Use the next refresh shown in your own account. An announcement or community prediction cannot tell you when your personal allowance returns.
From account display to a saved timer
Open your account’s usage display. Start with Usage settings ↗. In the desktop app, look for Settings → Usage & billing. If your client exposes usage or status details, use the information it actually shows; commands and labels may vary.
Choose the allowance you want to track. Read its next refresh time. If your account shows both weekly and 5-hour windows, record each separately. Their end times can differ.
Match the date, time and timezone. Use the explicit offset when a daylight-saving clock change makes a local time ambiguous. Do not calculate a new date from a purchase or announcement.
Save and cross-check. Open the timer below, select the window, enter its time and save. Compare the UTC line with your input. If your account later shows a different time, update the saved entry.
Illustrative input, not an account reading: 10 November 2026 at 18:00 with a fixed UTC−05:00 offset is 10 November at 23:00 UTC, or 11 November at 07:00 in UTC+08:00. All three refer to the same instant.
A fixed offset does not follow daylight-saving changes. Use the offset for the date your account shows. Also check your device clock; the countdown depends on it.
What if Usage does not show a time?
Leave that window unset rather than guessing. Check the account again or consult official support. A banked reset, paid reset or automatic offer can affect the next refresh; the account display remains the reference.
Source checked 9 November 2026: OpenAI’s reset guide ↗. This explains the workflow, not a promise that every plan has the same windows or reset offers.
YOUR TIME, BACK IN FOCUS
Your next Codex reset.
Save the time from your account. Know when to check back.
WEEKLY WINDOW
No account reset time set.
—
No reset time is inferred.
Source: your account time, entered by you. Not connected to OpenAI.
Start with your account time.
Open your Codex Usage page, then enter its next reset time and timezone below. We never guess your account schedule.
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.
Use the exact time shown in your account. Weekly and 5-hour windows are independent. Your entries stay in this browser; they do not sync between devices.
A few things worth knowing
Read the next reset in your account again after any banked, paid or automatic reset.
Check the weekly and 5-hour windows separately.
Use the timezone shown beside the account time. Check your device clock too.
Browser reminders stop when the page closes; import a calendar reminder for later.
Copies build, timezone and tracker status only. No credentials or exact saved reset times are included. Nothing is sent automatically.
CODEX / USAGE / RESET
Your usage & the bigger picture
Paste your /status and see whether you make it to the reset.
Everything here stays in this browser. No account, no upload, no cookie.
codex-usage --forecast
When does the next reset land?
Call the next verified reset. Community results unlock after enough forecasts, and every round is scored against what happened.
Community forecast
Model forecast:
Fetching the current reset…
Community unlock{count} / {min} forecasts
No reset landed in the last round — it closed at "not anytime soon" and this one reopened on the weekly refresh.
What readers expect
These percentages are reader expectations, not this site's forecast. The model number beside them is calculated from verified reset history and is never mixed with the vote.
The dashboard shows one number today. Log it a few times across the week and the shape appears: how fast you are actually burning, how much you can spend per day and still make it, and when you run out if nothing changes.
remaining now—
cycle elapsed—
readings this cycle—
sustainable pace your burn
codex-usage --reference-cycle
What a real cycle looks like
Archived example from codex-reset.com, captured 2 November 2026. Reset Watch did not collect these readings. This single-account illustration is not your account history or a population estimate.
Source: this site's own monitored account. Not OpenAI data, and not an average of users.
what is left, and where it went over the last days
5-hour window
when returned — live percentage and reset time
observed: a 5-hour limit card on one account, none on another
weekly window
yes — live percentage and reset time
yes — percentage left and a countdown ("Resets in 5d 1h")
history
no
yes — Analytics tab, 7 or 30 days
by chat / feature / model / surface
no
yes — Analytics tab
freshness
read at the moment you run it
limit cards live; Analytics aggregated and later
Run /status when you are deciding whether to start another task. Open the Analytics tab when you want to know which chat, feature, model or surface consumed the window.
codex-usage --limits
Codex limits by plan, with sources
The home page keeps the two core tables. This is the full reference: what OpenAI states, what others have measured, and where each figure comes from. Your own balance is in Usage or /status; the dollar values describe the work a full week bought, not money you hold.
one full weekly allowance in API dollars
one full weekly allowance in API dollars
plan
usage vs Plus
basis
≈ API $ per full week
Plus $20
1×
Projected from logged work; one full window with some unlogged usage, all GPT-6 Astra, came to about $62. [10]
Two estimates that disagree: 25 × the Plus figure gives ~$1,640; one night of logs put it at 0.77–1.05× the old Pro $200 rate, about $1,010–1,380. [10][11]
~$1,010–1,640
Business
not published
No comparable public sample yet.
unknown
OpenAI: "API token prices are separate from subscription usage; don't use them to estimate included tasks." These dollar figures are third-party valuations that do exactly that, so read them as a rough scale. [1]
Another Pro $100 study reports $103–237 a week after repricing; methods and model mixes differ, so the two are not one measured range. [12]
Through Oct 29, 2026, eligible Pro $200 subscriptions from before Sep 29 keep their older, larger allowance; one author measured it at about $1,300 a week on two accounts. [5][11]
Pro $100 / $200 / $500 has no 5-hour limit, only the weekly one. GPT-5.6 Sol, Terra and Luna stay in the model picker without published 5-hour estimates; GPT-5.5 left Codex on Oct 14, 2026. The last column applies only when Codex signs in with an API key. [1]
the 5-hour counts at API-key prices
What OpenAI's 5-hour message ranges would cost if the same work ran through an API key, at an example message size you choose. It is not a measured 5-hour or weekly allowance and does not change your plan's limits.
Enter whole numbers: input 1–272,000; output 0–128,000; cached share 0–100%.
the 5-hour counts at API-key prices
model
messages / 5h
example $ with an API key
GPT-6 Astra
5–45
$1.00–$9.00
GPT-6.1 Sol
15–160
$0.60–$6.40
GPT-6.1 Terra
35–285
$0.70–$5.70
GPT-6 Sol
15–150
$0.60–$6.00
GPT-6 Luna
350–3,000
$0.70–$6.00
Illustration only: Standard speed, text requests up to 272,000 input tokens; no cache-write charges, tools, images, regional uplifts or taxes. Not a claim about a typical Codex message.
Message ranges do not set a dollar budget, and OpenAI says API prices are not a way to estimate included usage. Changing the example changes this column only. [1][8]
plan-level summary
plan-level summary
plan
codex access
when you hit the wall
Free / Go
included for quick, lightweight tasks — no published numbers
wait for the window to roll over
ChatGPT Plus $20
GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna across CLI, IDE, web, cloud
buy credits (Settings → Usage → Credits) or wait
ChatGPT Pro $100 / $200 / $500
no 5-hour limit, weekly limit only; more usage per tier, Ultrafast on Pro 500
credits with auto top-up, or wait
Business
Plus per-seat 5-hour windows + admin controls
workspace credits
Enterprise / Edu
flexible pricing = no fixed rate limits; usage scales with credits
credits pool
OpenAI API key
pay per token — no 5h or weekly windows at all
only your own spend limit (loses cloud features)
Codex, ChatGPT Work, ChatGPT for Excel and Workspace Agents share one agentic usage pool; ordinary ChatGPT chat is metered separately and never drains it. Astra draws on that same allowance on every paid plan — 100% of it can go to Astra — at 5× GPT-6.1 Sol's credit rate. OpenAI says a typical GPT-5.6 Sol task may use 2–15 credits; credit prices vary by account and region, and purchased credits expire after 12 months. [2]
How the dollar figures are made
Each study prices the work logged in a window at API list prices, then divides by the share of the weekly allowance that window used. Activity missing from the logs, from another device or from cloud tasks, makes the result too low.
The sources use different methods and model mixes, and this site has not rerun their private logs. No dollar price per credit is assumed here; OpenAI does not publish one.
Pro $500 has no clean measurement yet: the 25× multiplier is official, the dollar figures are not. [3][11]
What uses the weekly allowance faster
The work itself: task size, context, reasoning effort, tool use and caching all change consumption. Local messages and cloud tasks share one allowance.
Image generation uses included limits about 3–5× faster than similar turns, and Voice in the desktop app costs $0.05 of Codex budget per minute. [1]
Fast mode spends included usage at 2.5× the Standard rate. Ultrafast, on GPT-6 Astra and GPT-6.1 Sol with Pro $500, spends it at 8×; purchased credits use 2× and 6×. [6]
Apps connected through Sign in with ChatGPT draw on the same plan; in Settings → Usage you can cap each one at a percentage of your weekly usage. [7]
Sources checked 2026-10-27. Figures change; the linked pages win over this summary.
codex-usage --explain-dashboard
What every block on the dashboard means
Archived dashboard notes from codex-reset.com, captured 2 November 2026. Reset Watch did not independently observe these account screens. Labels and availability may have changed; consult your current account display and official guidance.
plan limits
The first card on the Overview tab. It says the limits are shared across Codex, Work, Workspace Agents and ChatGPT for Excel, and that Chat conversations are not included. Below sit a Weekly limit card and, on some accounts, a 5-hour limit card, each with the percentage left and a countdown such as "Resets in 5d 1h".
easy to misread: It is a percentage, not a quantity. OpenAI publishes no weekly cap for any plan, so 45% left cannot be converted into a number of messages. The countdown is relative, so note when you read it.
recent plan usage
"How your activity draws down your allowance": a chart of your balance over time, with a 5-hour / Weekly switch where both limits apply and a View usage history link into the Analytics tab.
easy to misread: Both accounts observed on Oct 17, 2026 read "Balance history isn't available yet". The chart is new and fills over time; an empty one says nothing about your week.
credits
Credits keep Work and Codex running once you reach a usage limit. The card shows the credits remaining as the current balance, an Add more button, and an Automatic reload switch that tops the balance up.
easy to misread: Zero credits is the normal state for someone who has never bought any — it is not an error, and it is not your weekly limit hitting zero.
Usage limit resets
The section says "Use a reset to restore your 5-hour limit, weekly limit, or both" and has two tabs: Available, with a count, and History. Each saved reset shows as "Full reset" (on one account "Full reset (Weekly + 5 hr)") with its exact expiry and a "Use reset" button, as in the Codex app's usage summary.
easy to misread: Seeing Full reset means the reset is available, not already applied. Your percentages change only after you choose Use reset, and two saved resets can expire on different dates: copy each expiry rather than assuming one lifetime.
credit history
The Overview tab ends with Credit usage history, a paged list of credit spend by date and product (Desktop App, for example) that reads "No credit usage recorded yet" until credits are spent. The Analytics tab adds Credits history, the same spend over 7 or 30 days, by product.
easy to misread: Both record credit spend only. Ordinary in-plan usage never appears there, so an empty list says nothing about how heavy your week was.
usage history
The first chart on the Analytics tab: how plan usage and credits were consumed in Work, Codex and other agentic tasks, with Chat conversations left out. Split it By feature (Chats, Subagents, Agent-created chats, Computer history, Memory updates, Automations, Auto review, Proactive suggestions, Chat titles, Suggestion safety checks), By model, By surface or By turn start.
easy to misread: "Chats" here are Codex and Work threads, not ChatGPT conversations. Background features draw on the same limit: subagents, automations, memory updates and auto review can use the window while you are not typing.
top chats
"Compare each chat's plan and credit usage": your heaviest threads, each with the share of the 5-hour and weekly limit it used, the credits it spent, its mix of model, reasoning effort and speed, and an Open chat link.
easy to misread: This is the block that answers "what ate my week". A single long thread at a high reasoning effort can take a large share of the weekly limit by itself.
plan usage history
A table of past weekly-limit periods with the % of the limit used in each, broken down by feature.
easy to misread: Older periods can read "Some usage is unavailable; this period may be incomplete" or "Breakdown isn't available for this period": a low figure there may be missing data, not a light week.
tool activity
Which plugins and skills were used over time, with the time it was last updated: Plugins called and Skills used, each broken down by name.
easy to misread: These count invocations, not consumption. They are useful for spotting a skill that fires far more often than you expected, not for attributing budget.
messages
The number of messages sent over 7 or 30 days, By model (the live routing set, for example gpt-6-astra, gpt-6.1-sol, gpt-5.6-terra and gpt-5.6-luna) or By surface (Desktop, CLI, Other).
easy to misread: A message is not a unit of cost. A long Astra turn at high reasoning effort and a one-line Luna reply both count as one.
the controls
Two tabs: Overview for the live limits, credits and saved resets, Analytics for the history. Each Analytics chart has its own 7d / 30d range and its own breakdown menu: By feature, By model, By surface or By turn start for usage history, By model or By surface for messages, By product for credits history.
The ranges apply to the Analytics charts only; the limit cards on the Overview tab are always live. The custom range, the Group by selector and the Code review tab of the August page are gone.
Dashboard anatomy observed 2026-10-17
codex-usage --faq
Codex usage questions, answered
Where is the Codex usage dashboard?
It is in ChatGPT settings, on the Usage page (since October 2026); before that it sat in Codex settings as "Codex and Work Analytics". The Overview tab carries the plan limits, credits and saved resets; the Analytics tab carries the history. https://chatgpt.com/settings/usage
How do I check Codex usage without opening a browser?
Run /status in an active Codex CLI session. Read the live percentage remaining and reset time from the limit-window rows your client actually prints; the returned set of windows can vary.
Why does the dashboard not show my 5-hour limit?
It depends on the account. On Oct 17, 2026 one account's Usage page showed a 5-hour limit card next to the Weekly limit card, and another showed the weekly card only. OpenAI can return different window sets by plan and account, so read the cards on your own page and compare them with /status.
Where did the GPT-5.3-Codex-Spark meter go?
Neither account observed on Oct 17, 2026 showed a Spark card on the new Usage page; the August page had a Spark 5-hour and a Spark weekly card. If your page shows one, it is a separate allowance with its own percentage and reset time, and spending it does not touch your weekly window.
How do I find which chat used up my week?
Open the Analytics tab and read Top chats: each of your heaviest threads shows the share of the 5-hour and weekly limit it used, the credits it spent, and its model, effort and speed mix.
Does ChatGPT Work usage count against my Codex limit?
Yes. The Plan limits card says so outright: the limits are shared across Codex, Work, Workspace Agents and ChatGPT for Excel. Chat conversations are not included, so they never drain it.
How many messages is 20% of my weekly limit?
Unknowable from the Usage page. OpenAI publishes per-5-hour message ranges per plan but no weekly cap for any plan, so the weekly meter is a percentage of an undisclosed total. Anyone quoting an exact weekly message count is guessing.
Why did my usage percentage jump without me running anything?
Background work draws on the same limit: subagents, automations, memory updates, auto review, cloud tasks and Work sessions can use it while your terminal sits idle. Usage history By feature on the Analytics tab shows which; its charts are aggregated, so compare against /status, which reads live.
Where do I see and use a saved reset?
In the Codex app, open the profile usage summary. On the web, open ChatGPT Settings → Usage (the Overview tab). Look for the section named "Usage limit resets", then review the Full reset expiry and choose Use reset only when you want the listed windows restored. Read the banked reset guide
Would a reset actually help me?
Not always. A reset refills the weekly window and also restarts it from that moment, so if you were still holding most of your quota the top-up is small and your next rollover moves later — you can end up hitting the limit at a time you otherwise would not have. The reset-value calculator plays both futures forward from numbers you type. Was that reset worth it?
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.
