Rate limit errors — page 3
Issues 401–600 of the 3,738 matching this topic. The trend chart and topic overview are on page 1.
- /ultrareview returns empty findings after rate limit error — burns free trial slots
- [BUG] Claude Code Opus 4.6 has become extremely dumb and expensive for serious programming tasks
- [Bug] Session quota consumed without user action
- [BUG] Rate-limit 100% within 20 min -> same daily prompts/codes
- [BUG] Not even doing real work and we're at 40% Fix the rate limits (Max x5)
- [Bug] Rate limit consumption exceeds expected rate on 20x max plan
- Frequent 529 Overloaded errors on Max plan (00/month) — unacceptable service quality
- [BUG] Mobile verification problem while signing up
- [FEATURE] Built-in webhook/push notification support for permission requests
- Expose subscription quota/reset info in statusLine JSON
- [Bug] Anthropic API Error: Rate limit reached on claude-sonnet-4-6-1m with Claude Pro plan
- Context Limit Reached error should auto-compact and queue user message instead of failing
- [BUG] `Write` and `Update` tools normalize unicode double quotes to standard ASCII double quote
- [Bug] Opus 4.5 missing from Claude Code model picker menu
- [BUG] Subscription not updating to Max20 after upgrade from Pro
- Feature request: add config option to increase API retries from 10
- [BUG] incorrect timezone name in limit usage message
- [BUG] Fable 5 gated behind "Requires usage credits" under CLAUDE_CODE_OAUTH_TOKEN auth — client discards subscriptionType it already has
- [BUG] Parabolic Usage Spike June 20, 2026 7pm PT
- [BUG] Weekly usage bumped from 60% to 95% in a few hours without any active sessions or me using Claude Code
- [Bug] Weekly usage limit unexpectedly increased without API calls
- [BUG] Usage credits required for 1M context" blocks all requests on Pro plan — first use of the day, quota available, Sonnet selected
- [BUG] Weekly Sonnet limit non-functional — blocked despite 78% Sonnet quota remaining
- [BUG] Agent team subagents do not honor 1-hour prompt cache TTL — main sessions show 100% 1h, every agent session shows 0% 1h
- [BUG] Every command retries up to 10 times ("Retrying in Xs · attempt X/10") and never gets a response. Happens on every single input.
- [BUG] Claude Code freezes during thinking or at a random token while still consuming usage limits
- [Bug] Unexpected usage limit reset cycle change from Monday to Friday
- API access to usage limits and total monthly usage
- [BUG] Claude Max token quotas are badly broken
- Max x20 plan blocked from using Opus 4.6 with 1M context - "Extra usage is required"
- claude -p with OAuth (no API key) bills as API usage, not Max subscription
- [BUG] RATE LIMIT SUUUUUUUCKKSSSS
- You've hit your limit · resets 7pm (Europe/Berlin)
- Session resume (--continue) invalidates entire prompt cache, causes massive rate limit consumption
- [BUG] 5x Max non-peak: 10% of 5h window consumed by 2 lightweight questions (6% context), 1% by a single 3-tool-call request
- [BUG] API ERROR: Rate Limit Reached with 0% of my session or weekly usage even touched.
- [Bug] Anthropic API Error: Rate limit reached despite low session/weekly usage; missing per-minute limit documentation
- [BUG] --output-format stream-json intermittently hangs — process stops producing output and never exits
- Max plan (/mo) runs out of quota before completing single feature — GPT-4.5 at finishes same task
- [BUG] `API Error: Rate limit reached` Max plan ($200) cannot use model `sonnet[1m]` but can use model `opus[1m]`
- [BUG] Claude Code CLI - Rate limit error persisting after March 18-19 incident
- [Bug] Anthropic API Error: Overloaded
- [Bug] API Error: Rate limit reached on Max Plan subscription
- Feature request: expose rate limit utilization in statusline JSON
- Multi-line statusline: second line disappears on narrow terminals instead of wrapping
- Sessions spanning 5-hour rate-limit windows cause inflated usage attribution at window start
- [BUG]
- [Bug] Unexpected Weekly Usage Limit Exceeded Without High Activity
- Feature Request: Built-in usage monitoring command
- [Feature request] Configurable "Approaching Opus usage limit"
- statusLine always reports the main session, even when a subagent or teammate transcript is focused
- Feature request: read-only usage scope on `claude setup-token` (or a usage:read grant) for subscription accounts
- [BUG] Max X5 Usage Instantly Reaches 100% After Software Update
- [FEATURE] Tell the statusLine which subagent is focused when viewing its transcript
- [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
- [BUG] Transient server errors MUST NOT kill subagents
- Status line: expose monthly usage/limit data
- [Bug] Opus 4.8 responses not displayed after tool use — quota consumed with no output
- Sonnet 4.6 routes every request to long-context tier on Claude Desktop 2.1.149 (429 'Usage credits required')
- [Bug] Opus 4.7 xHigh performance degradation post-Colossus-1 rollout
- [Bug] Rate limits reached prematurely with 5x max plan tier
- [BUG] Abnormal session consumption on Max 5x plan — 17% usage drop on single small prompt, support tickets closed without human response
- Opus 4.7 repeatedly ignored explicit user instructions to use installed skills; caused excessive token spend over multi-hour session
- [BUG] 16% of 5-hour usage limit consumed by simple investigation prompt.
- [BUG] FALSE indication that limit has been reached. Primary quota fully available. Extra usage not relevant, yet error indicated that it is the blocker.
- [Bug] Token usage limits exhausted prematurely in 5-hour sessions
- Critical Regression: Disproportionate Session Limit Consumption for CLI Operations
- [BUG] Cache TTL silently downgrades from 1h to 5m when Extra Usage is active
- Feature Request: Allow OAuth/subscription tokens with Agent SDK for personal development use
- [BUG] 5 hour limit reached for claude code extensions visual studio code just with 4 prompts
- Connectors silently consume tokens on every API call — no warning, no disclosure, caused work disruption
- [BUG] Incorrect timezone name: Europe/Kiev should be Europe/Kyiv
- Haiku auto-downgrade mid-conversation destroys user work — please stop silent model switching
- [BUG] API Error: Rate limit reached
- [BUG] Pro plan token limits exhausted after 3-4 queries (VS Code Extension v2.1.84)
- [FEATURE] Expose account usage % to hooks and CLI so automated workflows can yield tokens for manual use
- [BUG] API Error: Rate limit reached
- [FEATURE] Allow OAuth tokens for Anthropic Messages API — enable subscription-based programmatic access
- [BUG] Single session startup triggers 429 rate limit on client_data endpoint, causing false "1 MCP server failed" status
- Feature: Expose plan usage limits (session/weekly) in statusline JSON payload
- Expose /usage data in statusLine JSON API
- Expose rate limit / usage quota info in statusLine JSON input
- VSCode extension consumes excessive tokens in background
- You've hit your limit · resets 11pm (America/Anchorage)
- Edit tool panics on UTF-8 multi-byte character boundary when editing Chinese text
- [BUG] Opus usage charged when using Haiku model
- OAuth expiration causes retry storm consuming 100% session usage (3.75M wasted tokens)
- Claude AI usage limit reached|1760000400
- [BUG] Usage Limit major leap to 17 from 4 hours gap!
- [Bug] Anthropic API: Rapid Usage Limit Exhaustion with Claude Opus
- [Feature Request] Session Token Tracking and Usage Limit Expansion for Claude Code
- [BUG] Sonnet 4 is completely unsuable because of 429s
- Statusline: expose per-model rate limit usage in rate_limits (e.g. separate Opus/Fable windows)
- [FEATURE] Background agent should pause (not fail) when hitting session limit with known reset time
- [FEATURE] add `extra_usage` to statusline callback info
- [FEATURE] Notification system for VS Code extension — limit reset, task complete, session events
- [BUG] API Error: Server is temporarily limiting requests (not your usage limit) · Rate limited
- [BUG] : API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy
- [BUG] Token limit drained in seconds due to repeated image processing error retries
- [BUG] Weekly usage limit not updated after upgrade from Pro to Max 20x — account still behaves as Pro/5x
- Add sandbox mode/status to statusline data fields
- You've hit your org's monthly usage limit
- [Feature Request] Distinguish between API key and OAuth subscription billing in startup banner
- Billing: /ultrareview consumed 2 free runs on server-side rate-limit error
- Expose per-model weekly usage in statusline hook payload
- [BUG] Idle but 18% usage limit was used.
- Session limits exhausted immediately post-April 15 outage — Max subscription (Claude Code)
- [BUG] Bug Report: 401 Invalid Bearer Token Immediately After Successful Login
- API 500 Internal server error on tool results (repeated)
- You've hit your limit · resets 2pm (America/Chicago)
- [Bug] Anthropic API Error: Out of extra usage quota
- [BUG] Paid usage on max20 - limit reached within one command... WTF?!
- Bug: /remote-control session permanently stuck on usage limit prompt — no recovery path from mobile app
- [BUG] Team Premium seat weekly limit stuck at 100% after only 102M tokens — other users on same plan consume 757M+ without issues
- Plan mode: Add 'Delegate to Agent' option for plan execution
- API Rate limit errors started appearing with no changes to usage patterns
- [BUG] Rate limit reached immediately on new Max subscription despite 1% usage
- You've hit your limit · resets 6pm (Europe/Lisbon)
- Make Fast Mode free for Max subscribers
- [Bug] Anthropic API Error: Rate limit exceeded with low usage quota
- Add rate limit utilization to status line JSON
- Expose rate limit data in statusLine JSON
- [BUG] Usage limits have been SEVERLY reduced - hitting limits 5x faster - is CC counting tokens correct?
- [FEATURE] Auto-continue after the limit is reset
- [FEATURE] Allow Max/Pro subscription authentication for third-party IDE integrations
- [BUG] Rate limit percentage appears incorrect after reset - shows 17% with minimal usage
- [BUG] @agent-explore "Out of Credits" on $100 Max Plan
- [Feature Request] Display API usage and rate limit reset time in statusline
- [BUG] Incorrect Usage Limit Warning
- [Bug] Billing: Unexpected Rapid API Usage Exhausting Weekly Quota
- Usage Limit Reset Inconsistency with Documented 5-Hour Interval
- [FEATURE] "Best of N" - Generate and Compare Multiple Solutions Simultaneously
- Feature Request: Now That You Throttle, Need Transparency of Usage for Max Users
- Claude AI usage limit reached|1753113600
- Claude AI usage limit reached|1753088400
- Were Opus 4 Usage Limits Lowered Recently?
- Auto mode classifier persistently unavailable — 2+ weeks, reproduces across accounts, machines, OSes, and CLI versions
- [Bug] Max 20x weekly quota drained 53% in 2 days; transcript accounting shows those days were <half the load of a heavier week that didn't drain — cache_read metering suspected
- [Feature Request] Pause rate limit reset timer during Anthropic API service outages
- [BUG] Auto-mode safety classifier reports model "temporarily unavailable," blocking all Bash/WebSearch while normal generation works fine
- [MODEL] Opus 4.8: forced balance-slot criticism, critique-for-its-own-sake baked into initial CoT, and attention-driven context collapse — plus a 71-issue failure inventory
- Opus 4.8 burns 5h limit in ~30min on operational work; no signal to downgrade to Sonnet
- Paid Max plan usage limits interrupt real work mid-task; need predictable quota or graceful continuation
- claude -p headless sessions billing misrepresented by model — repeated false confirmations led to €80+ unexpected charges
- [Feature Request] Live Usage Limit Tracker Widget — iOS & Android
- Claude Code provides no in-session determinism mechanism, forcing automation users onto the metered Agent SDK path
- CLI requires extra-usage billing for fast Opus 4.6, but desktop app runs it on Max plan
- [BUG] 20x Plan managed to burn the ENTIRE 5h window in ~30 minutes without any heavy use
- ultrareview: failed Find phase consumed free quota slot (empty results, ~10s heartbeats)
- [Bug] Weekly usage limit reset early, losing 36% of quota before scheduled reset time
- [BUG] Rate limit error (429) triggers unexpected plan usage consumption in Claude Code (Windows)
- [Bug] ultrareview timeout shouldn't consume quota credits
- Bash: sleep ≥2s blocked unconditionally, breaking legitimate polling/heartbeat patterns
- [BUG] API Error: Request rejected (429) · Rate limited
- [Bug] Rate limit error at 72% token usage
- [BUG] Max plan usage at 100% with zero requests — claude.ai (not Claude Code)
- [Windows] --dangerously-load-development-channels does not enable inbound channel notifications
- [Bug] Performance degradation after usage threshold suggests undisclosed rate limiting or model degradation
- [BUG] Max Plan User Getting "Extra usage is required for long context requests" Error
- Doesnt seem like new session resets usage limits correctly.
- You've hit your limit · resets 10pm (Europe/Istanbul)
- You've hit your limit · resets 4pm (Asia/Tashkent)
- Feature Request: Configurable usage warning threshold
- [Bug] Anthropic API Error: Rate limit reached despite available quota on Max plan
- Expose per-model rate limits (e.g. Sonnet) in statusline rate_limits field
- read tool should reliably deliver image files to the model as vision input — claude is multimodal, let it see
- Expose session/weekly rate limit usage in statusline JSON
- [BUG] Max x20 plan — 5-hour quota consumed in ~10 prompts (started March 14, 2026)
- [BUG] USAGE BUG, opus drains sonnet usage URGENT FIX NEEDED
- [BUG] Edit tool introduces Unicode curly quotes (U+201D) in HTML attributes, silently breaking CSS selectors
- [BUG] claude-agent-sdk: MessageParseError on rate_limit_event message type
- Feature Request: Expose /usage data as structured JSON for MCP servers and hooks
- [BUG] Stuck Claude Code instances, I can not stop or remove them
- [BUG] Model attempts file edits without reading file first, wasting tokens and time
- [claude.ai] No Programmatic Access for Subscribers - Locked Into Buggy Web UI
- [FEATURE] Expose Usage Metrics in Session JSON
- [Bug] Custom slash command appears duplicated and incorrectly highlighted in command selection menu
- Usage Quota Not Resetting at Scheduled Time for Max Customer
- [BUG] Claude Code extension in VS Code is using more tokens than the CLI
- SUB AGENT GIMMICK Agent Execution Stalls: Sub-Agent Delegation Causing Performance Degradation
- API Rate Limit Exceeded: Persistent Overloaded Error on Retry
- Bug Report
- Identifies the specific problem (high token usage)
- [BUG] Same-day 17x variance in tokens charged per weekly quota point (Max 20x, 2.1.221)
- [BUG] Weekly + Fable quota jumped 0% -> 50%/100% with account idle (Max 20x, after Jul 31 reset)
- [Bug] Opus 5 and Fable 5 depletes usage limits at the same rate. Usage limits decreased to 1/3 of previous limits on 20x max plan without code changes
- [BUG] Fable 5 blocked with 'usage credits' prompt on Team Premium seat; modelAccessCache stays empty after fresh login
- Claude Code (VS Code extension) prompts for usage credits on Fable 5 despite Max plan showing full entitlement
- Expose permission_mode in statusLine stdin JSON
- 10 background Agent tasks stuck running for 34+ hours, no way to cancel, burned ~1M tokens
- [BUG] /model picker shows Fable 5 as disabled while --model claude-fable-5 works on the same account
- [BUG] out of credits in 3 days, as a hobbyist.
- [BUG] VS Code extension resumes huge sessions without warning and rapidly exhausts Max usage
- [BUG] Weekly + 5hr limits wiped from single small edit - area:cost
- [BUGdeep-research workflow spawned 111 agents for a single query and consumed entire 5-hour session quota — zero output produced
- Unexpected 5-hour limit consumption in Claude Code
- feat: surface estimated token cost + require confirmation before launching resource-intensive skills
- [FEATURE] Expose model configuration for subagents in dynamic workflows
- [BUG] Max plan: 'Usage credits required for long context requests' on standard 400k context