OFFICIAL SERVICE REPORT
Service status
- Waiting for OpenAI Status.
Only Codex-named components actually reported by the official API are shown. Other surfaces and your personal quota are unknown.
Open official status ↗YOUR CODEX RESET TIMER
Your next session
starts here.
Track the Codex reset time shown in your account, then save a reminder.
My reset clock
This browser onlyWEEKLY WINDOW
No account reset time set.
—
No reset time is inferred.
Time entered by you · not connected to your account
A little setup. More focus.
Find the reset time in your account, then save it below. Each usage window gets its own clock.
Find my time ↗Set or update reset time
Calendar export downloads a file. Import it into your calendar app to receive a reminder. Android instructions →
Time source & accuracy
When this clock reaches zero, check your account to confirm the reset. A banked, paid or automatic reset may change the next date; update the time here afterward. Countdown accuracy also depends on your device clock.
PUBLIC CODEX UPDATES
Around the Codex community
Official service status and credited public updates. These never determine your personal reset time.
Data: codex-reset.com · Official service state: OpenAI Status
Connecting to this site's data service…
Recent reset records
All current records →“Confirmed” means marked confirmed by the data provider; Reset Watch has not independently observed private accounts.
- Waiting for records.
Latest public posts
Current feed →- Waiting for posts.
Explore the experimental outlook Historical estimates, not your account schedule
HISTORICAL OUTLOOK
Could a community reset happen?
—Next 24 hours
—Within 48 hours
Waiting for source data.
Experimental historical estimate, not a promise or your account reset time. Waiting longer does not raise this memoryless model's odds.
How we calculate this
We use up to eight completed intervals between source-marked confirmed reset records, deduplicate by UTC date, and exclude banked grants, previews and future records. Rate = intervals / total days; P(t) = 1 − exp(−rate × t). Displayed estimates are capped at 46% and 71%. This is our own implementation, not the original provider's exact model or a validated prediction.
PUBLIC WORDING
Latest reset signal
Not checked yet.
A conservative wording rule, separate from the historical percentage. A watch score is a rule level, not a measured probability. Banked grants do not reset this model's clock.
Sources, freshness & limitations
Data: codex-reset.com. Service status: OpenAI Status. Our backend fetches and briefly caches these public sources on request. It does not operate its own X API collector or account-monitoring fleet. No request is sent with your saved personal time or usage.
The visible page checks about every two minutes; source timestamps may be older than our fetch time. If an upstream fails, we show failure or stale data, not the old archived snapshot as a live result.
Community reference & advanced tools Snapshot · 2 Nov 2026
Your usage & the bigger picture
Enter the time shown in your account. No reset time is guessed.
Tibo's 28-day challengeDay 28 / 28Each day: 🚀 one improvement or ✅ a full reset
- Day 28Banked 2/2
- Day 27A new banked Codex reset landed on our monitoring accounts.
- Day 26You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀.
- Day 25We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
- Day 24Text your dot just like anyone else. Makes it super easy to share/forward things, leave it voice notes or you can even…
- Day 23Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though!
- Day 22Terra is back! Our first model that is significantly better at writing, personality and nuanced understanding of requests. Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions.
- Day 21Wonder what happens the remaining seven days. But today is a reset.
- Day 20Rest and reset
- Day 19Small updates. Calls connect much faster for dots, changing reasoning in codex & work mid conversation does not…
- Day 18Decisions API is GA, OpenResponses joined the Linux Foundation, we shipped some performance improvements and Uber is going all-in on codex & work. But yes… that’s a reset!
- Day 17Bet you thought we forgot, but no, it’s reset day today. Also good time to remind you to get Daybreak Blue access, it only takes 15 mins and you don’t want to have to do it in the middle of an incident.
- Day 16You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you…
- Day 15Nevermind, we're still cooking... and reset. Enjoy.
- Day 14Small quality of life improvement. You can now edit previous messages within a thread in the desktop app. Long time…
- Day 13Le limit reset
- Day 12We’ve made improvements to Codex & Work that increase the effective usage you get. We achieved this by reusing…
- Day 11We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive…
- Day 10Reset
- Day 9We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce…
- Day 8Reset
- Day 7We have increased default context length for GPT-6.1 Sol to 500k when used through Codex & Work, up from 272k or an ~ 80% increase.
- Day 6Reset
- Day 5Composer predictions in the desktop app. Often leads to a double take with how on point they are.
- Day 4We have improved steering to be instant, leading to the model now reacting much faster to adjustments you make…
- Day 3The big one is GPT-6 in Chat, but today is also a little celebration day with a new high of 40M active users…
- Day 22.1/ Approve for me (auto-review) is now included and does not use usage. Can be between 2-10% of plan…
- Day 1We have optimized the default speed to be ~50% faster across GPT-6 Astra and GPT-6.1 Sol through the subscription…
Will you make it to your next reset?
how it works
Reference account first; your `/status` time overrides it. Add your usage % to compare pace — all data stays in this browser.
❯ codex /status
the weekly windowCopy the exact time from the /status output in your Codex client.
--%
Account time not set Enter the exact next reset time from your account. No global reset is used as your anchor.
set my usage %slide in the usage from /status
--%
No usage entered Enter your current percentage used.
goodwill & banked resetsCopy the exact future expiry from your account or offer.
--%
No confirmed expiry entered Check the offer’s exact expiry.
❯
enter the exact time from /status · slide in the usage from /status · paste /status instead · / Command palette
Historical community outlook · 2 Nov 2026 snapshot
Did Codex reset today? No — not so far today (UTC). The latest verified global reset was 5 days ago (Oct 28, 6:35 AM UTC).
last global reset
5 days ago
- 61 global resets
- 12 banked resets
- pace ≈ every 2d
❯ will codex reset? No live account connection signals
Model outlook
🎟️A new banked Codex reset landed on our monitoring accounts.latest banked alert · 5 hours ago
🎟️A new banked Codex reset landed on our monitoring accounts.latest banked alert · 5 hours ago
teased · not a promisecast your vote
>0%
—
Next 24h
—
By 48h
Historical peak
12 PM - 3 PM
Your local time · GMT+8
Signal status
Not live
Archived community data
👀
Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what …
counted · 48% in 24h · 73% in 48h · · @thsottiaux
48% in 24h · 73% in 48h
@thsottiaux
FORECAST NOTES
Global reset outlook, without black-box scoring
No official reset window has been announced right now.
Codex reset calendar
see the reset rhythm chart- verified reset
- last global reset
- banked reset update· not a reset · never moves the clock
All-time median gap: 3.4 days · last 30 days: 2.0 days · tracked since Sep 2025
Goodwill resets verified from @thsottiaux posts · a rhythm, not a schedule.
what is this?
This model tracks irregular goodwill resets for everyone. Your personal burn meter above stays private and account-specific.
Experimental · not above baseline You have waited 4.9 days; 100% of the latest 8 completed reset intervals were shorter. Typical wait 2 days, average 1.9, longest 2.6. Recent history, not a schedule. This historical baseline uses up to 8 completed intervals. Ordinary posts and hints are not extra probability factors. Sample through 2026-10-28 06:35:38 UTC.
👀 Tibo, last 7 days: a hint on Oct 31 — "Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what …". Counted: 48% in 24h, 73% in 48h — a floor on the displayed number, not the historical base rate. It lapses 60h after the post, or the moment a reset lands.
The homepage answers one question first: when could a new reset signal appear? Waiting longer does not raise the odds — models that treated a reset as becoming "due" scored worse in the backtest, so the 24h number stays flat while the quiet stretch runs.
- Recent cadence: a reset every ~1.5d across the last 5 (weighted mean 4d) Details
- Last reset: 2026-10-28 (4.9d ago) Source
- Most common window: 12 PM - 3 PM in Asia/Singapore Details
open verified timeline · see the reset rhythm chart · open full Tibo radar
RADAR
Did Codex reset today?
Tibo's latest posts, classified live into reset, banked and limits signals, next to the verified reset log and the hour-of-day pattern.
I demand a banked reset
180232KBanked 1/2
1.6K2289.8KDay 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀. t.co/iQxsqbuk0f
2.6K64814KBetter announce 28 days of reset
7141437.7KGood list
709928Graduating from The Reset Company to The Token Company.
8121698.7KDay 25/ We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
7.4K2.7K39KMaybe it’s because I have bad long term memory.
9781.4KLands by midnight PST.
452582.2KDay 23/ Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though! t.co/tHe09XkVXH
1.1K3488.3KWhat's going on
12771.3KDay 22/ Terra is back! Our first model that is significantly better at writing, personality and nuanced understanding of requests. Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions. t.co/1ilnCkAPuy
2.7K46610KNot enough resets
161151.7KDay 21/ Wonder what happens the remaining seven days. But today is a reset.
2.4K43111K- 5241.6K
Not a real improvement, put the reset in the bag
68162.2KBy midnight PST
358562.2KDay 20/ Rest and reset
1.2K47212KOne day
693594On codex cli updates. We've added reusable prompt presets, inline model and permission settings, and enterprise MCP sign-in. We've also fixed failures when resuming long sessions and added Windows corporate-proxy authentication. Surprisingly the CLI has grown 2X in usage since devday.
225321.8K
recorded global limit events
- 2026-11-01BANKED · AVAILABLEA new banked Codex reset landed on our monitoring accounts.
- 2026-10-31BANKED · AVAILABLEA new banked Codex reset landed on our monitoring accounts.
- 2026-10-28RESETLands by midnight PST.
- 2026-10-28RESETDay 23/ Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though! https://t.co/tHe09XkVXH
- 2026-10-26RESETDay 21/ Wonder what happens the remaining seven days. But today is a reset.
- 2026-10-25RESETBy midnight PST
- 2026-10-23RESETLanding tomorrow before 10am PST together with a small ship.
- 2026-10-23RESETDay 18/ Decisions API is GA, OpenResponses joined the Linux Foundation, we shipped some performance improvements and Uber is going all-in on codex & work. But yes… that’s a res
avg 6d between recorded events
What time of day do Codex resets happen?
Every recorded announcement, bucketed by hour in your timezone. Resets cluster in the US afternoon — if you're waiting on a goodwill reset, that's the window to watch.
80 announcements bucketed by hour in your timezone (Asia/Singapore) · peak 07:00
LIMITS(5)
How Codex usage limits work
the 5-hour window
The short clock. Local messages (CLI, IDE extension, desktop app) and cloud chats draw from one shared 5-hour budget — they are not separate allowances. When your Codex CLI reports this window, /status shows its percentage left and reset time; use the rows your own client actually prints.
the weekly window
The ceiling behind it, running seven days. OpenAI has never published how large it is for any plan — the official pricing page says only that "additional weekly limits may apply". Clearing a 5-hour window does not restore weekly budget; the two refill independently.
what a reset actually is
The reset time is not computed on your machine. OpenAI's servers send an absolute resets_at timestamp with each usage report, and the CLI just renders it. A reset restores your percentage to 100% — it doesn't add credits or change your plan. Community reports suggest each window's clock starts on your first request after a reset, though OpenAI hasn't confirmed that.
goodwill & banked resets
Separately from scheduled windows, OpenAI may apply an automatic reset or save a banked reset for later. A banked grant does not refresh usage; redeeming a full banked reset resets both 5-hour and weekly windows. Referral resets normally use a 30-day window unless the offer says otherwise; every grant follows the expiry shown by its offer or account.
5-hour limit status: OpenAI lifted the 5-hour restriction for paid plans on Jul 12, 2026 and brought it back for Plus accounts on Aug 26, 2026 (announced by Tibo a day ahead to smooth compute load). OpenAI's pricing page now says Pro plans have no 5-hour limit, so Pro runs on the weekly limit only; Plus and Business keep 5-hour estimates. Treat your own /status output as the live truth.
Will it last until reset?
Enter your weekly reset time and percentage used in the tracker.
Example: 70% left → enter 30% used.
Your entries stay in this browser. Pace is an estimate, not a live account reading.
messages per 5-hour window · Plus $20 and Business
| model | local messages / 5h | credits per 1M tokens · in / out |
|---|---|---|
| GPT-6 Astra | 5–45 | 250 / 1,250 |
| GPT-6.1 Sol | 15–160 | 50 / 250 |
| GPT-6.1 Terra | 35–285 | 25 / 125 |
| GPT-6 Sol | 15–150 | 50 / 250 |
| GPT-6 Luna | 350–3,000 | 2.5 / 12.5 |
OpenAI's estimates, not fixed caps: real counts move with task size, context, reasoning effort and caching. Pro $100 / $200 / $500 has no 5-hour limit, only the weekly one.
weekly allowance by plan
| plan | 5-hour limit | usage vs Plus | ≈ API $ per week |
|---|---|---|---|
| Plus $20 | yes | 1× | ~$66 |
| Pro $100 | none | 5× | $330–380 |
| Pro $200 | none | ~10× (reported) | $640–670 |
| Pro $500 | none | 25× | ~$1,010–1,640 |
| Business | yes, per seat | not published | not measured |
OpenAI publishes no weekly number and says API prices should not be used to estimate included usage; the dollar column is third-party measurement and projection, a rough scale only, not a cap or a balance. Every figure with its original source: Codex usage · Verified 2026-10-27.
FAQ
Codex reset questions, answered
When does my Codex 5-hour limit reset?
Your Codex client shows the windows currently returned for your account. Run /status in the Codex CLI and read the percentage left and reset time from the limit-window rows it actually prints. If a 5-hour limit (quota) row appears, enter that row's reset time in the tracker above; if it does not, do not infer one from this page.
When does the Codex weekly limit reset?
Seven days on its own clock, shown in the "Weekly limit" row of /status for your weekly quota. There is no universal weekly reset moment shared by everyone: community reports consistently indicate each account's window anchors to its own first request after the previous reset. That's why this tracker asks for your reset time instead of pretending one global countdown fits all.
How big is the weekly limit on my plan?
OpenAI does not publish it. The official pricing page says only "additional weekly limits may apply" and gives no weekly number for any plan — anyone quoting an exact weekly cap is guessing. What is documented: the weekly window runs seven days and refills independently of the 5-hour window.
Did Codex reset today?
Check the radar above — it watches @thsottiaux (the Codex lead, who announces virtually every goodwill reset), flags rate limit reset announcements automatically, and shows how long ago the last one landed. OpenAI has granted at least 56 recorded global resets since September 2025, including 10 in the twelve days after GPT-5.6 launched, and the GPT-6 Astra rollout (Sep 3–5, 2026) added a banked reset for every day a paid account lacked Astra plus a full banked reset for all Plus, Pro and Business users once it reached everyone.
Does clearing my 5-hour window restore my weekly limit?
No. They are independent budgets refilling on separate schedules. If your weekly window is exhausted, a fresh 5-hour window won't unblock you — you need the weekly rollover, a goodwill reset, a banked reset, or credits.
Are Codex limits separate from my ChatGPT chat limits?
Yes, but Codex isn't alone in its pool: Codex, ChatGPT Work, ChatGPT for Excel and Workspace Agents all share one agentic usage pool. Ordinary ChatGPT chat has separate caps and never drains Codex budget — a heavy ChatGPT Work session will, though.
What is a banked reset, and when does mine expire?
A reset saved to your account until you choose to redeem it. The grant itself does not refresh usage; a full redemption resets both the 5-hour and weekly windows and moves the weekly date to roughly seven days later. Referral resets normally must be used within 30 days unless the offer says otherwise, while milestone, compensation, and one-time grants follow the expiry shown by the account or offer. Read the banked reset guide
Can I buy a Codex reset?
Yes, if your account is offered one. Eligible ChatGPT Plus and Pro personal accounts can buy an instant reset from Usage settings in the desktop app ("Buy an instant reset") or from the offer that appears once the weekly limit is used up; it is not available on Free, Go, Business, Enterprise or Edu, and being on the right plan does not guarantee the option. It restores your 5-hour and weekly usage immediately, even if you still had some left, pulls your normal weekly allowance forward instead of adding extra, cannot be saved for later, and is generally not refundable. Source: OpenAI Help Center: Paid weekly Work and Codex rate limit resets.
Tibo posted a reset but my usage hasn't changed. Why?
A global reset rolls out over time — Tibo's own posts often say it is still propagating — so give it a while. "Global" also does not mean every account or every limit: OpenAI applies it to the accounts and limits the offer selects, so check who the post covers. If the post announced a banked reset, nothing refills until you redeem it in Usage settings. Usage can also take a moment to update: refresh or reopen Usage settings and confirm you are on the right account and workspace. OpenAI asks you not to spend a banked reset or buy one just to test whether the first one worked. Source: OpenAI Help Center: How resets work in Codex.
Why did my weekly reset date change after a reset?
A reset that restarts a usage period replaces the old schedule. If a weekly period due to end on Friday restarts on Tuesday, its next refresh is the following Tuesday and the Friday refresh no longer applies; after a purchased reset, the new week starts with your first Work or Codex request, not at checkout. Banked, global and paid resets can all do this without touching your subscription billing date, so read the next refresh time from Usage settings (or /status in the CLI) instead of counting from an announcement. Source: OpenAI Help Center: How resets work in Codex.
What time of day do Codex resets usually happen?
From the 50 recorded announcements: they cluster between 17:00 and 23:59 UTC — US afternoon — with a secondary bump just after midnight UTC. The histogram above localizes every announcement to your timezone. Day of week is nearly uniform, so don't bother planning around one.
What happens when I hit a limit mid-task?
OpenAI lets the agent finish the turn in progress (subject to fair use), then blocks new turns until a window clears. Your session and history stay put. Options: wait it out, spend a banked reset, buy credits (Plus/Pro: Settings → Usage → Credits; valid for 12 months), switch to a lighter model like GPT-6 Luna (its 5-hour estimate on Plus is roughly 70× Astra's), or move the task to an API key.
Can I dodge subscription limits with an API key?
Yes, with a trade-off: signing Codex in with an API key bills per token at standard API rates and removes the 5-hour and weekly windows entirely — but you lose the cloud features (GitHub code review, Slack, Codex cloud), and your only ceiling is the spend limit you configure.
Is the 5-hour limit still lifted?
For Pro, yes; for Plus and Business, no. OpenAI removed it for paid plans on July 12, 2026 during the GPT-5.6 demand surge, then Tibo announced on August 25 that the 5-hour limit would return for Plus accounts across ChatGPT Work and Codex the next day, to smooth compute load. OpenAI's pricing page now says Pro plans have no 5-hour limit, so Pro runs on the weekly limit only, and it publishes 5-hour estimates for Plus and Standard Business. Check your own /status for the live answer, and watch the radar either way.
Does GPT-6 Astra have its own usage limit?
No separate meter. Astra is included in the normal allowance on every paid plan and you can spend 100% of it on Astra, but it is the most expensive model in the pool: OpenAI estimates 5–45 local messages per 5-hour window on Plus, against 15–160 for GPT-6.1 Sol and 350–3,000 for GPT-6 Luna, and Fast mode spends Astra usage at 2.5× its standard rate. During the Sep 3–5, 2026 rollout OpenAI banked one reset per day for paid accounts without Astra, then a full banked reset for all Plus, Pro and Business users.
Can this site see my real Codex usage?
No — this site never touches your OpenAI account. Your real numbers live on ChatGPT's Usage settings page at https://chatgpt.com/settings/usage or run `/status` in the CLI. OpenAI provides no public personal-quota API for this site, so your countdown, notifications, and calendar export still run only in your browser. The public announcement feed remains available at `/api/feed`.
What Reset Watch can tell you
Your personal reset time comes from your Codex Usage display or client. Enter that time and its timezone here; weekly and 5-hour windows are independent. Public community records and historical estimates cannot determine your private account schedule.
Saved times stay in this browser. Calendar export creates a file you must import; it does not enable background push notifications. Reset Watch is an independent tool, not an OpenAI product.
Public updates & account clock · Set your account time · Help & calendar instructions · Official reset guide ↗