{"slug": "the-codex-5-hour-limit-is-making-it-practically-unusable", "title": "The Codex 5-Hour Limit Is Making It Practically Unusable", "summary": "OpenAI's reintroduction of a 5-hour usage limit for Codex on Plus has drawn criticism from a developer who found that a single coding task consumed the entire allowance in about 24 minutes. The developer argues that the limit undermines the agent's usefulness for extended coding sessions and creates a disincentive to thorough testing and verification.", "body_md": "OpenAI recently brought back the 5-hour usage limit for Codex on Plus, and after actually running into it today, I have to say: this is awful.\n\nNot because I expect unlimited access. I don't.\n\nI completely understand that these models are expensive to run and there need to be usage limits somewhere.\n\nThe problem is that the 5-hour window makes it incredibly difficult to actually use Codex for the thing it is designed to do: sit down and work on software.\n\nToday I gave Codex one fairly simple task in my Markdown notes app.\n\nAdd Find and Replace.\n\nThat was it.\n\nI wanted Find in the Edit menu, keyboard shortcuts, match navigation, Replace, Replace All, and the usual behavior you would expect from a basic editor.\n\nCodex implemented most of it, wrote tests, ran the build and linting, and started doing browser verification of the actual UI.\n\nThen my entire \"5-hour\" limit was gone.\n\n**Actual elapsed time: about 24 minutes.**\n\nOne task.\n\nTwenty-four minutes.\n\nFive-hour allowance gone.\n\nAnd the best part? It didn't even completely finish.\n\nThe search highlighting still isn't finished, and Codex hit the usage limit while it was wrapping up verification. Now I have an implementation that is almost done, Codex knows what it changed, Codex knows what it was checking, and I can't even tell the agent to finish its own work until my limit resets.\n\nThat is the part that makes this system feel fundamentally broken.\n\nObviously I don't expect \"5 hours\" to literally mean five hours of wall-clock time.\n\nAgentic coding usage depends on context size, reasoning, tool calls, tests, commands, and a bunch of other factors.\n\nThat's fine.\n\nBut there is a pretty enormous difference between \"this might not last exactly five hours\" and **\"one normal coding task can consume the entire allowance in less than half an hour.\"**\n\nAt that point, calling it a 5-hour limit is almost meaningless from the user's perspective.\n\nI can't reasonably plan around it.\n\nI don't know whether opening Codex means I have an afternoon of coding available or one 20-minute task.\n\nAnd that uncertainty completely changes how useful the product is.\n\nFor a short time, Plus users effectively had the weekly limit without this restrictive 5-hour window getting in the way.\n\nI actually preferred that.\n\nI could sit down on a Saturday or Sunday and work.\n\nMaybe I burned through a large chunk of my weekly allowance in one weekend. Fine. That's my choice.\n\nIf I use my week's allocation in two days, I understand that I'm not going to have much left for the rest of the week.\n\nBut at least I could decide **when I wanted to be productive.**\n\nThe current system gives me a weekly allowance and then prevents me from actually using it when I want to.\n\nThat's the frustrating part.\n\nI can still have plenty of weekly usage remaining and be locked out because one agentic task demolished the smaller 5-hour bucket.\n\nSo what exactly is the weekly allowance accomplishing at that point?\n\nSoftware development is not evenly distributed throughout the week.\n\nSometimes I barely touch a project for several days.\n\nThen I have an afternoon free and want to spend four or five hours working through features, bugs, refactoring, and testing.\n\nThat is exactly where an agent like Codex is useful.\n\nYou give it a task. It explores the codebase. It implements something. It tests it. Maybe it finds a bug. It fixes the bug. It runs the browser. It verifies the behavior.\n\nThat process can be expensive, but that's also the entire point of using an agent instead of a chatbot that spits out a code snippet.\n\nIf the more thoroughly Codex works, the more likely it is to lock me out halfway through a coding session, we're creating a really weird incentive.\n\nI don't want it to skip tests to save my quota.\n\nI don't want it to avoid inspecting the codebase.\n\nI don't want it to stop verifying its changes.\n\nThose are some of the biggest reasons I use a coding agent in the first place.\n\nLooking through the OpenAI community, there are already multiple Plus users describing almost exactly the same experience.\n\nPeople are reporting ordinary development tasks consuming most or all of the 5-hour allowance while they still have significant weekly usage remaining. Some have also had Codex stop before the work was finished.\n\nThat's pretty telling.\n\nThis isn't someone trying to run an autonomous agent against a million-line repository for eight hours straight.\n\nThese are normal coding sessions.\n\nInterestingly, OpenAI's current documentation says usage depends on things like the model, task complexity, context, reasoning, speed, and tools, which makes sense. It also says an active Codex turn may continue after reaching a limit, subject to fair-use restrictions.\n\nThat certainly wasn't a very useful distinction in my case. My session still ended with a usage-limit error before the overall implementation was where I wanted it.\n\nI am completely fine with having limits on Plus.\n\nGive me a weekly compute allowance.\n\nGive me a generous rolling limit designed to prevent extreme abuse.\n\nThrottle extraordinarily expensive workloads if necessary.\n\nWhatever.\n\nBut the current setup, where one completely reasonable development task can consume an entire 5-hour allowance in about 24 minutes, is not a useful coding workflow.\n\nIf I still have weekly quota available, I would much rather be allowed to decide when I use it.\n\nMaybe I blow through the whole thing in one marathon weekend.\n\nThat's okay.\n\nAt least I got something done.\n\nRight now I have most of a Find and Replace feature, missing search highlighting, an agent that stopped before completely finishing what it was doing, and a several-hour timeout before I can ask it to continue.\n\nThat's not really a productivity tool anymore.\n\nIt's a productivity tool with a mandatory intermission halfway through and to me that makes it almost useless.", "url": "https://wpnews.pro/news/the-codex-5-hour-limit-is-making-it-practically-unusable", "canonical_source": "https://dev.to/sizzlebop/the-codex-5-hour-limit-is-making-it-practically-unusable-3nbc", "published_at": "2026-08-30 01:10:50+00:00", "updated_at": "2026-08-30 02:22:23.233817+00:00", "lang": "en", "topics": ["ai-products", "developer-tools", "artificial-intelligence"], "entities": ["OpenAI", "Codex"], "alternates": {"html": "https://wpnews.pro/news/the-codex-5-hour-limit-is-making-it-practically-unusable", "markdown": "https://wpnews.pro/news/the-codex-5-hour-limit-is-making-it-practically-unusable.md", "text": "https://wpnews.pro/news/the-codex-5-hour-limit-is-making-it-practically-unusable.txt", "jsonld": "https://wpnews.pro/news/the-codex-5-hour-limit-is-making-it-practically-unusable.jsonld"}}