ChatGPT on the web: “Too many requests” blocks chat access and disrupts Work tasks
What version of the Codex App are you using (From “About Codex” dialog)?
During the original August 14 occurrence, ChatGPT desktop 26.810.41047 (build 6570) was also open on the same account. The visible “Too many requests” conversation-access modal described in this issue has since been isolated to ChatGPT on the web (chatgpt.com) in Chrome.
What subscription do you have?
ChatGPT Pro ($200/month), the Pro tier with 20x higher usage allowance than Plus under OpenAI's current Pro tier documentation.
What platform is your computer?
macOS 26.6.1 (25G76)
arm64Browser surface: Google Chrome on chatgpt.com.
What issue are you seeing?
Original report — August 14, 2026
During normal ChatGPT use, ChatGPT on the web can temporarily lose access to chats and display this modal:
Too many requests You’re making requests too quickly. We’ve temporarily limited access to your conversations to protect your data. Please wait a few minutes before trying again.
This is highly disruptive and does not appear to be an ordinary model-usage limit. The restriction affects access to chats themselves.
At the time of the original occurrence, the same account was signed in to both the ChatGPT desktop app and chatgpt.com. That originally raised the question whether activity across both surfaces might contribute to the restriction, but that has not been established as the cause.
The problem is especially serious for Work tasks. When access to the relevant chats is temporarily restricted, Work tasks that depend on that conversation context can be interrupted or left without reliable access to the context they depend on.
Feedback/diagnostic reports were submitted from the affected account. Public identifiers from those submissions are intentionally omitted here.
A screenshot of the original modal was captured at approximately 2026-08-14 2:04 AM America/New_York.
What steps can reproduce the bug?
The exact minimal trigger is not yet isolated because the behavior is intermittent.
- Sign in to ChatGPT on the web in Chrome.
- Use chats, projects, and Work tasks normally and navigate between chats.
- At some point, the “Too many requests” modal can appear and temporarily block access to chats.
- Waiting eventually restores access, but the behavior can recur.
I am not intentionally performing bulk, scripted, or high-frequency requests.
What is the expected behavior?
- Normal use of ChatGPT on the web should not temporarily block access to chats.
- Navigation between chats and projects should continue to work during normal interactive use.
- Conversation-access requests should avoid unnecessary duplication and should respect appropriate retry/backoff behavior when temporarily limited.
- Work tasks should receive a clear temporary-failure state rather than continuing without reliable access to required conversation context.
- The UI should distinguish a temporary chat-access restriction from model or subscription usage limits.
Update — August 15, 2026
The issue recurred on 2026-08-15 at approximately 2:34–2:35 PM America/New_York.
During this recurrence, the same modal appeared in two different chats within the same Chrome browser session, including a chat in a project and another regular chat. The restriction was therefore not confined to a single chat or project.
Surface clarification: during this August 15 recurrence, I observed the modal only in ChatGPT on the web. I did not observe this modal in the ChatGPT desktop app.
This recurrence confirms that the behavior is not a one-time event. Screenshots were captured. Chat titles, project names, local paths, account-specific identifiers, feedback identifiers, and private content are intentionally omitted from this public report.
This issue does not assert a specific HTTP status code or backend endpoint for the browser modal without browser network evidence.
A separate issue, #38632, tracks a different desktop-app symptom where the app explicitly displayed Request failed with status 429 while chatgpt.com remained usable. That desktop error should not be conflated with the browser conversation-access modal tracked here.
Potentially related reports include #37518 and #38763.
18 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Completely agree this 429 error in normal use, on paid accounts well below any usage limit is extremely frustrating and can only be considered a bug.
Browser-only recurrence — August 15, 2026
At approximately 2:34–2:35 PM America/New_York, the same “Too many requests” modal appeared twice in ChatGPT on the web in Chrome while navigating between two different chats.
Screenshots were captured showing the browser behavior.
This report is based on the visible ChatGPT UI behavior. I am not asserting a specific underlying HTTP status or endpoint for this occurrence because I did not capture browser network diagnostics for it.
The separate desktop-app symptom that explicitly displayed
Request failed with status 429is tracked in #38632. Related browser report: #38763.this is very annoying!
Happens way too often and there seems to be no way of disabling it other than waiting.
bumping this, I would expect there to be a way to unlock or bypass via a code to email or two auth confirmation.
I work in heavy bursts, sometimes less sometimes a lot more.
Also seeing this in a fresh browser session
<img width="932" height="342" alt="Image" src="https://github.com/user-attachments/assets/7c5484e3-0147-41f9-b0d3-ddb6f7fe7455" />
my list of chats isn't displaying so this could be chat enumeration hammering the server
I've been seeing this bug since 5.6 was released, not that it's related but simply as a timeframe. Over the last week it has worsened and now ChatGPT is almost unusable, every single time I open a chat or send a message I get this message. Just opening the ChatGPT app on my phone causes it to display "Too many requests". I've enabled MFA, logged out all my devices which I'm not actively working on, and my requests are actually minimal lately, yet I still get "Too Many Requests" as soon as I wake up and access ChatGPT for the first time in the morning. Using the Pro 20x plan.
im receiving this problem also. what's going on. im using codex as per normal
I keep getting this message all day since yesterday and it's very frustrating. Nothing has changed in my usage pattern. Using the Pro 20x plan.
<img width="563" height="197" alt="Image" src="https://github.com/user-attachments/assets/2d569318-412b-4cd7-afaf-39db675405d1" />
same here since 2 days ago, standard pro plan . codex app works as normal.
Same here. It's been on and off over the last few months, but it started happening heavily again a couple of days ago.
The main issue is that the sidebar doesn't load the list of chats, in addition to the inconvenience of the message itself.
It only happens on ChatGPT Web, where I have a reasonable number of pinned projects and chats. The macOS and Android apps aren't affected. I'm on the Pro plan, and Codex works fine.
exact same issue as this person
Same issue here, also Pro plan (an interesting commonality...?). Codex likewise works fine. Seems very intermittent and random as to when it actually triggers, like I woke up this morning and almost immediately got the alert.
Same here — started on July 9, 2026, the day the Codex app was merged into
the ChatGPT desktop app, and has never cleared since. Details in #38763.
I have been experiencing this for weeks but it really intensified in the past 1-2 days, I feel. Now simply sending 1 message after hours of inactivity returns this message 3 times at ~5 seconds increments. Forces me to click on "Got it" many times and blocks access from Chat History.
Severely degrades the experience for paying users. Please urgently fix this !
My issue got less severe, i revoked authentication of all of my devices and any api that i had . Also stopped using opencode harness. Right now, thinking is working properly but i still sometimes lose access to my chat history.
I'm not experiencing the issue anymore.
Same here, became a nightmare to use ChatGPT on the web...
I was using this Chrome extension to fix performance in long conversations: ChatGPT Performance Long Chats
It worked amazingly well. Chats I was completely unable to interact with, even on a MacBook Pro M4 Max with 128 GB of RAM, became usable again. But I’m not sure whether the extension could somehow be contributing to the “Too many requests” issue.
Same here on Pro account, been a few days now.
I asked Chatgpt after pressing "got it" a million times and it answered about the bug:
" a product this central to paid Pro workflows, 11 days feels long since it was reported on Github and presumably to OpenAI support.
What makes it especially irritating is that OpenAI has resolved plenty of broader ChatGPT incidents in hours on its status page. For example, recent conversation and login incidents affecting large user groups were fixed the same day.
The difference here is that your problem appears to be a narrow regression rather than a broad outage. The exact “temporarily limited access to your conversations” issue was opened on 14 August and is still open, while another essentially identical Pro/macOS report from 15 August is also still open.
That usually means one of three things: OpenAI has not yet isolated the trigger reliably, the bug sits at the intersection of several systems such as conversation history, session handling and rate limiting, or they are working on it internally but haven't updated the public issue.
The part that makes me less forgiving is this: the GitHub report is not some obscure cosmetic glitch. It explicitly says ordinary ChatGPT use can trigger an account-wide restriction on conversation access, disrupt Work tasks and recur after recovery. That is a serious productivity bug for a Pro customer.
So yes, I would have expected days, not approaching two weeks, especially given the number of recent changes around Codex and ChatGPT.
My best guess is that the delay is not because OpenAI considers it unimportant, but because it is proving difficult to reproduce and fix without weakening the anti-abuse/rate-limit protections that sit behind it."