I am frustrated from the recent updates in the Codex. I was previously working with 5.4 and 5.3 models with fast speed and I never ran out of token but after the 5.5 updates. The weekly qouta started running out after just a small bug fix for Pro if I use 5.4 or 5.5. if I dont use them and use 5.3-…

[image] VeitB: Codex rate limits for Pro users are currently doubled until the end of the month. If you are seeing rapid and massive usage limit drain, that appears to be a bug. I ran out an entire 6 hour quota in about 12 minutes flat with only 8 messages sent. I haven’t bothered since, as u…

Yeah, vb’s guidance here is on point. If you’re seeing unusually fast Codex quota drain, /feedback from Codex is helpful because it sends app-side context to the team. These may also help explain how Codex usage is counted: - https://help.openai.com/en/articles/11369540-using-codex-with-your-chatgpt…

Very interesting :sweat_smile: I described almost the same problem as you. I’m a relatively new user, so I can’t compare Codex with its previous versions, but I’m facing the same issue: the tokens disappear before you even really start working. It feels like they overestimated the 5.5 models and are…

I understand the sarcasm about my “bank account,” but that is not the issue. The problem is not whether I can afford it. The problem is that Codex limits are unclear, unpredictable, and in real usage the quota can disappear before meaningful work even starts. Also, API pricing and practical Codex us…

[image] Serdjio: At minimum, the UI should explain the limits honestly, and there should be some fallback/basic model for audits, tests, or smaller tasks after the main quota is exhausted. This honestly hadn’t occurred to me until you pointed out the problem, but anyone dealing with a standar…

This is one of the simple example on How Codex is actually forcing us to use the 5.5 or 5.4 I have already created the tests in a specific manner through 5.3 and recently I gave it a curl asked it in the new chat to create the test and it started editing the actual source files and created new sou…

I’ve noticed similar issues lately, especially with longer projects and context handling. The planning phase feels much slower now and sometimes the model loses track of earlier requirements after compaction. Hopefully they improve optimization and developer experience soon because workflow consiste…

For those who are still struggling I figured out the solution which is easy and seems like limitless. Credits never run out. Create a custom GPT and map via actions to your system. ChatGPT power tbh surpasses codex and response time is few seconds. In less than 10 minutes ChatGPT Heavy Mode fixed…

Nothing like utilising an exploit to get your account banned … be careful out there! Very cool btw, but may not make everyone happy :thinking:

Frustrated with new Codex Limits for the Pro Users

Codex

merefield May 15, 2026, 3:19pm 10

5.5 is ~ double the cost per token to 5.4, but it’s meant to make up for that by using fewer tokens (but not quite half unfortunately):

Topic		Replies	Views
GPT 5.5 Codex Quota Drains Quickly Codex codex , codex-app	19	5029	July 11, 2026
Need to have serious discussion with the $200/month plan Codex	8	3192	September 9, 2026
Why Is GPT-5.4 Mini Showing Up in My Codex Usage? Codex	10	970	September 10, 2026
Codex using up MASSIVE credits (850 credits + 5 hour limit used on only 8 queries) Codex codex , bugs	17	6918	November 11, 2025
Usage Limits of Codex within Cursor Codex codex , gpt-5	15	17654	January 23, 2026

Frustrated with new Codex Limits for the Pro Users

Related topics