[Rate limits] 5-hour usage window missing from /status on ChatGPT Plus

Open 💬 9 comments Opened Jul 13, 2026 by zenglowups
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex CLI is running?

codex-cli 0.144.3

What subscription do you have?

ChatGPT Plus

Which model were you using?

gpt-5.5, reasoning xhigh, summaries auto

What platform is your computer?

Microsoft Windows 11 Pro 10.0.26200 64-bit

What terminal emulator and version are you using (if applicable)?

Windows Terminal with Windows PowerShell 5.1

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1783964455s since unix epoch",
  "overallStatus": "ok",
  "codexVersion": "0.144.3",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "C:\\Users\\Admin\\.codex\\app-server-control\\app-server-control.sock",
        "daemon state dir": "C:\\Users\\Admin\\.codex\\app-server-daemon",
        "mode": "ephemeral",
        "pid file": "C:\\Users\\Admin\\.codex\\app-server-daemon\\app-server.pid (missing)",
        "settings": "C:\\Users\\Admin\\.codex\\app-server-daemon\\settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "C:\\Users\\Admin\\.codex\\app-server-daemon\\app-server-updater.pid (missing)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth file": "C:\\Users\\Admin\\.codex\\auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "C:\\Users\\Admin\\.codex",
        "config.toml": "C:\\Users\\Admin\\.codex\\config.toml",
        "config.toml parse": "ok",
        "cwd": "C:\\Users\\Admin",
        "enabled feature flags": "<redacted>",
        "feature flag overrides": "none",
        "feature flags enabled": "35",
        "log dir": "C:\\Users\\Admin\\.codex\\log",
        "mcp servers": "1",
        "model": "gpt-5.5",
        "model provider": "openai",
        "sqlite home": "C:\\Users\\Admin\\.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.51.2.windows.1",
      "details": {
        "PATH git #1": "C:\\Program Files\\Git\\cmd\\git.exe",
        "PATH git entries": "1",
        "git build options": "git version 2.51.2.windows.1; cpu: x86_64; built from commit: bd2ecbae58213046a468256b95fc4864de25bdf5; sizeof-long: 4; sizeof-size_t: 8; shell-path: D:/git-sdk-64-build-installers/usr/bin/sh; feature: fsmonitor--daemon; libcurl: 8.16.0; OpenSSL: OpenSSL 3.5.4 30 Sep 2025; zlib: 1.3.1; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
        "git exec path": "C:/Program Files/Git/mingw64/libexec/git-core",
        "git version": "git version 2.51.2.windows.1",
        "repo detected": "false",
        "selected git": "C:\\Program Files\\Git\\cmd\\git.exe"
      },
      "remediation": null,
      "durationMs": 88
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "C:\\Users\\Admin\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "current executable": "C:\\Users\\Admin\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "install context": "standalone (windows, package C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc, bin C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\codex-path)",
        "managed by bun": "false",
        "managed by npm": "false",
        "managed by pnpm": "false",
        "managed package root": "not set"
      },
      "remediation": null,
      "durationMs": 64
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "MCP configuration is locally consistent",
      "details": {
        "configured servers": "1",
        "disabled servers": "0",
        "stdio servers": "1"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "proxy env vars": "none"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT base URL": "https://chatgpt.com/backend-api/ reachable (HTTP 403)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 72
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv6",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "models etag present": "true",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 569
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running standalone on windows-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "C:\\Users\\Admin\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "install method": "standalone (windows, package C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc, bin C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\codex-path)",
        "platform": "windows-x86_64",
        "version": "0.144.3"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "C:\\Users\\Admin\\.codex\\packages\\standalone\\releases\\0.144.3-x86_64-pc-windows-msvc\\codex-path\\rg.exe",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "none",
        "execve wrapper helper": "none",
        "filesystem sandbox": "restricted",
        "network sandbox": "restricted"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "C:\\Users\\Admin\\.codex (dir)",
        "active rollout files": "64 files, 9731902921 total bytes, 152060983 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "C:\\Users\\Admin\\.codex\\goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "C:\\Users\\Admin\\.codex\\logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "C:\\Users\\Admin\\.codex\\log (missing)",
        "memories DB": "C:\\Users\\Admin\\.codex\\memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "sqlite home": "C:\\Users\\Admin\\.codex (dir)",
        "standalone release cache": "1 entries in C:\\Users\\Admin\\.codex\\packages\\standalone\\releases",
        "state DB": "C:\\Users\\Admin\\.codex\\state_5.sqlite (file)",
        "state DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 238
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "ok",
      "summary": "rollout files and state DB thread inventory agree",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "64",
        "rollout DB active rows": "64",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "0",
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai=64",
        "rollout DB rows": "64",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "subagent:other=36, vscode=27, cli=1",
        "rollout DB stale rows": "0"
      },
      "remediation": null,
      "durationMs": 44035
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language en-US",
      "details": {
        "EDITOR": "not set",
        "VISUAL": "not set",
        "os": "Windows 10.0.26200 (Windows 11 Professional) [64-bit]",
        "os language": "en-US",
        "os type": "Windows",
        "os version": "10.0.26200"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "color output": "enabled",
        "console input code page": "852",
        "console output code page": "852",
        "stderr console mode": "0x00000007 (VT processing: true)",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout console mode": "0x00000007 (VT processing: true)",
        "stdout is terminal": "true",
        "terminal": "unknown",
        "terminal size": "120x30"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "cwd",
        "terminal title project value": "Admin",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 0
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.144.3",
        "check for update on startup": "true",
        "last checked at": "2026-07-13T17:29:33.322098800Z",
        "latest version": "0.144.3",
        "latest version status": "current version is not older",
        "update action": "standalone installer",
        "version cache": "C:\\Users\\Admin\\.codex\\version.json"
      },
      "remediation": null,
      "durationMs": 365
    }
  }
}

What issue are you seeing?

I am using Codex CLI 0.144.3 on Windows with a ChatGPT Plus subscription.

The official Codex pricing documentation currently states that local messages share a five-hour usage window and that additional weekly limits may also apply.

However, /status on my account displays only:

Weekly limit: 59% left
Resets at 21:58 on 19 Jul

The five-hour usage meter and its reset timer are completely missing. The same five-hour meter is also absent from Settings > Usage & billing.

Please investigate whether this is:

  1. A Codex CLI or Usage & billing display bug
  2. A backend quota/accounting problem
  3. An account entitlement problem
  4. An intentional change that has not been documented

Please also verify whether my weekly included usage is being calculated correctly. My weekly allowance is being consumed while no five-hour window is displayed.

Reproduction steps:

  1. Sign in to Codex CLI with a ChatGPT Plus account.
  2. Start Codex CLI 0.144.3 on Windows.
  3. Run /status.
  4. Observe that only the weekly limit is displayed.
  5. Open Settings > Usage & billing.
  6. Observe that the five-hour usage window and reset timer are also missing.

What steps can reproduce the bug?

Uploaded thread: 019f5c86-effa-74b2-8ad5-0d02998668ce

What is the expected behavior?

For a ChatGPT Plus account, /status and the Usage & billing page should display the five-hour usage window and its reset time alongside any applicable weekly limit.

If the five-hour window has intentionally been removed or replaced, the product and documentation should clearly explain the new limit system.

Additional information

Feedback was already uploaded through the Codex CLI.

Uploaded feedback thread:
019f5c86-effa-74b2-8ad5-0d02998668ce

Observed on: 13 July 2026
Codex CLI version: 0.144.3

View original on GitHub ↗

9 Comments

github-actions[bot] contributor · 1 month ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #32791
  • #32707

Powered by Codex Action

Mahkhmood9 · 1 month ago

as a rule of tumb , I recomend you ignore SOL existance ,, try start from the smallest like Luna , then move to Terra if you are unhappy with it

as a rule of tumb the smallest models now , are 4x times better than models of last years

Mahkhmood9 · 1 month ago

@topemalheiro

What are they thinking???

the 5 hour limit was removed

the resets seems to be happening daily, the SOL model seems to be a bigger model than 5.5 slightly despite being 2x as faster (and in many cases know when to stop)

it better the users feel like they risk something with each prompt --- better prompts will happen -
they need to want to not spend their whole token usage

if they only use it once every week - which is a lot of users - doing a single big prompt -- yes they use ue the ULTRA or MAX option

but for most cases
thats what LUNA was built for thats what TERRA was built for

you cant forget , it was a successful launch - they were able to reset limits after new high record number of users

I personally thing a 7d limit- if you hit it , you are stuck of a 1d daily limit

they are a powerful models --- but sometimes they are missing things (like idk not utalsing a framework or something - [ like bro why did i task you to use something?])

Mahkhmood9 · 1 month ago
What are they thinking???

as long as what your words mean and say -- your words should be translated into literal logic --- 5.6 even for chat are the only models that feel logical in their pattern of talking -- but I like to say the same about 5.4 and to minor degree 5.3 WHICH WAS MAGNITUTES BETTER THAN other products

even 5.4 mini is better than sonnet5 and that says a lot

topemalheiro · 1 month ago
> What are they thinking??? as long as what your words mean and say -- your words should be translated into literal logic --- 5.6 even for chat are the only models that feel logical in their pattern of talking -- but I like to say the same about 5.4 and to minor degree 5.3 WHICH WAS MAGNITUTES BETTER THAN other products even 5.4 mini is better than sonnet5 and that says a lot

https://github.com/openai/codex/issues/34190

Mahkhmood9 · 1 month ago
> > What are they thinking??? > > > as long as what your words mean and say -- your words should be translated into literal logic --- 5.6 even for chat are the only models that feel logical in their pattern of talking -- but I like to say the same about 5.4 and to minor degree 5.3 WHICH WAS MAGNITUTES BETTER THAN other products > even 5.4 mini is better than sonnet5 and that says a lot #34190

honestly its your responsiablity to ration your tokens, like you ration your monthly salary (I am not saying this because I am from an Ex-Soviet country - despite that I am)

What I say is, you should be careful with your prompts - the reality is ,
you get a lot more usage than you get on Claude

I recomend you use Terra - reasoning:Medium

where Luna 5.6 is great and fast--- 5.5 can fail in those tasks

with chatgpt gpt 5.6 models or any of the other models 5.5 , 5.4 , 5.3

its like it seens things you failed at , using the models for but learn

with Anthropic, its like that dont learn the users patetern

..
as per cost efficetiveness , use Luna ---- try to remind your -- does it worth 500$ or does the task worth 5$?

you should know this now , as we are risking all of the billing models being changes in the next years -- so you should be careful - not to get used to the biggest models like SOL or 5.6

what I do hope 5.7 , (I assume they will call it gpt 6 [not gta lol] ) would be much more token efficent , like you ask it it does it in a 3 tools calls , and not 20 --- I have a slightly feeling claude has gotten a bit better than it on the model-level but again - gpt models dont try to spew nonsensical code for no reasons

the /goal is actually useable --- the "Blocked" cube/block is okay - hrrm /plan seems interesting--- I did get the models work for much longer for me , which does seems to be a bit new for me -- which I dont mind - but it can get slow -- I wouldnt be surprise --- if GPT is a 4x times smaller model than what anthropic does for Sonnet or Opus ---- where it refuses it feels like a human refused it, and not based on a keyword ...

the good things is, you are using GPT, which is a good model, I assume you have being using Codex and did enjoy codex -
so the product is now good - (i got a lot of meaningful work without touching the ide even with 5.4 or 5.3 or 5.2)

Lastly , I recomend not touching GPT SOL ,,,
try even Luna EXTRA-HIGH or HIGH ----
a lot of your usage are not tokens but caching tokens I think? which is a clever trick to save compute I think -- but does increase your token use

I understand than GPT SOL or TERRA can shine in some tasks or niches --- but Luna preform just as well or not the same if giving 40% more time

on another node ,, nodejs/typescript codebases -- seems to be a bit problematic (naming of files) (cant understand or find functions --- forgets the meaning of certains files refuses to delete old dead code, will only add code - wouldnt never revise like a good developer )

with some commercial / enterprise -- you write a code and then you submit a PR so no a lot of mutating and reformating -- but sometimes you need to migrate , maybe to a new language or platform (I recomend using the prompt "FOSS and OpenSource alternative to X software") so you save a nickle in a subscription to another product (just be careful with CRM --- a lot of great apache prodcuts )

as with AI AGENTS , its very easy just to prompts -- oh I want a ""backup of that and that - I want this and this to happen ""--
"help me calculate the bill, what are the biggest offnders -- use this Spreadsheet"

again things you should ask and task the agent

REMINDER, coding agents ARE NOT YOUR BOSS
you are THE BOSS you need to declare what you want and have goals

<img width="1383" height="463" alt="Image" src="https://github.com/user-attachments/assets/2c20ce22-d2d8-4033-9595-a9117759d85e" />

Mahkhmood9 · 1 month ago

I think changing the limits to 4d instead of 7d might be a good idea

but in any capacity I gonna think the 5 hours limits should be back, because some users just visit the app once a week - they reach a limit and they will cancel because of the 5 hours limits of feeling regret --- and then next week they forget they paid 20$ and then they dont use chatgpt ever again

thats my two nickles here

bigfishi · 1 month ago

I am observing the same issue on a ChatGPT Plus account.

The account is correctly recognized as Plus, but the current authoritative account/rateLimits/read response contains only:

{
  "planType": "plus",
  "primary": {
    "windowDurationMins": 10080
  },
  "secondary": null
}

Historical local diagnostics from the same account showed both the 300-minute and 10,080-minute buckets.

Additional reset test:

  • One earned Full reset credit was redeemed.
  • The reset refreshed/re-anchored only the existing 10,080-minute weekly bucket.
  • It did not recreate the missing 300-minute bucket.
  • A second Full reset credit remains unused.

This indicates that the missing five-hour row is not merely stale client UI state: the 300-minute bucket is absent from the backend rate-limit response itself. Restarting, re-authenticating, checking the web usage dashboard, and removing a non-default local service_tier setting did not change the result.

OpenAI Support has documented the issue but stated that front-line support does not have access to inspect or modify account-level Codex quota assignments.

bigfishi · 29 days ago
I am observing the same issue on a ChatGPT Plus account. The account is correctly recognized as Plus, but the current authoritative account/rateLimits/read response contains only: { "planType": "plus", "primary": { "windowDurationMins": 10080 }, "secondary": null } Historical local diagnostics from the same account showed both the 300-minute and 10,080-minute buckets. Additional reset test: One earned Full reset credit was redeemed. The reset refreshed/re-anchored only the existing 10,080-minute weekly bucket. It did not recreate the missing 300-minute bucket. A second Full reset credit remains unused. This indicates that the missing five-hour row is not merely stale client UI state: the 300-minute bucket is absent from the backend rate-limit response itself. Restarting, re-authenticating, checking the web usage dashboard, and removing a non-default local service_tier setting did not change the result. OpenAI Support has documented the issue but stated that front-line support does not have access to inspect or modify account-level Codex quota assignments.
I am observing the same issue on a ChatGPT Plus account. The account is correctly recognized as Plus, but the current authoritative account/rateLimits/read response contains only: { "planType": "plus", "primary": { "windowDurationMins": 10080 }, "secondary": null } Historical local diagnostics from the same account showed both the 300-minute and 10,080-minute buckets. Additional reset test: One earned Full reset credit was redeemed. The reset refreshed/re-anchored only the existing 10,080-minute weekly bucket. It did not recreate the missing 300-minute bucket. A second Full reset credit remains unused. This indicates that the missing five-hour row is not merely stale client UI state: the 300-minute bucket is absent from the backend rate-limit response itself. Restarting, re-authenticating, checking the web usage dashboard, and removing a non-default local service_tier setting did not change the result. OpenAI Support has documented the issue but stated that front-line support does not have access to inspect or modify account-level Codex quota assignments.

Update from OpenAI Support:

Support has confirmed that, as part of an ongoing incident, the 5-hour usage limits have been temporarily removed for ChatGPT Plus, Pro, and Business users.

During this temporary period, users are expected to see only the weekly usage limit. Therefore, the following response shape is currently expected:

{
  "primary": {
    "windowDurationMins": 10080
  },
  "secondary": null
}

Support also confirmed that redeeming a Full reset only refreshes the currently available weekly bucket; it does not recreate the temporarily removed 300-minute bucket.

No restoration date or public incident reference was provided. I will update this issue if the 300-minute bucket remains absent after the temporary change is lifted.