Codex Pulse
What Codex users are asking right now
The most reported Codex usage problem this week is unexpected usage depletion, with 15 public GitHub reports in the last 7 days.
Latest scheduled observation
Observed
199 GitHub community reports observed by Codex Pulse.
0 change in reports since the previous scheduled observation.
Usage-related issues in openai/codex, within Pulse's 14-day creation window. Counts describe this source set, not affected users or platform-wide OpenAI behavior.
Previous scheduled observation: (199 reports).
Scheduled scan record on GitHubEach dot is one successful scheduled observation. Counts use a rolling 14-day creation window; reports can leave that window. No measurements are implied between scans.
Exact observation times and counts
- : 293 reports
- : 285 reports
- : 255 reports
- : 252 reports
- : 247 reports
- : 240 reports
- : 241 reports
- : 247 reports
- : 248 reports
- : 245 reports
- : 242 reports
- : 244 reports
- : 243 reports
- : 236 reports
- : 235 reports
- : 236 reports
- : 221 reports
- : 222 reports
- : 206 reports
- : 200 reports
- : 202 reports
- : 204 reports
- : 199 reports
- : 199 reports
Newly observed since the previous scheduled scan
4 reports and 0 topics present now were absent from the previous observation. Newly observed does not mean newly created on GitHub or first ever reported.
Current topics by observed report count
Existing Pulse classifications across the 14-day window. A report can also belong to an emerging topic, so topic counts can overlap.
- Usage display & /status
42 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations. - Unexpected usage depletion
38 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations. - Hitting the limit
18 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations. - Requests to change limits
12 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations. - Plan changes & allowance
11 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations. - “Model at capacity” errors
9 observed reports
First seen in scheduled history: .
Last seen: .
Present in 41 scheduled observations.
Current reports: source links and observation history (199)
First/last seen refer only to retained scheduled observations. GitHub creation/update times describe the source issue. Absence from a later scan does not prove resolution.
- Existing subagents appear to retain GPT-6 Astra model/usage rate after parent switches to GPT-6.1 Sol
First observed: . Last observed: . Present in 1 scheduled observations.
GitHub created: . GitHub updated: .
- Sharp reduction in usage
First observed: . Last observed: . Present in 1 scheduled observations.
GitHub created: . GitHub updated: .
- [ChatGPT][Regression] Existing Chat local execution is blocked and redirected to separately-metered Work
First observed: . Last observed: . Present in 1 scheduled observations.
GitHub created: . GitHub updated: .
- Bonus usage resets can leave users worse off
First observed: . Last observed: . Present in 1 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS][Codex Desktop] Sudden ~60% increase in 5h quota usage overnight; large prompt-cache miss on small turn
First observed: . Last observed: . Present in 2 scheduled observations.
GitHub created: . GitHub updated: .
- Banked usage resets expire at least one hour earlier than the expiration time shown in Codex Desktop
First observed: . Last observed: . Present in 2 scheduled observations.
GitHub created: . GitHub updated: .
- Unexpectedly high usage during a long multi-agent task without a cumulative usage checkpoint
First observed: . Last observed: . Present in 3 scheduled observations.
GitHub created: . GitHub updated: .
- Dots: opaque “abuse prevention” breaks undermine always-on reliability; no usage meter or reset information
First observed: . Last observed: . Present in 3 scheduled observations.
GitHub created: . GitHub updated: .
- Clicking upgrade when prompted your usage remaining is low, it redirects you to a new codex within your codex instead of pricing
First observed: . Last observed: . Present in 3 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Astra High] Request to investigate repeated lookups, task distribution, and weekly usage attribution in a long development session
First observed: . Last observed: . Present in 3 scheduled observations.
GitHub created: . GitHub updated: .
- Resetting the usage limit and getting it drained only in 5 minutes
First observed: . Last observed: . Present in 4 scheduled observations.
GitHub created: . GitHub updated: .
- HTTP 429 with Retry-After prevents loading existing conversations in ChatGPT Web and Windows Desktop
First observed: . Last observed: . Present in 4 scheduled observations.
GitHub created: . GitHub updated: .
- Thread stuck running — please check credit usage
First observed: . Last observed: . Present in 4 scheduled observations.
GitHub created: . GitHub updated: .
- GPT-6 Astra Ultra: 14 user-driven turns generated 90 Ultra executions and exhausted purchased credits
First observed: . Last observed: . Present in 4 scheduled observations.
GitHub created: . GitHub updated: .
- gpt-6.1-sol: the Codex backend rejects `prompt_cache_breakpoint`, so multi-turn requests never read from cache
First observed: . Last observed: . Present in 5 scheduled observations.
GitHub created: . GitHub updated: .
- Codex desktop app: show remaining usage limits and reset times in the header
First observed: . Last observed: . Present in 5 scheduled observations.
GitHub created: . GitHub updated: .
- Selected model is at capacity. Please try a different model.
First observed: . Last observed: . Present in 5 scheduled observations.
GitHub created: . GitHub updated: .
- [Work desktop / Automations] Minutely browser heartbeat ran for 8 days through access failures, consuming Pro usage and credits
First observed: . Last observed: . Present in 6 scheduled observations.
GitHub created: . GitHub updated: .
- Auto-apply banked Codex reset at expiration (opt-out)
First observed: . Last observed: . Present in 6 scheduled observations.
GitHub created: . GitHub updated: .
- Show the usage reset date alongside the remaining percentage in the desktop profile menu
First observed: . Last observed: . Present in 6 scheduled observations.
GitHub created: . GitHub updated: .
- Codex CLI should not continue implementation before unanswered user decisions (causes wasted usage)
First observed: . Last observed: . Present in 6 scheduled observations.
GitHub created: . GitHub updated: .
- Web GPT-6 Pro conversation appears in Codex Cloud and uses subagents: execution and usage accounting
First observed: . Last observed: . Present in 6 scheduled observations.
GitHub created: . GitHub updated: .
- Possible weekly quota accounting discrepancy between two $200 Pro accounts (GPT-6.1-Sol)
First observed: . Last observed: . Present in 7 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Desktop 26.930.31730: default memory generation fans out into hidden agents and consumes ~15% of 5-hour quota after a 2-minute task
First observed: . Last observed: . Present in 7 scheduled observations.
GitHub created: . GitHub updated: .
- Codex macOS app: persistent "Selected model is at capacity" across all conversations despite available usage
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- Subscription Sharing usage limit on Pi still blocking OpenAI model usage after reset
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- Selected model is at capacity. Please try a different model.  Retry in 45s  Latest response
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- Codex quota drains abnormally fast even on trivial cached prompts
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- Request for flexible higher tiers (2x/3x/4x)
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug] 5-hour usage limit exhausted while 30%+ was still remaining
First observed: . Last observed: . Present in 8 scheduled observations.
GitHub created: . GitHub updated: .
- Unified agent control plane: account state is global, but task/compute/Remote controls are surface-local
First observed: . Last observed: . Present in 9 scheduled observations.
GitHub created: . GitHub updated: .
- Unable to reset quota
First observed: . Last observed: . Present in 9 scheduled observations.
GitHub created: . GitHub updated: .
- One dot-delegated task reports usage limit despite available allowance; other delegated tasks work
First observed: . Last observed: . Present in 9 scheduled observations.
GitHub created: . GitHub updated: .
- [P2][Bug] Pro $200 GitHub reviews stop at reported exact 50% of doubled allowance: recurrent Oct 2/4 refusals
First observed: . Last observed: . Present in 9 scheduled observations.
GitHub created: . GitHub updated: .
- Usage reset unavailable
First observed: . Last observed: . Present in 9 scheduled observations.
GitHub created: . GitHub updated: .
- Limit reach
First observed: . Last observed: . Present in 10 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug] 62,500 promotional credit grant disappeared; 61,081.09 → 0 with Pro allowance remaining
First observed: . Last observed: . Present in 11 scheduled observations.
GitHub created: . GitHub updated: .
- Token problem
First observed: . Last observed: . Present in 12 scheduled observations.
GitHub created: . GitHub updated: .
- [Regression][macOS][CLI 0.160.0] Active Goal survives terminal exit and daemon restart, drains usage, and recreates deleted checkout
First observed: . Last observed: . Present in 12 scheduled observations.
GitHub created: . GitHub updated: .
- [CLI 0.158.0-alpha.2.1] Banked reset consumed immediately after "Use a reset" without expiration details or confirmation
First observed: . Last observed: . Present in 12 scheduled observations.
GitHub created: . GitHub updated: .
- [ChatGPT Plus][Work] Five-hour allowance drains unusually fast with GPT-6 Astra Max and GPT-6.1 Sol
First observed: . Last observed: . Present in 13 scheduled observations.
GitHub created: . GitHub updated: .
- [Codex Desktop][Automations] Independent incident: repeated heartbeat wakes during local-host failure; ~20% usage drop reported
First observed: . Last observed: . Present in 13 scheduled observations.
GitHub created: . GitHub updated: .
- Android Remote: dot-created Windows tasks missing from host list, with “Too many requests”
First observed: . Last observed: . Present in 13 scheduled observations.
GitHub created: . GitHub updated: .
- Plus plan and remaining usage limits do not display
First observed: . Last observed: . Present in 13 scheduled observations.
GitHub created: . GitHub updated: .
- Extreme token useage
First observed: . Last observed: . Present in 15 scheduled observations.
GitHub created: . GitHub updated: .
- GPT-5.6 Light consuming ~20% of 5-hour allowance on minimal read-only task
First observed: . Last observed: . Present in 15 scheduled observations.
GitHub created: . GitHub updated: .
- codex version of linux codex desktop consumes larger token than cli version
First observed: . Last observed: . Present in 16 scheduled observations.
GitHub created: . GitHub updated: .
- Alleged Unjustified Blockages
First observed: . Last observed: . Present in 16 scheduled observations.
GitHub created: . GitHub updated: .
- Expose reported token usage for failed and interrupted runs in codex exec --json
First observed: . Last observed: . Present in 16 scheduled observations.
GitHub created: . GitHub updated: .
- Expose model-request lifecycle, timing, and per-request usage in codex exec --json
First observed: . Last observed: . Present in 16 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS desktop 26.930] Add credits consistently resets UI; View usage also resets intermittently
First observed: . Last observed: . Present in 16 scheduled observations.
GitHub created: . GitHub updated: .
- Issue: ChatGPT / Codex usage unexpectedly dropped from 63% to 0% within approximately one minute
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- DOT: weekly usage shows 93% left and 19-hour reset despite reported inactivity and expected fresh weekly quota
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- [Rate limits] Oct 2 global reset did not reach paid account after "Reset all propagated"
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- Five-hour allowance drops before prompt submission, then drops further during a low-effort response
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS] Usage history graphs are duplicated in Usage & billing → Analytics
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- Linux VS Code Codex: response stream failures and repeated UI errors; paid usage impact
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug] 62,500 promotional credits disappeared and Work/Codex tasks stopped
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- Codex reset credits disappeared before their displayed expiration dates
First observed: . Last observed: . Present in 17 scheduled observations.
GitHub created: . GitHub updated: .
- Critical Windows sandbox startup outage: persistent deny ACLs hit 64 KiB; generic ACEs double capacity usage
First observed: . Last observed: . Present in 18 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug] Recurring Computer Use failures, browser login freezes, and abnormal usage consumption
First observed: . Last observed: . Present in 18 scheduled observations.
GitHub created: . GitHub updated: .
- Frequent "Selected model is at capacity" on GPT-6.1-Sol despite 97% 5h and 99% weekly quota remaining
First observed: . Last observed: . Present in 19 scheduled observations.
GitHub created: . GitHub updated: .
- 6.1sol repeatedly fails simple YAML routing tasks: criticism of OpenAI pricing and halved usage quotas
First observed: . Last observed: . Present in 21 scheduled observations.
GitHub created: . GitHub updated: .
- Make the remaining-usage warning less intrusive
First observed: . Last observed: . Present in 21 scheduled observations.
GitHub created: . GitHub updated: .
- Can't Restart `/review` on "Model is at capacity error" because "'/review' is disabled while a task is in progress."
First observed: . Last observed: . Present in 21 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Usege Analytics, interface issue
First observed: . Last observed: . Present in 21 scheduled observations.
GitHub created: . GitHub updated: .
- Repeated early compaction across GPT-6.1 Sol and Astra: internal token counts exceed reported usage
First observed: . Last observed: . Present in 22 scheduled observations.
GitHub created: . GitHub updated: .
- Code review usage stops at %50 wrong for Pro 200 (with x20 until oct 30) since announcement
First observed: . Last observed: . Present in 22 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows] Reset-time timezone mismatch between the ambient Usage menu and the Remaining usage fallback
First observed: . Last observed: . Present in 22 scheduled observations.
GitHub created: . GitHub updated: .
- Windows desktop intermittently loses workspace/Usage/Dot state after ERR_CERT_VERIFIER_CHANGED or ERR_NETWORK_CHANGED
First observed: . Last observed: . Present in 22 scheduled observations.
GitHub created: . GitHub updated: .
- Usage Bug: Incorrect Limit Tracking and Missing Credit-Switch Warning
First observed: . Last observed: . Present in 23 scheduled observations.
GitHub created: . GitHub updated: .
- Astra reasoning-token usage differs between ChatGPT Enterprise–authenticated Codex and public Responses API at the same effort
First observed: . Last observed: . Present in 23 scheduled observations.
GitHub created: . GitHub updated: .
- "You've hit your usage limit" only when working on SSH remote connection
First observed: . Last observed: . Present in 23 scheduled observations.
GitHub created: . GitHub updated: .
- Pro: purchased credits consumed while weekly allowance simultaneously dropped 19% → 2% (`codex exec`, v0.159.2)
First observed: . Last observed: . Present in 23 scheduled observations.
GitHub created: . GitHub updated: .
- Desktop: MCP App loopback WebSocket blocked by Local Network Access despite CSP allowance
First observed: . Last observed: . Present in 24 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Pro Limit Scam
First observed: . Last observed: . Present in 24 scheduled observations.
GitHub created: . GitHub updated: .
- codex github review connector says I've reached the usage but there's plenty of remaining
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- Weekly allowance shows 25% remaining while Work/Codex credits decrease and credit usage history is empty
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Pro] Remaining weekly subscription allowance drops by several percentage points per day without intentional usage
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Plus] GPT-6 Luna Max quota burn spike with unusually frequent auto-review/guardian calls
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- TypeScript SDK: resumed turn.completed.usage returns thread totals despite the per-turn Usage contract
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- "Selected model is at capacity" constantly on Pro 20x account with GPT-6 Astra (High), never on Pro 5x account
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows] Usage history UI is rendered repeatedly in Usage & billing
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- Expose sub-1% precision in Codex usage / rate-limit telemetry
First observed: . Last observed: . Present in 25 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code extension no longer shows Weekly remaining usage percentage after update
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS][Voice] Session stops after ~1 second with usage-limit warning despite reported 16% voice usage
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS][Voice] Usage-limit error on Pro while regular Codex allowance remains
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- GPT-6 Sol Medium: single `ok` interaction consumed ~7% of 5-hour Work/Codex quota
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- [ChatGPT Chat][macOS/Web/Mobile] GPT-6 Pro fails with generic/limit errors while other models work; VPN on/off unchanged
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Pro] Desktop Voice says usage limit reached while Codex usage is available
First observed: . Last observed: . Present in 26 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Voice] Realtime voice stops with usage-limit error while Codex reports 27% weekly allowance remaining
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- Pro account blocked by usage limit while 77% of weekly limit remains; 5-hour limit meter missing
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- Codex web weekly allowance flips 58% → 16%; usage responses differ in account_id and report 42% vs 84% used
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- /status displays an outdated usage dashboard URL that redirects to ChatGPT home
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- Pro $500 weekly allowance at 86% after 1 hour 43 minutes of four High chats
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- Auto-review rejects explicit owner changes to a self-imposed quota rule; blocked heartbeat keeps consuming usage
First observed: . Last observed: . Present in 27 scheduled observations.
GitHub created: . GitHub updated: .
- [Performance / Rate limits] GPT-6 Sol uses quota more slowly, but real developer throughput appears significantly worse
First observed: . Last observed: . Present in 28 scheduled observations.
GitHub created: . GitHub updated: .
- Usage dropped too fast on sol 6.1
First observed: . Last observed: . Present in 28 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Usage Reporting Metrics: Double Usage
First observed: . Last observed: . Present in 28 scheduled observations.
GitHub created: . GitHub updated: .
- codex using to many tokens
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Usage Decreasing Without My Use and Banked Reset Missing
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Browser Auto-review fails with “workspace is out of credits” despite available Codex usage
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- macOS app missing normal Chat history sync and normal ChatGPT quota/model access
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- The remaining usage quota should be displayed in gray in the macOS client
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Paid got no Extra time
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- The subscription plan seems a bit much.
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Codex quota leak
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Built-in image_gen returns usage_limit_reached with 45% 5h and 38% weekly quota left on Windows
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- ChatGpt Plus 5-hour usage drops too fast issue
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Inconsistent 5-hour usage reset times across Usage UI and /status
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- Entire conversation disappeared after usage limit was reached
First observed: . Last observed: . Present in 29 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug] Excessive quota consumption (6%) for a single-word prompt using GPT-6 Luna Light
First observed: . Last observed: . Present in 30 scheduled observations.
GitHub created: . GitHub updated: .
- GPT-5.5 enters repetitive agent loop in Xcode Coding Intelligence, consumes usage without progress
First observed: . Last observed: . Present in 30 scheduled observations.
GitHub created: . GitHub updated: .
- Codex/ChatGPT Desktop embedded checkout fails while attempting to open the credit/usage checkout flow.
First observed: . Last observed: . Present in 30 scheduled observations.
GitHub created: . GitHub updated: .
- User-authorised usage-aware routing between Chat and Work/Codex
First observed: . Last observed: . Present in 30 scheduled observations.
GitHub created: . GitHub updated: .
- Accessibility: Voice-first troubleshooting can consume Codex allowance disproportionately
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- GPT-5.6 Luna 5-Hour Usage Limit Is Being Consumed Abnormally Fast
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Desktop usage accounting mismatch: 36,318-token Luna request followed by ~6% 5-hour depletion and ~2.95M daily tokens
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- Single GPT-6 Astra task consumed 89% of the 5-hour limit and 2.4M input tokens
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- Codex Work tasks aren’t queueing properly Usage waste
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows] 5-hour usage reset tooltip intermittently shows a time 9 hours later than expanded view
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- sudden ~3x increase in Codex usage-limit consumption with GPT-5.6 Sol Medium on ChatGPT Plus
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- macOS app: ordinary ChatGPT conversation blocked by "Codex / Work usage limit" error (Go plan)
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- Automatic compaction double-counts prior reasoning against reported token usage and triggers unnecessary compaction
First observed: . Last observed: . Present in 31 scheduled observations.
GitHub created: . GitHub updated: .
- Polish translation error: "5-week usage limit" instead of "5-hour usage limit"
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- Composer hard-disabled by ChatGPT subscription rate limit even when model traffic is routed to a custom provider (`openai_base_url`)
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- macOS desktop 26.915.31945: startup ambient suggestions generate 291k tokens; quota attribution unclear
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code extension: `Rate limit: Unavailable` with repeated 403 from `/subscriptions`
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- Windows desktop app shows only “ChatGPT Work” and “Codex”; usage settings fail to load
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- Feature request: Separate regular quota, banked resets, and purchased credits
First observed: . Last observed: . Present in 32 scheduled observations.
GitHub created: . GitHub updated: .
- Usage % and credit balance
First observed: . Last observed: . Present in 33 scheduled observations.
GitHub created: . GitHub updated: .
- [Pets][Diagnostics] Simple custom-pet sprite defects can trigger excessive agent investigation and usage-window burn
First observed: . Last observed: . Present in 33 scheduled observations.
GitHub created: . GitHub updated: .
- Rate limit and usage unavailable in VS Code extension after update
First observed: . Last observed: . Present in 33 scheduled observations.
GitHub created: . GitHub updated: .
- use the details you provided (plan/app version/time/model/session ID) to investigate whether this was an unexpected eligibility change.
First observed: . Last observed: . Present in 34 scheduled observations.
GitHub created: . GitHub updated: .
- Token usage Astra off the charts
First observed: . Last observed: . Present in 34 scheduled observations.
GitHub created: . GitHub updated: .
- macOS: Send disabled for third-party models after Codex subscription quota is exhausted
First observed: . Last observed: . Present in 35 scheduled observations.
GitHub created: . GitHub updated: .
- [ChatGPT Web][Sep 26–27] All chats intermittently blocked; loaded conversation disappears into error, Pro work blocked
First observed: . Last observed: . Present in 35 scheduled observations.
GitHub created: . GitHub updated: .
- Codex desktop: daily token usage history shows 0 or NaN despite recorded activity
First observed: . Last observed: . Present in 35 scheduled observations.
GitHub created: . GitHub updated: .
- Windows desktop app: Chat / Work toggle missing, app opens Work only
First observed: . Last observed: . Present in 35 scheduled observations.
GitHub created: . GitHub updated: .
- Linux desktop: ship Btrfs socket-isolation fix; confirmed recovery and request for usage review
First observed: . Last observed: . Present in 35 scheduled observations.
GitHub created: . GitHub updated: .
- Resume thread automatically when usage limits reset
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- Add a CLI command to check remaining account usage
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- app-server: account/rateLimits/read returns untyped -32603 when the backend rejects the credential (401)
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- 1-3% usage used from saying hi
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- [Codex App] First-day 61% weekly usage with long-context amplification and missing activity entries
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- Local Codex account usage depletion causes remote ssh connections disabled even when remote computer has usage in its account.
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- Windows Desktop spins forever on startup; restarting only codex.exe restores UI
First observed: . Last observed: . Present in 36 scheduled observations.
GitHub created: . GitHub updated: .
- Token Replenish Setup is not user friendly or customer useful,
First observed: . Last observed: . Present in 37 scheduled observations.
GitHub created: . GitHub updated: .
- Automatic Codex resets can leave users worse off by postponing weekly replenishment
First observed: . Last observed: . Present in 37 scheduled observations.
GitHub created: . GitHub updated: .
- False usage-limit banner consumed a reset credit despite 98% remaining
First observed: . Last observed: . Present in 37 scheduled observations.
GitHub created: . GitHub updated: .
- Using codex-cli 0.157.1 is a terrible experience
First observed: . Last observed: . Present in 38 scheduled observations.
GitHub created: . GitHub updated: .
- [macOS][Chat] Send and dictation remain disabled after conversation refetch enters streaming and GET 429
First observed: . Last observed: . Present in 38 scheduled observations.
GitHub created: . GitHub updated: .
- usage,billing
First observed: . Last observed: . Present in 38 scheduled observations.
GitHub created: . GitHub updated: .
- Reset time
First observed: . Last observed: . Present in 38 scheduled observations.
GitHub created: . GitHub updated: .
- Publish actual Codex subscription quota consumption rates
First observed: . Last observed: . Present in 38 scheduled observations.
GitHub created: . GitHub updated: .
- Quota Limit Bars in VS Code Extension not visible since extension version 26.5917
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- app-server: turn ends with `error` then `turn/completed` when the account usage limit is reached, so drivers relaunch in a tight loop
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code Codex extension 26.917.62051: 5-hour and weekly usage indicators missing after update
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Windows app shows Codex reset timestamp +1 hour compared with web Usage
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Add a setting to disable CLI usage-limit warnings
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Quota limit not visible
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Usage limits unavailable in VS Code Insiders extension while CLI works
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Codex / Work analytics shows incorrect 5-hour reset time based on local OS time
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Selected model is at capacity. Please try a different model.
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [Bug][macOS][Work] Deterministic reasoning regression across high-end models + repeated capacity errors; Chat mode remains correct
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Codex App MacOS /status says Rate limit: Unavailable while Settings shows usage
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- many users commenting on excessive usage
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Hosted search usage causes premature auto-compaction
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code: Work locally selector does not open; subscription endpoints return 403
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [CLI][Astra] Research loop consumes excessive quota and incorrectly re-applies an old pause instruction
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Request for an investigation into Codex GPT-6 task quality and high usage, and for quota compensation
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Upgraded to Pro hit limit after running one command!!!
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Feature request: remove the 5-hour usage limit
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Windows Codex app: read_thread/list_threads advertised but unavailable; rate-limit RPC fails with -32603
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- chatGPT windows app repeatedly fails to follow explicit response style instructions and wastes many codex credits
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code 26.917.62051: missing authenticatedUserId causes SSE usage data to be discarded (Rate limit: Unavailable)
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [App] Allow hiding the weekly usage percentage in the sidebar
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [zh-CN][Windows Desktop] Usage & billing overview remains partly English in Chinese UI
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Codex returns usage_limit_exceeded while account has 100% usage remaining
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [Feature request] Reduce context/token overhead in long-running Codex development sessions
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- 01a0d4d0-f04f-7813-9a08-57ffb1545ba9
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Useage cut off 12%.
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Bug: Goal kept auto-continuing after scheduled pause and exhausted weekly Pro allowance
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Avoid duplicate quota warning when status line shows limit
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Feature request: user-enforced scheduling lock and sticky pause, independent of subagents
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Make banked Full resets recurring and predictable for heavy Codex users
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][Astra Ultra][Daybreak research blocked] ~50% of my weekly usage gone; repair unfinished after 7h15m
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- VS Code: closing the owning Codex tab leaves a Goal running invisibly and consuming usage
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows] ChatGPT Plus OAuth returns 401 incorrect sk-svcac key after 5-hour usage reset
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Pro — multiple weekly resets exhausted during LexPulse / ~50% Subagent usage / Analytics periods marked incomplete
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- 4 warnings in the TUI that never clear
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Production outage, lies about verification and usage visibility, and wasted paid credits
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Bug: Send button remains disabled globally after OpenAI usage is exhausted
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Usage drained in 11 minutes of 5 hours.
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Auto Resume once usage limit resets
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [ChatGPT Web/Android][Sep 24–26, 2026] Frequent conversation load failures, 429 errors, and delayed image attachments
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Codex credits - usage limit
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- Pro 20x: All models return "Selected model is at capacity" since Sep 23 (72% quota remaining)
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
- [Windows][tr-TR] Usage popover duplicates remaining percentage (%6%6 / %41%41)
First observed: . Last observed: . Present in 41 scheduled observations.
GitHub created: . GitHub updated: .
Latest questions by topic
- Unexpected usage depletion15 this week · steadyUnexpectedly high usage during a long multi-agent task without a cumulative usage checkpoint
- Usage display & /status15 this week · steadyDots: opaque “abuse prevention” breaks undermine always-on reliability; no usage meter or reset information
- “Model at capacity” errors5 this week · steadySelected model is at capacity. Please try a different model.
- Requests to change limits4 this week · ↓ cooling[macOS][Codex Desktop] Sudden ~60% increase in 5h quota usage overnight; large prompt-cache miss on small turn
- Hitting the limit4 this week · ↓ cooling[ChatGPT][Regression] Existing Chat local execution is blocked and redirected to separately-metered Work
- Plan changes & allowance3 this week · ↓ coolingClicking upgrade when prompted your usage remaining is low, it redirects you to a new codex within your codex instead of pricing
This week at a glance
- Most reported
- Unexpected usage depletion
- 15 reports in 7 days
- Fastest rising
- No clear riser
- No topic grew enough to call it a trend.
- New recurring terms
- None this week
- No unfamiliar name recurred across 3+ reports
What changed: 74 usage-related issues were filed in the last 7 days, against 125 the week before. Overall volume is roughly steady. 12 came in over the last 24 hours.
Topics this week
Ordered by reports in the last 7 days. Open a topic for the actual questions, links to each GitHub issue, and what Codex Usage already covers.
Unexpected usage depletionSteady15 this week · 23 the week before
15 reports in the last 7 days, 23 the week before. Roughly steady. 2 in the last 24 hours.
Recent questions
- #51519Unexpectedly high usage during a long multi-agent task without a cumulative usage checkpoint
- #51498GPT-6 Astra Ultra: 14 user-driven turns generated 90 Ultra executions and exhausted purchased credits
- #51445Resetting the usage limit and getting it drained only in 5 minutes
- #51239[Work desktop / Automations] Minutely browser heartbeat ran for 8 days through access failures, consuming Pro usage and credits
Models or modes named in these titles: Astra (4), Sol (4), Luna (4), Reasoning effort (2).
What this shows
About as many reports as the week before. This is a steady, recurring question, not a new spike.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Usage display & /statusSteady15 this week · 27 the week before
15 reports in the last 7 days, 27 the week before. Roughly steady. 1 in the last 24 hours.
Recent questions
- #51540Dots: opaque “abuse prevention” breaks undermine always-on reliability; no usage meter or reset information
- #51365Codex desktop app: show remaining usage limits and reset times in the header
- #51281Show the usage reset date alongside the remaining percentage in the desktop profile menu
- #51177Codex Desktop 26.930.31730: default memory generation fans out into hidden agents and consumes ~15% of 5-hour quota after a 2-minute task
What this shows
About as many reports as the week before. This is a steady, recurring question, not a new spike.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
“Model at capacity” errorsSteady5 this week · 4 the week before
5 reports in the last 7 days, 4 the week before. Roughly steady. None in the last 24 hours.
Recent questions
- #51384Selected model is at capacity. Please try a different model.
- #51054Selected model is at capacity. Please try a different model.  Retry in 45s  Latest response
- #51030Codex macOS app: persistent "Selected model is at capacity" across all conversations despite available usage
- #50252Frequent "Selected model is at capacity" on GPT-6.1-Sol despite 97% 5h and 99% weekly quota remaining
Models or modes named in these titles: Sol (1), Astra (1), Reasoning effort (1).
What this shows
About as many reports as the week before. This is a steady, recurring question, not a new spike.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Requests to change limitsCooling4 this week · 8 the week before
4 reports in the last 7 days, down from 8 the week before (-50%). 2 in the last 24 hours.
Recent questions
- #51604[macOS][Codex Desktop] Sudden ~60% increase in 5h quota usage overnight; large prompt-cache miss on small turn
- #51554[Windows][Astra High] Request to investigate repeated lookups, task distribution, and weekly usage attribution in a long development session
- #51120Request for flexible higher tiers (2x/3x/4x)
- #50596Expose model-request lifecycle, timing, and per-request usage in codex exec --json
Models or modes named in these titles: Astra (1).
What this shows
Fewer reports than the week before. That can mean a fix shipped, or just a quieter week. The issue stream can't tell those apart.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Hitting the limitCooling4 this week · 14 the week before
4 reports in the last 7 days, down from 14 the week before (-71%). 1 in the last 24 hours.
Recent questions
- #51805[ChatGPT][Regression] Existing Chat local execution is blocked and redirected to separately-metered Work
- #51478HTTP 429 with Retry-After prevents loading existing conversations in ChatGPT Web and Windows Desktop
- #51010One dot-delegated task reports usage limit despite available allowance; other delegated tasks work
- #49773"You've hit your usage limit" only when working on SSH remote connection
Models or modes named in these titles: Astra (1), Daybreak (1), Reasoning effort (1).
What this shows
Fewer reports than the week before. That can mean a fix shipped, or just a quieter week. The issue stream can't tell those apart.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Plan changes & allowanceCooling3 this week · 8 the week before
3 reports in the last 7 days, down from 8 the week before (-62%). 2 in the last 24 hours.
Recent questions
- #51549Clicking upgrade when prompted your usage remaining is low, it redirects you to a new codex within your codex instead of pricing
- #51484Thread stuck running — please check credit usage
- #50601[macOS desktop 26.930] Add credits consistently resets UI; View usage also resets intermittently
- #49150Browser Auto-review fails with “workspace is out of credits” despite available Codex usage
What this shows
Fewer reports than the week before. That can mean a fix shipped, or just a quieter week. The issue stream can't tell those apart.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Banked & instant resetsFew reports3 this week · 3 the week before
3 reports this week, 3 the week before. Too few to call a trend. 1 in the last 24 hours.
Recent questions
- #51646Banked usage resets expire at least one hour earlier than the expiration time shown in Codex Desktop
- #51265Auto-apply banked Codex reset at expiration (opt-out)
- #50868[CLI 0.158.0-alpha.2.1] Banked reset consumed immediately after "Use a reset" without expiration details or confirmation
- #49143Usage Decreasing Without My Use and Banked Reset Missing
What this shows
Only a handful of reports. Treat these as individual accounts, not a pattern.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Token accounting & compactionFew reports3 this week · 3 the week before
3 reports this week, 3 the week before. Too few to call a trend. None in the last 24 hours.
Recent questions
- #50586Expose reported token usage for failed and interrupted runs in codex exec --json
- #49961Repeated early compaction across GPT-6.1 Sol and Astra: internal token counts exceed reported usage
- #49757Astra reasoning-token usage differs between ChatGPT Enterprise–authenticated Codex and public Responses API at the same effort
- #49026Automatic compaction double-counts prior reasoning against reported token usage and triggers unnecessary compaction
Models or modes named in these titles: Astra (3), Reasoning effort (2), Sol (1).
What this shows
Only a handful of reports. Treat these as individual accounts, not a pattern.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
Reset timing & windowsFew reports1 this week · 1 the week before
1 report this week, 1 the week before. Too few to call a trend. None in the last 24 hours.
Recent questions
What this shows
Only a handful of reports. Treat these as individual accounts, not a pattern.
Evidence type: community-reported GitHub issues. Not official, not measured by Codex Usage.
How the Pulse works, and what it can't tell you
- Source: public issues in the openai/codex repository. Everything OpenAI labels
rate-limits, plus issues whose titles clearly mention usage, quota, limits or resets. Titles about CPU usage, context limits or usage policy are left out. - Windows: the last 24 hours, the last 7 days, and the 7 days before that, counted back from the update time. Of 229 issues checked in that span, 199 were usage-related.
- Topics: each issue title is matched against fixed rules, with no AI in the loop. An issue lands in one topic only. 55 usage-related issues didn't fit any topic and aren't shown in one.
- Emerging terms: a name that shows up in at least three different issue titles, on more than one day, and isn't part of what this site already covers.
- Trends: a topic is only called rising or cooling when it moves by at least 3 reports and at least half of the previous week. If neither week reaches 5 reports, there's no trend call, and percentages only appear once the previous week has at least 5.
- Limits: GitHub issues come from people motivated enough to file one. The counts show what's being reported, not how many Codex users are affected, and they don't confirm any change on OpenAI's side. Everything on this page is community-reported evidence.
- Freshness: successful scheduled scans are persisted about every 4 hours, then published through a site deployment. Failed scans leave the last successful observation in place. The same data is available as JSON.