Rapidly hitting weekly limits on ChatGPT Pro plan

gpt-5-codex high seems to consume insane amounts of usage compared to gpt-5 high. I had been using gpt-5 high with 4-6 agents for 8+ hours a day on my Pro plan without ever hitting usage limits - then I tried gpt-5-codex high when it released yesterday and hit the 5-day usage limit after only 30 minutes of running 2 agents. Very frustrating (and agreed: What do you see instead? = _Incentive to not spend on ChatGPT Pro_)

gpt-5-codex high seems to consume insane amounts of usage compared to gpt-5 high. I had been using gpt-5 high with 4-6 agents for 8+ hours a day on my Pro plan without ever hitting usage limits - then I tried gpt-5-codex high when it released yesterday and hit the 5-day usage limit after only 30 minutes of running 2 agents. Very frustrating (and agreed: What do you see instead? = _Incentive to not spend on ChatGPT Pro_)

Since it released they heavily recommend using medium. It's more dynamic than before - using fewer tokens for thought when it identifies "easy" problems (without using a router), and using more tokens (like high) for "hard" ones. You might want to try this.

Btw how many tokens did it report were used in those 30 minutes?

Btw how many tokens did it report were used in those 30 minutes?

If I recall, it was around the same magnitude shown by @Alfredo-Sandoval - around 10 million cached tokens (far higher than I ever saw with GPT-5 high)

> Btw how many tokens did it report were used in those 30 minutes? If I recall, it was around the same magnitude shown by @Alfredo-Sandoval - around 10 million cached tokens (far higher than I ever saw with GPT-5 high)

Sounds like something is going wrong then. I used around 10 million un-cached tokens yesterday, on my first day of Pro usage. This was using medium though.

From my largest session:
Token usage: total=8,755,957 input=8,537,903 (+ 30,605,824 cached) output=218,054 (reasoning 122,496)

Had the weekly limit lifted for a few messages and its back now. Can't help but think its related to the usage spike from people coming over to codex

I just hit limit on Pro plan using gpt-5-codex-medium with 2.5 days till reset, something is off. Max 2 terminals at a time this week so far using only medium.

And the limit message is also telling me to upgrade to Pro to increase my limits.

Latest session stats:

Session ID: e1a372f3-fc9e-49fa-af2e-6b894b7d5bce
• Input: 0 (+ 12929408 cached)
• Output: 44,736
• Total: 44,736

Tweets:

⚠️⚠️⚠️The Codex GPT-5-Codex model should be cautious to use (for plus users), as it quickly reaches its limit, requiring a wait of several days for the limit to reset.

Very, very light. In fact, one of my friend who just landed about codex two days before and he did not use much and I asked him whether he is having the same problem. He started using the new version of GPT5 in codex immediately got hit by the limit.

Guys, don't try gpt-5-codex if you want do anything. Wasting limit in simple 4 prompts at medium resoning

I tried running gpt-5-codex high with plus and it suddenly died. It took 3 days.

[tried gpt-5 codex. spent 5 minutes flailing on a single prompt, adding a bunch of unnecessary complexity and then ran into usage limit.

absolute garbage](https://x.com/testttt1236/status/1968050446435791002)

i didn't know it was possible but I hit the codex limit! first time in weeks

Horrible rate limits. I reached mine in 3 hours on one project

[I hit my Codex quota limit so now I have to wait 2 days.

How am I supposed to code now? In an IDE like some kind of savage? 😤](https://x.com/AlinCatalin/status/1967959656028115165)

And I’m just loosing all that vibe cause my usage limit for codex extension will reset only after two days 😔

Codex: "You've hit your usage limit. Upgrade to Pro or try again in 23 hours 54 minutes." IMO, this is a mistake by OpenAI, needs to be more granular/short. If you need a 24-hour pause, you can't rely on this for serious work. Claude 5hr window more reasonable.

Codex token usage is insane. I just asked it to fix a test file and suddenly it burned 200K tokens. Bug?

Is it normal to reach the limits so quickly?

Have limits been updated with the codex model launch? They seem tighter

Please raise the limits for the plus! I didn't even have time to complete one operation on the new codex.

the new gpt-5-codex is burning through my limits 15-20x faster. i sent 3 messages to gpt-5-codex (medium) and now i can only use it again in 35 hours.

Are the limits low just for me? I've been working with GPT 5 high/medium for weeks without reaching any limits, the first time with the codex i reached the limit

I was running gpt-5-high without hitting limits for days. Had a break. Registered to use gpt-5-codex (ie a non gated model, verified my id etc). Used one /init command and was placed on ice for 48 hours. Hmmmmm…..

I am on the Pro plan and somehow have hit usage limits with Codex and can't use it again for over a day. Any solution here besides using an API key?

I am a pro user who has apparently hit my WEEKLY limit in Codex, as its been hours and I am still locked out. Can we PLEASE ship a clear indicator of when this ends?

I’m really confused about the new Codex limits. I was working this morning and suddenly got locked out. I’ve never once hit a limit in a 5-hour window, and today I’ve only sent around 15 messages, all on low settings. Same story yesterday, only low-setting usage. The OpenAI website for Plus says: Local tasks: Average users can send 30–150 messages every 5 hours with a weekly limit. So how am I locked out for nearly a week when I’ve never even seen a warning before? I really don’t see how I could be hitting the limits.

This doesn't seem normal. Hopefully OpenAI will address this ASAP - 2+ day timeouts is unacceptable for those of us paying $200/mo and relying on Codex as a crucial part of our workflows.

Unfortunately, the docs only mention a weekly usage limit but don’t specify the actual numbers. Since the gpt-5-codex release, it feels like the cap has dropped significantly. Could you please publish the concrete weekly limits (per plan/model) and reset rules?
Hitting the limit after half a day of normal work on a Pro plan is pretty unreasonable without clear guidance.

与 GPT-5 High 相比，GPT-5-Codex High 似乎消耗了大量的使用量。我之前一直在 Pro 套餐中使用 GPT-5 High，搭配 4-6 个代理，每天使用 8 个小时以上，从未达到使用限制——然后我尝试了 GPT-5-Codex High，昨天它发布后，我运行了 2 个代理，仅 30 分钟就达到了 5 天的使用限制。非常令人沮丧（并且同意：你看到的是什么？ =_不花钱购买 ChatGPT Pro 的_动机）

you scare the shit out of me. I am using high sometimes , most time is medium. now I will watch my back when I use high. thx to mention this.

@rockyicer I've just gone back to gpt-5 high and having no issues with limits there so far, avoiding the new gpt-5-codex models entirely until these usage limits issues are confirmed to be fixed.

gpt-5 high is working better for me anyway, in the limited time I tried gpt-5-codex the other day, it spent 30 minutes working and ultimately reverted everything it did because it wasn't sure how to solve the issues that were coming up - never saw that behavior with gpt-5.

@rockyicer I've just gone back to gpt-5 high and having no issues with limits there so far, avoiding the new gpt-5-codex models entirely until these usage limits issues are confirmed to be fixed. gpt-5 high is working better for me anyway, in the limited time I tried gpt-5-codex the other day, it spent 30 minutes working and ultimately reverted everything it did because it wasn't sure how to solve the issues that were coming up - never saw that behavior with gpt-5.

Does it seem too smart?

@iwangjie I don't know if I would call it "too smart" but from what I've observed it seems aggressively RL'd in such a way that it views itself as more of a solo engineer / project owner than an assistant/collaborator.

@iwangjie In my experiece gpt-5-codex high also turns out to be far worse than gpt-5 high, at least for a complex codebase. It comes across as a shallow drama queen that claims to find bugs where there actually aren't any. The bugs it sees are simply misunderstandings on the part of gpt-5-codex high - it's thinking too shallow. gpt-5 high doesn't do that - it performs very well and it does so consistently, and I'm using it a lot (and before that codex-1).

My speculation is that gpt-5-codex high is actually a very capable model (and probably better than gpt-5 high in a theoretical sense, or in some specific cases) but the part that makes it auto-decide how short or long to think is often seriously misbehaving. So the model ends up spending little reasoning time on things that are actually subtle and hard issues. I find that this model behavior is definitely reproducible, it's not just a one-off, or rare. Inconsistency kills the UX.

I'm more and more convinced that the real fix is for OpenAI to drop the "auto-mode", and instead add a radio group UI widget where users can choose between think time: 1sec, 10secs, 100secs, 1000secs (or even a log scale slider that allows all values between), because the user knows much better what he wants/needs than the model ever will.

Just tried first run of gpt-5-codex medium and it spent 45minutes running powershell cmds changing 2 files and then ultimately reverthing them at the end. Incredible waste of time it returned this message:

codex: I’m sorry, but I wasn’t able to finish the implementation.

📊 Token Usage
• Session ID: 5f0463d4-4eb2-4527-9348-6436342a8cce
• Input: 267,626 (+ 17749504 cached)
• Output: 117,325
• Total: 384,951

@iwangjie In my experiece gpt-5-codex high also turns out to be far worse than gpt-5 high, at least for a complex codebase. It comes across as a shallow drama queen that claims to find bugs where there actually aren't any. The bugs it sees are simply misunderstandings on the part of gpt-5-codex high - it's thinking too shallow. gpt-5 high doesn't do that - it performs very well and it does so consistently, and I'm using it a lot (and before that codex-1). My speculation is that gpt-5-codex high is actually a very capable model (and probably better than gpt-5 high in a theoretical sense, or in some specific cases) but the part that makes it auto-decide how short or long to think is often seriously misbehaving. So the model ends up spending little reasoning time on things that are actually subtle and hard issues. I find that this model behavior is definitely reproducible, it's not just a one-off, or rare. Inconsistency kills the UX. I'm more and more convinced that the real fix is for OpenAI to drop the "auto-mode", and instead add a radio group UI widget where users can choose between think time: 1sec, 10secs, 100secs, 1000secs (or even a log scale slider that allows all values between), because the user knows much better what he wants/needs than the model ever will.

Yes, it seems that we know better what kind of problem this is, and there may be compromises, such as providing strong evidence to prove the complexity of this problem when triggering thinking. If it is not provided, it needs to be clarified by the user, after all, it is a blank sheet of paper before starting

I hit a weekly limit in less than 2 days. What are the actual limits, cause this isn't what I signed up for...

!Image

Same here after 2 days, weekly limit reached. A bit underwhelmed. Might have to cancel.

Hit 5 day on my business account in a day - Back to Claude.

Hit 5 day on my business account in a day - Back to Claude.

Biz account is same as Plus. At best it's only for trialing it. Pro is mandatory for serious use

they need to fix this asap im bout to unsubscribe and stop paying as i do every single time because of those problems ... this is making the experience suck very much very suck and very much ....

we are helping build chatgpt giving them data bout our projects and thinking for them loudly in the chat

and our pay is weekly limit and stop gates .... this is sucks and i hope thay will give some more power and ability to power users that not always can pay 200$ or even 20$ subscription.... and still do it because of passion and bigger agenda to this ...

hope codex will see this and realy it to to the upper management up there

at least give us gpt4o for free or 5 nano or instant .... without limits ...

currently need to wait f 3 days for my limit to rest

after i tried to use only instant

used something like 2 mil tokens until i got to the limit with plus subscription

we are helping build chatgpt giving them data bout our projects and thinking for them loudly in the chat and our pay is weekly limit and stop gates

It's crazy to watch them boast on podcasts about creating "abundance of intelligence" meanwhile cutting off their paying users from accessing said intelligence for days at a time.

Plus subscription is only usable for a few sessions per week, as they've said. You need Pro to expect daily use. I'm not sure codex with gpt 5 nano would be productive and they probably don't want to promote usage of something below productivity standards that could harm its reputation

Actually the real problem is Usage Monitoring. It would be nice to see how much daily and weekly usage you've been using in terms of percentage (like the context left) so you don't feel cut off from working unexpectedly.

Actually the real problem is Usage Monitoring. It would be nice to see how much daily and weekly usage you've been using in terms of percentage (like the context left) so you don't feel cut off from working unexpectedly.

Check the main branch. It just landed...

Plus subscription is only usable for a few sessions per week, as they've said. You need Pro to expect daily use. I'm not sure codex with gpt 5 nano would be productive and they probably don't want to promote usage of something below productivity standards that could harm its reputation

But that's exactly the issue. Many of us are already on the 200$ Pro subscription, yet we still hit the limits during a standard daily workflow with just a single codex-high agent, without abusing the service.

■ You've hit your usage limit. Try again in 19 hours 34 minutes.

That's troubling - I haven't run into it yet

Does anyone know how the weekly limit rollover works? I can now see I'm at 38% of my weekly limit, but I have no idea what that means in terms of my pace. E.g. am I 38% done just 2 days into the week, or have I underused it and it's going to reset tomorrow? Or is it a sliding window which would mean I should try to stay near 100% without hitting it to avoid wasting unused tokens? I haven't been able to find any info.

edit: https://github.com/openai/codex/issues/4080 covers my question (unanswered though)

Well guys, Let me show you something even crazier. After my limit had reseted I tried a single prompt in gpt 5 codex medium and after waiting for 30 minutes, the AI stopped halfway.

<img width="597" height="390" alt="Image" src="https://github.com/user-attachments/assets/53b0be64-0d09-4170-b88c-48c7b8009efe" />

I didn't use the high, only using the default medium. Reaching 75% within 3 days. Very disappointing. People were complaining Claude Code Pro US$20 also has the same issue, but I am 99% sure it's not. I was working only on one side project with Claude Code last month, very similar usage per day. Never reach the limit of Claude code.

Then, this month, switched to Codex and this quickly happens within 3 days. Cancelling the subscription for now until Codex becomes more reasonable.

<img width="628" height="267" alt="Image" src="https://github.com/user-attachments/assets/ca8498e8-504e-4480-aa58-1514ec62994c" />

I used 10% of my weekly Pro limit coding for 8 hours with "gpt-5-codex high" with a single agent in Codex CLI. I closed and reopened a bunch of times, but just 8 hours of feedback loops. No crazy agentic mega task lists or automated agentic workflows like Speckit or Bmad. Just normal manual back and forth.

So $200 a month is cutting it very close at that rate for a 5-6 day work week. At least claude code never had the weekly cut off, just the 5 hour cool down. Any one using multi agents or GitHub actions would be cutting it even closer.

like really i just had 5 hours of coding and i get limited for 5 days .... that absurd

"■ You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again in 5 days 19 hours 29
minutes."

at least the new version is telling us 75 90 and 95% use ... really im just getting of sick trying to do stuff like this .. :[ sam Altman and codex please read this and fix

like really i just had 5 hours of coding and i get limited for 5 days .... that absurd "■ You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again in 5 days 19 hours 29 minutes." at least the new version is telling us 75 90 and 95% use ... really im just getting of sick trying to do stuff like this .. :[ sam Altman and codex please read this and fix

You'll need to either sign up for multiple Plus accounts or upgrade to Pro. They're unlikely to raise it much from here since Pro is pretty good for nonstop usage without parallelization now

The usage limit must not be this small.
And when the limit is hit, an alternative model should be available.

This issue has been open for nearly a full month and still no acknowledgement from OpenAI. I've been using (well, attempting to be using) Codex on my Pro plan exactly as they advertise it:

Developers looking to power their full workday across multiple projects

<img width="706" height="242" alt="Image" src="https://github.com/user-attachments/assets/c9b34920-8c0c-4bf6-92a2-09f010bab1b8" />

Yet, I'm still reaching the weekly limits multiple days before the weekly reset takes place - a direct contradiction of the experience they state Pro users will receive at https://help.openai.com/en/articles/11369540-using-codex-with-your-chatgpt-plan

How can I "power [my] full workday across multiple projects" if attempting to use the plan exactly as they state it can be used results in me being locked out for multiple work days at a time?

I mostly use "medium" in Pro. But it goes really fast. I am a mid-heavy user ( not very heavy user ). but always hit near 100% in weekly limits. Never hit 5h limit even 50%. Not many mcp ( only context 7. not much used )
I believe weekly limits should be more limit.

We're recently introduced some changes that help your extend your available usage.

Introducing a less capable model does not fix the issue. If OpenAI had a tiny model that was capable of auto selecting an appropriate LLm given the task's complexity that would be great for everyone.

@mateususa, our most recent models already dynamically adjust their reasoning level based on the specified task. We're continually looking for ways to lower the costs of inference while increasing what you can accomplish within a given budget. If history is any guide, you can assume that costs will continue to drop over time while capabilities will continue to increase. If you are hitting usage limits in the meantime, you have the option of upgrading to a less restrictive plan, buying additional credits, or switching to metered (pay-for-what-you-use) API key pricing.

Sounds great. I was aware that supposedly the Gpt 5 models are meant to auto adjust. But from my experience. At least in the Web app (I am new to using CLI) I have not experienced this auto adjust. I always keep "extended thinking" ON because the regular 5.2 never seems to satisfy my questions. I suppose this happens because there is not a lot of good quality data for the model to be trained on. Thus I seem to always need extended thinking ON for the model to take edge cases into consideration.

Anyhow, it's hard to complain about a great tool.