ChatGPT Plus Codex limits penalize honest weekend open-source use

I am posting this separately because my earlier reply was in the rate-limit discussion thread, which had been active for about two weeks. After my reply, the only response that followed was off-topic, and the thread was closed a few hours later. That left me with no real opportunity to bring the discussion back to the actual issue, so I want to restate my point clearly on its own.

My point is not about workflow optimization. My point is about the fairness of the current Codex usage model in ChatGPT Plus for honest weekend open-source use. It is very important to me not just to post this, but to be heard, understood, taken seriously, and answered.

I use Codex for my private open-source work, not for my job. I usually work on that project once a week, on weekends, in one or two longer sessions.

At work, I use a company-paid AI coding subscription (in my case, Copilot). But I cannot use company-paid tools for my private project, and I do not want to blur that boundary. I think that boundary matters. Company resources should be used for company work, and personal resources for personal open-source work.

The problem is that the current session budgeting for Codex in ChatGPT Plus seems to favor many smaller sessions spread across the week. That is the opposite of how I use Codex. I do not need many small sessions. I need one or two substantial sessions for my private open-source project.

For example, I started working at around 7 p.m. After less than three hours, I had already used the amount I could use within one session window, and the next window only opened at midnight. In practice, that means the model forces a two-hour interruption in the middle of an evening session and then pushes me into the night if I want to continue.

At that point, the official alternatives are not really good solutions. I can buy additional credits, or I can continue local work with an API key on usage-based pricing. But if I need to do that regularly just to keep one or two substantial weekend sessions viable, then ChatGPT Plus no longer fits my actual use case in any reasonable way.

As a result, the next viable subscription step for my use case is ChatGPT Pro. But ChatGPT Pro costs five times as much as ChatGPT Plus. So because I keep the boundary between work and private use, and because I use Codex in a concentrated but entirely legitimate way, I am effectively pushed toward a plan that costs five times as much.

That is the part I find especially hard to accept. I am not asking for free usage. I am not asking to stretch or abuse a company subscription. I am doing the honest thing, and the result is that I am being penalized for it.

From my perspective, this is not “more flexibility.” It is a pricing change that makes one specific kind of legitimate use much worse: serious private open-source work done honestly, but only once a week. In practice, it turns honest separation between work and private use into forced overpayment.

Does it feel right?

Hi @dpolivaev

Yeah, I get why that feels frustrating, especially if you tend to do most of your work in a few longer sessions.

What’s happening here is that the limits are tied to time windows, not just total usage. So if you’re doing a lot in a short span (like a focused weekend session), you can run into them faster than someone spreading the same usage out over the week.

So you’re not using it “wrong” or anything like that, it’s more that the current setup doesn’t map especially well to bursty workflows. We do see this come up for people who prefer longer, uninterrupted sessions like you described.

Those limits are mainly there to keep things stable across a lot of users, which is why they’re structured this way. But your point about it not fitting certain usage patterns is totally fair.

~Smith

Hi Smith,

Thank you for the reply.

I appreciate that you acknowledged the mismatch directly. My point is exactly that: this is not misuse, but a usage pattern that the current setup disadvantages.

What I would ask OpenAI to reconsider is the assumption behind these new 5-hour limits. If there are concrete operational reasons why longer concentrated sessions must be restricted this way, then I would prefer that to be stated plainly. But if there is no such concrete reason, then I think users should be treated as adults and allowed to decide how to use their included budget. In that case, I would strongly prefer the new 5-hour limits to be removed.

I also do not see any practical recommendation in your reply, and that is something I would expect from support. Right now, none of the alternatives seems good for my situation.

I already tried adapting on my side: I switched from 5.4 back to 5.3 and got about three hours instead of two. But that still does not solve the actual problem. What I need is the ability to have one or two five-hour sessions per week to fit my schedule, while using the rest of my budget spread across the week.

So my question is: what do you actually recommend for a user in this situation, if credits, API usage, and the jump to Pro are all economically poor fits for regular use?

And separately, please pass this on to the product team: the current model does not just “fit some workflows less well.” It materially disadvantages honest, concentrated weekend use without offering a reasonable alternative.

Regards,
Dimitry

I support your idea. I have a suggestion that I hope the ChatGPT team can consider: for example, unused quota within a 5-hour window could be carried over to the next 5-hour period. The next period would prioritize using this carried-over quota, and the quota can only be rolled over once. This would be more user-friendly for those who do intensive development during the first 5 hours of the day, while still ensuring that users do not exceed the weekly quota limit.

If you only need to use two 5-hour quota windows within a few hours, here’s a useful tip. Suppose you start using Codex at 7 PM—your next quota refresh would normally be at 12 AM. You can set up an automated task in Codex to “warm up” the 5-hour window at 5 PM by assigning a lightweight task, such as summarizing a few international news headlines. This way, your 5-hour window will reset at 10 PM, allowing you to use two 5-hour quotas within a short period of time. Hope this tip helps!