history
- [BUG] Sudden Reduction of Max Plan Usage Limits – Without Prior Notice
- Claude AI usage limit reached|1748268000
- [BUG] Claude Max 20 subscription is being fully consumed without any usage
- [BUG] compact
- [Bug] Skill descriptions truncated due to context budget constraints
- [BUG] Claude Code uses entire 5 hour token limit in one prompt with zero feedbacks or results
- [BUG] Rapid quota consumption in Claude Code with Opus 4.7 1M context — minutes-scale 90%+ burn from few prompts
- [Bug] Auto-compact triggers far below 1M window on Opus 4.7 [1M] — severe token burn regression on Max 5x (post-2.1.116)
- [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
- Feature Request: Auto-pause when approaching usage limit to prevent work loss
- [Bug] Anthropic API Error: Out of extra usage despite remaining quota
- [BUG] CLI caches subscriptionType and rateLimitTier indefinitely — plan upgrades not reflected
- Max 20x ($200/mo) plan - session limits depleting abnormally fast
- You've hit your limit · resets 8pm (Europe/Berlin)
- [Bug] Unexpectedly High API Usage and Rate Limit Hits
- [BUG] Usage extremely high after 5-10 minutes into planning a feature
- [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] Regression v2.1.74: ~3% quota consumed per 20k token session — Max20 plan
- [Bug] Voice recording fails with native audio module load error
- [Bug] Anthropic API Error: Internal Server Error (500) with no retry mechanism
- Opus 4.6 1M context model unusable on Max plan - immediate rate limit error
- [FEATURE] Expose Plan Quota/Usage Data to StatusLine
- [Bug] Pro plan usage limits consuming excessive tokens for simple tasks
- [Bug] Edit tool corrupts Unicode typographic characters in non-ASCII text
- [BUG] 5 hour limit reached randomly, earlier and earlier
- Expose timeout settings
- I used $10.63 of Claude Code, and have set my account...
- [FEATURE] Token-burn circuit breaker: runtime-enforced spend caps with per-source attribution (hooks, plugins, subagents), not just warnings
- statusline: expose per-model weekly rate limits (Opus/Sonnet/Fable) to the status line command
- [BUG] "Buy credits" button permanently disabled - Free tier account incorrectly shows $500 limit, HTTP 429 errors on billing page
- False Usage Limit and Request blocked
- Bug: Desktop app shows "Usage Limit Reached" incorrectly
- [Feature Request] Expose API usage limits and rate-limit reset timer to Claude Code
- [FEATURE] Align weekly usage limit reset with billing cycle renewal
- [BUG] Claude Code Pro API Error: Rate limit reached on brand new Pro account with 0-2% usage
- [BUG] Rate Limit Reached without typing anything, and /insights causes insane token usage
- [Bug] Anthropic API: Extreme latency on Claude Code requests (15s+ to first token)
- [BUG] issue #33120 - API Error: Rate limit reached in Cowork and Code
- Expose rate-limit / plan quota data in statusline JSON stdin
- [FEATURE] Expose rate limit utilization data in status line JSON
- Restore session/weekly usage percentage display in /stats
- ToolSearch:optimistic polling loop causes 100% CPU usage
- [BUG] Getting "No task found with ID" from subagent
- [Bug] Incorrect Usage Limit Message for Claude Opus Model
- [Feature Request] Add scoped rate limit data to statusline input JSON payload
- [Feature Request] Keep Claude Fable 5 included in the Max plan after July 7 (not usage-credits-only)
- Bug Report: Uncontrolled Sub-Agent Recursive Loop Caused ~800k Token Consumption & $27.60 Unexpected Charge
- [Bug] Usage credits required for 1M context on Max 5x plan — standard model selected, Cowork + Claude Code
- Weekly limit depletes disproportionately to 5h-session limit on Max 20x — quantified telemetry shows ~5x drift vs historical baseline
- Graceful handling when hitting usage limits mid-session
- [BUG] Routines are not visible in sidebar
- [Bug] Unexpected high usage consumption on Claude Max plan (using claude code)
- Feature: Better session organization (folders/projects/tags) like Claude.ai
- API Error 500 (api_error) — multiple requests in a long Opus 4.6 session
- [BILLING] Medium effort default (effort=85) causing excessive token burn and unexpected extra usage costs
- Feature request: `claude usage` command / API endpoint for Max subscription limits
- [BUG] Max 20x plan ($200/mo) — quota exhausted in ~1h, making the product unusable for our team
- [BUG] I keep getting API Error: Rate limit reached - I am not even close to a rate limit.
- Expose usage/rate limit data via CLI flag or hook event
- Max plan usage limits reported as much lower than they should be
- [BUG] Claude Pro subscription purchased via iOS App Store not recognized by Claude Code (subscriptionType: null)
- [BUG] Usage limit discrepancy: Claude Code blocked at 100% while claude.ai shows 73% on the same account
- Claude Code usage discrepancy - shows 100% while web shows 71%
- [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
- [BUG] AWS Bedrock SSO federation login endpoint spamming until 429 error
- You've hit your session limit · resets 11:50am (Europe/Budapest)
- [Bug] One transient advisor failure permanently latches the tool off for the whole session; distinct error causes flattened to generic "unavailable"
- [BUG] /deep-research — default workflow frequently hits "API Error: Server is temporarily limiting requests"
- [BUG] Server-side rate limits break parallel agent workflows — request transparent auto-retry
- [BUG] Parallel Claude Code sessions started right after 5-hour limit resets — first 3–4 work, the rest fail with "Server is temporarily limiting requests (not your usage limit) · Rate limited"
- Feature: prompt before consuming extra usage credits on session limit
- Bug Report - Extreme usage limit drain on Max Plan with Claude Code (one prompt consumes huge amounts)
- [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
- New account immediately hits rate limit with zero usage
- [BUG] Max5 plan hitting session limits daily (including off-peak hours)
- [Bug] Rate limit errors with unexplained session quota consumption
- [BUG] "API Error: Rate limit reached" repeatedly despite having significant quota remaining.
- [BUG] API Error 500 on all prompts including /feedback command - Sonnet 4.5 and Opus 4.5
- [FEATURE] Expose session/weekly rate limits to statusline script JSON input
- [BUG] Rate Limit Message Infinite Loop
- [BUG] Multi-Account Usage Limits overlap - Deadlock in #3857 and #5001
- [URGENT] Increase weekly Sonnet rate limits by at least 50%
- [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
- 5-hour limit reached in less than 10 messages
- Claude AI usage limit prematurely reached
- Claude AI terminal scroll issue | 1754510400
- Limit reset should indicate timezone
- [BUG] /model → Fable 5 blocks on usage credits, ignoring active promotional weekly allowance
- [FEATURE] Claude Code on the web: allow read access to public GitHub repositories via user OAuth (no GitHub App install required)
- [BUG] ultrareview crashed and used up quota
- Allow customizing or hiding the permission mode indicator text
- [Bug] Unexpected high token usage spike on session resume with minimal prompt input
- [BUG] Claude Code Not responding from last 1 hour
- [Docs] Cloud scheduled task limits per plan tier are undocumented
- [Bug] Rate limit exceeded despite low session usage percentage
- Remote Control permanently disconnects after rate limit with multiple concurrent sessions
- [FEATURE] /fast mode should consume included quota instead of billing separately
- [BUG] Headless single-agent sessions die with SIGTERM after 3-10 minutes (Max subscription, no rate limits)
- [Bug] claude.ai and Claude Code show different usage data for the same account
- Max plan shows as 'API Usage Billing' in CLI
- $200/Month "Max" Subscription Provides ~12 Usable Days Due to Weekly Rate Limits + Wasted Tokens on Tool Bugs
- [DOCS] /extra-usage slash command is undocumented and incorrectly advertised to users
- [BUG] Is the weekly quota for the Pro version only 20 hours?
- unable to write commands inside claude code box in vscode...
- [BUG] I have a problem with my Usage leak.
- `claude-api` skill dumps entire ~784KB SKILL.md into context for a simple usage-limit question, burning huge Pro-plan usage
- [BUG] Fable 5 [1m] prompts 'usage credits required' during active 1M promo window (Jul 17, promo extended to Jul 19)
- [BUG]b"Usage limit reached" triggered after weekly usage jumped from ~35% to blocked in ~12 minutes
- [Bug] `opusplan` silently falls back to Sonnet during plan mode (no signal)
- [FEATURE] Opus 4.8 (1M context) model option disappeared from the model picker
- [BUG] Server is temporarily limiting requests
- [BUG] close to ridiculously usage limits. 4 messages and 50 percent used in peak at 5x max.
- [BUG] Remote Control daemon dies with 403 "no longer a member of the organization" while idle — Max plan personal Gmail, no client-side action
- [BUG] /ultrareview crashes before producing findings, but consumes quota