Rate limit errors
Requests rejected or throttled with rate-limit, quota, or usage-limit messages.
4051 related issues · 505 open · 3546 resolved · peaked at 676 open (2026-04)
Backlog trend over time
The line shows how many issues in this topic were open at the end of each month, derived by
counting each issue from its creation date until it was closed. First-party data from the
anthropics/claude-code tracker.
All rate limit errors issues
Ranked by community engagement (reactions and comments).
- [BUG] Instantly hitting usage limits with Max subscription
- [BUG] Claude Max plan session limits exhausted abnormally fast since March 23, 2026 (CLI usage)
- Feature request: Connect Claude code to Claude projects
- HERMES.md in git commit messages causes requests to route to extra usage billing instead of plan quota
- Cache TTL silently regressed from 1h to 5m around early March 2026, causing quota and cost inflation
- [BUG] IME input causes performance issues and duplicate conversion candidates
- [Feature Request] Support for MCP Sampling to leverage Claude Max subscriptions and reduce API costs
- Weekly Usage Limits Making Claude Subscriptions Unusable
- [BUG] Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage
- [BUG] API Error: Rate limit reached despite Claude Max subscription and only 16% usage
- Add Quota Information Access to Claude Code CLI
- [BUG] Critical: Widespread abnormal usage limit drain across all paid tiers since March 23, 2026 — multiple root causes identified, no formal communication issued
- Feature Request: Multi-Account Profile Support
- [FEATURE] Auto-continue after subscription rate limit resets
- You've hit your limit · While usage is still at 84%
- Max 20 plan: rate limit 100% exhausted within ~70 minutes after reset (never happened before v2.1.89)
- [Meta] Unexpected change in Claude usage limits as of 2025-09-29. (30+ reports)
- Opus 4.6 token consumption significantly higher than 4.5 - quota feedback from Max subscribers
- Feature Request: API Fallback for Pro/Max Subscriptions When Limits Are Reached
- [BUG] Usage limits bugged after double limits expired on new years.
- [FEATURE] Multi-account support in VSCode extension
- [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] Opus 4.6 removed from Claude Desktop Code tab model picker after Opus 4.7 release
- [FEATURE] Add status bar to Desktop App
- StatusLine should expose API usage/quota information in JSON input
- [BUG] Claude Code Usage for Max Plan hitting limits extremely fast
- [FEATURE] Team/Enterprise: shared routines (org-owned scheduled agents)
- [FEATURE] Task queue for queuing multiple prompts/tasks
- [BUG] Opus usage limit reached unusually fast with Max 20x plan since Claude Code v2
- [BUG] Opus 4.5 usage limits significantly reduced since January 2026 - most restrictive since Opus 4.5 launch
- [BUG] Claude Code defaults to 1M context on fresh session with no workaround on Pro plan
- [BUG] Abnormal / inflated rate limit / session usage
- Expose rate limit usage (session %, weekly %) to statusLine configuration
- [BUG] Per-Turn Tool Call Limit Regression Breaks Agentic MCP/SSH Workflows in Claude Desktop
- [Bug] Max plan usage consumed at unusually high rate without workflow changes
- Feature Request: Expose subscription usage data via local file or API
- [Bug] Incorrectly Prompts for API Credits Despite Active Subscription Usage Limit
- Max Plan: Token usage increased ~3-5x without any configuration change (since ~March 28-29)
- Feature Request: Include usage data in status line JSON input
- [BUG] Fable 5 prompts 'usage credits required' on Max plan from 2026-07-20, the day it became standard on Max (saved model claude-fable-5[1m])
- [BUG] resume flag fails to maintain conversation context after hitting usage/context limits
- [BUG] Hitting much faster usage limits than before
- [BUG] API Error: Server is temporarily limiting requests (not your usage limit) · Rate limited
- Clarification needed: Are Opus and Sonnet limits independent or shared after Nov 24 update?
- [BUG] Abnormal Usage Consumption on Claude Code Session Resume — Possible Bug
- [Feature Request] Add message timestamps to interactive conversation view
- Expose /usage subscription quota data in statusLine JSON payload
- Use subscription and fallback to credits, or allow switching without re-login
- [Bug] Anthropic API Error: Image processing failures causing conversation token waste
- Feature Request: Add weekly/daily usage limits to statusLine hook JSON
- Subscription usage jumping to 80% within minutes of reset
- [BUG] /api/oauth/usage endpoint returns persistent 429 for Claude Max users (retry-after: 0)
- [FEATURE] Max plan usage limits silently reduced since Claude 4.6 release
- Subagent model routing is broken — all mechanisms resolve to parent model (Opus)
- [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
- [FEATURE] Expose rate limit/session usage data to statusLine configuration
- [Bug] Anthropic API Error: Usage credits required for 1M context window with opus-plan model
- [BUG] Max 20x plan: 100% usage after 2 hours of light work (5 commits, no agents)
- [FEATURE] Expose rate-limit / plan quota usage in statusLine JSON input
- auto resume
- [BUG] Repeated "Image couldn't be processed" API errors consuming usage limit in Claude Code
- [FEATURE] Give users control over weekly limit reset timing (configurable reset day, or banked on-demand resets like Codex)
- [BUG] Abnormal rate limit consumption — 1-2 prompts exhausting 5-hour window
- Sandbox blocks Go TLS cert verification on macOS (gh CLI fails)
- [BUG] Insanely rapid usage limit reached!
- [CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated subagent work.
- [BUG] API Error: Rate limit reached
- [BUG] API Error: Rate limit reached on Cowork only - account-specific, persists across machines
- [BUG] Extreme token consumption — quota depleted in minutes with normal usage
- Show usage limits on main screen / persistent usage indicator in desktop app
- Opus 4.6 (1M context) hits 'API Error: Rate limit reached' on Max subscription
- Add --max-context flag to cap context window usage
- Task runner reports ENOSPC on subprocess output despite disk having free space
- Display Current Model and Add a Shortcut for Model Switching
- Claude Code API Usage Limit Unexpectedly Reduced on MAX Plan
- [BUG] Skill `model:` frontmatter triggers 429 "Extra usage required" on 2.1.76 when session uses opus[1m]
- [BUG] /rate-limit-options command repeatedly auto-executes after session reset, causing excessive token consumption
- Feature Request: 1M Context with Max Plans in CC
- [BUG] Weekly Usage Limits Making Claude Subscriptions Unusable - This IS a bug.
- statusline: expose per-model weekly rate limits (Opus/Sonnet/Fable) to the status line command
- [BUG] Raching rate limit usage with Xcode Intelligence
- [BUG] # Issue: Misleading Cost Command Output in Claude Code
- /usage command incorrectly shows 'only available for subscription plans' for Pro subscribers
- [BUG] Severe session limit reduction for Pro users (Hitting 100% in ~3 simple prompts)
- [FEATURE] Bring 1M context window to Max plan subscribers
- # Feature Request: Add Usage Metrics Transparency to Claude Code
- [BUG] Cowork Dispatch not responding on macOS
- Sudden 5-hour session window squeeze starting Apr 29, 2026 evening
- Claude CLI not working with sonnet 4 in bedrock [BUG]
- [BUG] Remote Control (mobile): session silently hangs mid-execution; only local Esc recovers it — no remote unstick mechanism
- [BUG] Rate limit 429 errors despite dashboard showing available quota - Two Max accounts, documented inconsistencies
- [BUG] Error installing VS Code extension: 1: ENOENT Please restart your IDE and try again.
- Statusline JSON missing effort level field
- [Bug] Unexpected high API usage consumption - 100% quota in 1-2 hours
- [Bug] Rate Limit Error persists after increasing plan limits and adding funds and Max plan only at 33% used
- Chat Branching: Spawn side-chain conversations with selective merging back to main
- [Bug] Anthropic API Error: credit_balance_too_low despite sufficient account credits
- [Bug] Anthropic API Error: Stream idle timeout - partial response received
- [BUG] Non-deterministic quota accounting: 65% of 5-hour session consumed with minimal actual token usage — Max $100 plan
- [Bug] Anthropic API Rate Limiting: Usage quota exceeded rapidly with minimal requests
- [BUG] Sonnet model consuming both "All models" AND "Somente Sonnet" limits
- Feature Request: Pro Plan 5-Hour Window Usage Visibility
- [Bug] Unexpected Rapid Usage Depletion on Claude Code 20x Plan
- Cache read tokens consume 99.93% of usage quota - architectural scaling issue with CLAUDE.md re-reads
- [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
- Usage Limit Tracking Inaccuracy in Session Management
- Ambiguous 'Don't ask me again' option in session resume prompt
- Add rate limit data to statusline JSON input
- [BUG] Claude hitting usage limits in no time, something broken for sure
- Fable 5 → API-only: please reconsider a subscription path (👍 + comment here if it affects you)
- Expose organization API credit balance to statusLine scripts (and via Admin API)
- Max plan: usage exhausted abnormally fast, twice in one day (March 31)
- [BUG] /api/oauth/usage endpoint aggressively rate limits, making usage monitoring unusable
- [Bug] Rate limit triggered before reaching session usage limit (71%)
- [FEATURE] Expose /usage and /context data in statusLine JSON
- Rate limit errors show 'API Error' without distinguishing usage vs throughput limits
- [BUG] API Error: Rate limit reached incorrect in CLI
- Feature Request: API access tier for Max subscribers (bring your own harness)
- Feature Request: Expose rate limit data in statusline JSON input
- [BUG] /usage command fails with rate_limit_error when checking usage data
- Feature Request: Expose Max/Pro plan usage limits for status line display
- Feature: Long-context (≈1M) support for Claude Sonnet 4 in Claude Code
- [BUG] macOS v1.0.51: Claude Max users incorrectly treated as Pro users - Cannot access Opus model
- [BUG] You've hit your org's monthly usage limit
- CLI returns "API Error: Rate limit reached" on every command including logout (native binary, Max plan)
- [FEATURE] GitHub CLI Support for iOS Claude Code
- Usage limit reached repeatedly without active use — Pro plan
- Feature Request: Expose usage quota in status line JSON
- Session permanently stuck on 'Rate limit reached' after transient rate limit
- Frequent 504 Gateway Timeout errors from api.anthropic.com
- Fast mode is excluded from subscription plans, so Max capacity can't cover the one feature I'd spend it on
- [Bug] Fable 5 incorrectly requires usage credits on Max 20x plan despite available weekly allowance
- [BUG] Rate limit errors triggered by unthrottled keystroke API calls in Claude Code Web interface
- [BUG] Weekly usage not reset during Feb 27 global reset + cycle date shifted (Max 5× subscriber)
- [BUG] Usage limit decrease without Anthropic telling developers
- [Bug] Unexpected Weekly Usage Limit Tracking for Max Plan User
- [BUG] CLI Crashes with posix_spawn EAGAIN Error Due to Recursive pgrep Calls
- [BUG] Output blocked by content filtering policy
- Let the Code tab's usage ring report session context, not only the 5-hour window
- You've hit your org's monthly usage limit
- Desktop app: session history lost when switching accounts
- Auto mode should be available on Pro/Max plans (not just Team/Enterprise)
- Opus/Sonnet 1M context variants broken on Max 20x — misleading 'Rate limit reached' error
- [BUG] Usage limit erreicht trotz verfügbarer Weekly Quota (85% verbraucht laut claude.ai)
- [FEATURE] Allow agent to pick up where it was when interrupted
- Expose Fable weekly usage (seven_day_fable) in status line rate_limits
- OAuth usage API (/api/oauth/usage) returns persistent 429 rate limit
- Anthropic API: Unexpected Opus Usage Limit Warnings on Pro Plan
- [BUG] : Cannot use AWS Bedrock with Claude Code. Getting API Error (429 Too many tokens)
- [BUG] Max 20x upgrade not reflected in weekly limits — depleting at Max 5x rate or worse (upgraded July 16, 2026)
- [BUG] Claude Code shows 'Usage limit reached' despite session at 2% and weekly at 32%
- [BUG] CLI completely blocked by "out of extra usage" error despite Max 20x plan at only 10% usage
- [FEATURE] Expose Claude.ai plan usage in statusLine JSON payload
- [FEATURE] Claude Code / Chrome Extension + API Support = makes this usable to me
- [BUG] CLAUDE CODE Hitting usage limits after barely over an hour of usage. (max plan), when previously I had it set to auto (opus till near limit)...worked all day, NEVER hit limits. WTF!?
- Max 20x plan hitting daily limit with reduced usage — limits appear silently tightened (April 28-29, 2026)
- Token usage limit reached significantly earlier than in previous versions
- [FEATURE] Built-in status line with rate limit usage bars
- [Bug] API Error: Rate limit reached despite 0% usage
- API Error: Rate limit reached
- MAJOR BUG: Claude Code Stuck in Infinite Compaction Loop Making it Basically Useless!
- New Rate Limits Require Granular Model Selection for Cost-Effective Usage
- You've hit your limit · resets 11am (America/Chicago)
- [Feature Request] Reduce verbosity in plan mode to minimize token consumption
- [BUG] Rate limiter not functioning correctly "API Error: Rate limit reached" when spawning more that one agent
- Claude Max + Claude Code rate limits exhausting abnormally fast / possible metering bug
- [Bug] Max plan rate limiting: 5-hour usage limit exhausted after 3-5 requests
- [BUG] Slash commands with Skill() in allowed-tools trigger rate limit on minimal diffs (regression)
- [Bug] Rate limit error despite low API usage when using Opus 4.6 (1m)
- [BUG] Haiku 4.5 usage being counted the same as Sonnet 4.5 despite 3x lower cost
- [BUG] 20x Max Plan User Hitting "Extra Usage" Limits After Single Session - Severe Regression
- 93% rate limit consumed in ~3 minutes on fresh session (Max plan, v2.1.85)
- [BUG] Opus 1M context window suddenly returns "Rate limit reached" on both Max and Team plans (200K works fine)
- Max 20 user: Usage limits make sustained research work inaccessible — data-backed feedback from community
- 5-hour usage limit hits 100% instantly despite low context usage (11%)
- Feature request: intermediate prompt cache TTL tiers (15m, 30m) for interactive use
- [Bug] Team Billing: Frequent Unexpected Usage Limit Resets
- Anthropic API: Unexpected Reduction in Claude Code MAX Plan Usage Limits
- Expose rate_limits.model_scoped (per-model weekly windows, e.g. Fable) in statusLine stdin
- [Bug] Weekly usage limit reset occurring before scheduled reset time & new week ends in 5 days, not 7 days
- Opus model quality regression — significant degradation starting ~April 15, 2026
- [BUG] Excessive token consumption
- Opus 4.6 (Max $100) — Quota reaches 93% after minimal prompting in a single session
- [BUG] 🛑 **INSTANTLY** Running out of Limits Because Claude Code Is Submitting Messages **TWICE**
- [BUG] Claude Code not responding?
- [FEATURE] Enterprise usage bar support
- [BUG] Critical: Token consumption is 100x faster after v2.1.88 leak.
- Max Plan (00/mo) usage limits significantly reduced compared to 2 weeks ago
- [BUG] Claude Code usage limit hit after 7 minutes on new session
- [BUG] 5-Hour Rate Limit Exhaustion Accelerating Despite Comparable Workload
- [BUG] Session usage meter accruing at impossible rate — Max plan, single + multi-session usage
- [BUG] Billing: $50 credits disappeared after Claude Pro subscription renewal (Receipt XXXX-XXXX-7352)
- [BUG] Both the web portal and claude code report usage at ~70% but Claude Code reports I have hit my rate limit
- [BUG] Claude Code uses API billing despite forceLoginMethod: claudeai setting
- Feature: Add usage reset time to status line metadata for customization
- Claude Code agent behavior degradation: instruction ignoring, false reporting, and unauthorized actions
- [BUG] Claude Desktop crashes when browser preview renders Cloudflare Turnstile — reproducible across multiple machines/GPUs, app becomes unlaunchable
- [BUG] Session unrecoverable after upstream 429: every retry returns 400 previous_message_id
- [ISSUE] Not getting Opus usage in line with the Help Center article