The Codex 5-Hour Limit Is Making It Practically Unusable
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. Not because I expect unlimited access. I don't. I completely understand that these models are expensive to run and there need to be usage limits somewhere. The problem is that the 5-hour window makes it incredibly difficult to actually use Codex for the…
OpenAI has reintroduced a 5-hour usage limit for Codex on Plus, but users are finding it nearly unusable. The issue stems from the fact that one simple coding task can consume the entire allowance within 24 minutes. While OpenAI acknowledges that costs necessitate usage limits, the 5-hour window has made it difficult for users to plan and utilize Codex effectively.
Previously, the weekly limit was more usable, allowing users to work on projects as they saw fit, but the current setup prevents users from using their allotted time when they want to. This has led to frustration among Plus users, with many reporting that one task can consume most or all of the 5-hour allowance, even with significant weekly usage remaining.
Codex's ability to work thoroughly and efficiently is often hampered by the system's inability to continue working after hitting the limit, which defeats the purpose of using an agent instead of a simple code snippet generator.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
