Glad everyone else is noticing that Codex usage limits have been destroyed. >It’s draining as fast as 5hr limit. But weekly >Cheaper models, are seeming to drain our quota just as fast. >20x plans feel like 5x “5.6 is extremely efficient, and costs just as much as 5.5” yeahh right.
Sorry but Codex Usage limits are terrible now? Yesterday, i only used 5.6 sol high, i let it running in a /goal, configured cheaper terra/ lunar subagents. I come back 40% of my total weekly usage is gone? ( 20x) BTW i was using multiple 5.6 Sol xhigh + Max, all day everyday, last week. Id rather get no resets, steady and fair usage, as opposed to getting resets, but every time they do, they reduce our quota. They also removed the invite friends for banked resets. Anyone else noticing this? Just gets worse by the day.

Jul 24, 2026 · 3:07 PM UTC

146
85
1,557
120,312
Hope this helps everyone
Given the latest Codex Usage limits have been heavily limited. Here’s EXACTLY how to minimise the IMPACT: >1 | Make sure to configure your own Subagents - Set the model + reasoning to Terra or luna. >2 | Clear your cache + Recycle your sessions after 2 compactions - When this happened last time, a bug that was causing weekly limits, to act as 5hr was due to built up cache or from staying in the same session. >3 | /Goals is hurting us - I love /goals, but recently and like before, it absolutely drains your Quota. >4 | Go review your Agents.md ensure its under 300 lines. -Keep it maintained. >5 | Manage aka limit the amount of skills, being loaded into Codex -if you’ve got more than 30 skills, configured. It’s just draining context, which drains your sessions much much faster. >6 | Only use GPT Sol extra high or Max for planning. Hope this helps. ( Save it just in case ) Most of have important projects we’re building so don’t let your usage kill your work.
8
5,925
Sort replies: Relevant Recent Liked
Replying to @jturntdev
If they don't fix this I'm cancelling and I would support them throughout everything but even Claude has better limits than this. Its extremely frustrating to pay 100-200 per month and STILL be on edge about usage.
5
64
4,121
Yh its the worse. You need to buy 2-3 accounts
1
4
3,610
Replying to @jturntdev
I'm still convinced it's a harness issue and Codex is just broken somewhere...
2
44
3,416
Same.
2
9
3,172
Replying to @jturntdev
I wonder if they silently nerfed the usage limits while giving us a bunch of resets so we wouldn’t notice
1
26
1,507
Probably
2
1,371
Replying to @jturntdev
Yeah idk if it's cause I keep engaging with people who needs a reset too, but it's all over my tl and @thsottiaux is not flinching at ALL
1
18
2,433
I wouldn’t know
1
2,119
Replying to @jturntdev
I wonder why no one from OpenAi team talking about this
4
17
2,577
They dont until everyone begins to talk about it
28
2,366
Replying to @jturntdev
5x feels like 1x
1
8
2,733
😭😭
1
2,525
Replying to @jturntdev
I don't think Codex is broken. Admit it, OpenAI is cutting user quotas
102
Replying to @jturntdev
true
26
Replying to @jturntdev
you're on the $200 plan right? right? you're not complaining about usage limits on anything lower than the $200 one I hope?
2
277
Replying to @jturntdev
Usage is no different. You are naively acclimating to greater freedom and blaming OpenAI for it
104
Replying to @jturntdev
Weekly plan feels like 5 hour usage limit. I hope this is a huge bug @thsottiaux
228
Replying to @jturntdev
Yep, there is no free lunch... All these free reset and banked reset was to mask something
70
Replying to @jturntdev
It’s unusable at a sustained pace if Tibo doesn’t press the button multiple times per week.
8
172
Replying to @jturntdev
This was their plan, get us hooked with a bunch of resets then make it really easy to buy extra credits in the app.
5
466
Replying to @jturntdev
they removed the 5 hour limit, and created the illusion in the midst of reset party 🎊😈
1
4
46
Replying to @jturntdev
If we had 5 hour limits we'd had easily understood the companies changing the limits behind the scenes But with weekly only we are less sensitive to the noise
4
45
Replying to @jturntdev
OpenAI scammed us
1
3
139
Replying to @jturntdev
I agree. not even 2 days. With the previous 5.5 I would almost never even burn in a week. At least grok is "only" at 94% usage after a full week, 3 more hours before reset.
4
377
Replying to @jturntdev
What pisses me off is the OpenAI bros... they keep shilling for Codex when they're clearly taking you for a ride. It's time to call them out so they fix this 💩.
3
93
Replying to @jturntdev
I hate people who have no clue what they are saying. 5.6 is incredibly efficient and very cheap, close to fable at 1/3rd of the price. The problem is with the token subscription not the actual pricing. There might be a point where 200$ subscription will only u get that much in api usage. This is only because it’s heavily subsided and they really don’t know what to price it at. They can play around with how many tokens you get per subscription. It’s still very good pricing in the sub, and more of a plan problem not actual cost of the model.
1
3
365
Replying to @jturntdev
Seems they dont give a shit abt that , I've beeen shouting it everywhere but "hey look our new update on codex" ffs x20 feels like x5 tf
2
157
Replying to @jturntdev
Its the same usage scam Anthropic pulled of earlier this year
3
737
Replying to @jturntdev
I used 3 resets in 5 days. xHigh on a 20x plan used to last me a week. Now it lasts 2 days. Tried lower model same usage.
3
110
Replying to @jturntdev
I swear I’m doing a chargeback literally $200 20x plan finishes in a 24 hours
3
243
Replying to @jturntdev
bro u r right!
1
8
Replying to @jturntdev
最糟糕的是,昨天更新后,当我完全不使用codex,周额度也在不断减少,直到归0,太沮丧了。
1
35
Replying to @jturntdev
Yes goes very fast downhill and chatgpt app was completely down here in EU this morning @OpenAI
1
737