Markdown version of https://extraheadroom.com/codex-usage-limits

# Codex usage limits in 2026: the 5-hour window, the weekly cap, and what each plan gets

Codex limits changed twice this year: token metering arrived in April, and the 5-hour limit was switched off during the July GPT-5.6 launch surge, then switched back on. If you searched for "did Codex remove the 5-hour limit" or keep seeing the "you've hit your usage limit" message, here is the current state of every limit, plan by plan, plus how to check what you have left.

## Quick answer

Codex meters subscription usage on a **5-hour rolling window** with a separate **weekly cap** on top. Both are active again: OpenAI temporarily removed the 5-hour limit for Plus, Pro, and Business on July 12, 2026, and restored it on July 30, 2026. Since April 2026 those plans meter by **tokens** , not messages, so heavy requests drain the window faster. Local CLI messages, cloud tasks, and ChatGPT Work draw from the same pool. Regular ChatGPT chat has its own separate allowance. Check what you have left with `/status` in the Codex CLI, or the usage page in Codex settings.

- **5-hour window:** rolling, starts with your first message. Back on since July 30, 2026.
- **Weekly cap:** separate, applies even when the 5-hour window is paused or lifted.
- **Metered by tokens** on Plus, Pro, and Business since April 2026.
- **Unlimited on no plan:** higher tiers buy bigger windows, not uncapped use.
- **When you run out:** buy credits, switch to a lighter model, or wait for the reset.

## How the 5-hour rolling window works

Once you send your first message, a 5-hour window opens. Everything Codex does inside it counts toward your allowance: your prompts, the files it reads, tool and terminal output, cloud tasks, and the model's responses. Hit the cap and you are blocked from starting new turns until the window rolls over. If a limit lands mid-turn, Codex is allowed to finish the turn it is on, within fair-use bounds.

The window is shared across surfaces. Local Codex CLI messages, Codex cloud tasks, and ChatGPT Work usage all draw from one pool, so a burst of cloud tasks shrinks what your terminal sessions have left. Regular ChatGPT chat has its own separate allowance.

## What counts toward Codex usage

Everything Codex reads and writes: your prompt, the files it opens, terminal output, logs, search results, JSON payloads, tool responses, and the model's own replies. Since April 2026 Plus, Pro, and Business meter those tokens directly instead of counting messages, so one noisy debugging turn can cost more than a dozen short prompts. The workflows that burn usage fastest are debugging from logs, codebase exploration, large JSON payloads, shell-heavy tasks, and repeated file reads.

## The weekly limit

On top of the 5-hour window sits a weekly cap sized for sustained use. It exists to stop round-the-clock consumption: you can hit your 5-hour wall with most of the week's allowance still intact, but a few maxed-out days in a row will find the weekly ceiling. When OpenAI paused the 5-hour limit in July, the weekly cap was the limit that remained, which is why "no 5-hour limit" never meant unlimited.

The weekly window resets on its own schedule, roughly seven days from when it opened. During the July capacity crunch OpenAI also reset weekly usage manually several times; those were one-off goodwill resets, not a feature to plan around.

## Did Codex get rid of the 5-hour limit? What changed in July 2026

Briefly, yes; permanently, no. The timeline:

- **July 9-11:** GPT-5.6 (Sol, Terra, Luna) rolls out and demand roughly doubles in 48 hours.
- **July 12:** OpenAI temporarily removes the 5-hour limit for Plus, Pro, and Business, and resets weekly usage to 100%. The weekly cap stays on.
- **July 12-29:** repeated weekly resets and efficiency fixes while capacity catches up.
- **July 30:** the 5-hour limit returns, as announced by the Codex team.

So if Codex feels more constrained now than it did in mid-July, nothing is broken on your end: the temporary window without a 5-hour cap ended. Some Plus and Pro accounts can still earn banked rate-limit resets through referral promotions; redeeming one resets both the 5-hour and weekly windows.

## Coding in the ChatGPT app: chat and coding limits are separate

Codex now lives inside the ChatGPT app, and the coding windows follow it there: the app's Codex tab, the `codex` CLI, cloud tasks, and ChatGPT Work all drain the same 5-hour and weekly pool. Regular chat has its own allowance. Hitting the Codex cap does not lock you out of chat, and a day of chat does not touch your coding windows, so if the Codex tab says you are limited while chat still works, the number that matters is the coding pool.

## What each ChatGPT plan gets

OpenAI does not publish fixed message caps, because since April 2026 metering is by tokens: how far a window stretches depends on how heavy your requests are. Community measurements exist, but they are estimates and drift with model efficiency changes. What is stable is the relative sizing:

| Plan | Codex capacity | You'll hit the limit when… |
| --- | --- | --- |
| Free & Go | Minimal access, enough to evaluate it. | Almost immediately for real work. |
| Plus | The entry tier for real Codex work; short focused sessions. | Heavy debugging, large file reads, or agentic multi-step runs. |
| Pro (x5 / x20) | Roughly 5x or 20x the Plus allowance; the x20 tier is sized for full-workday use. | Long multi-project days (x5); rarely (x20). |
| Business & Enterprise | Per-seat allowances comparable to Plus by default; workspaces with flexible pricing scale through purchased credits. | Depends on whether your workspace buys credits. |

No tier is unlimited. Higher tiers buy bigger windows, and Enterprise flexible pricing converts the question into a credit budget rather than a cap. The right tier depends on workflow more than seniority: many short, narrow prompts use far less than long debugging sessions with lots of file reads.

## How to check your remaining Codex usage

Three ways, from quickest to most continuous:

- **In the CLI:** run `/status` in a Codex session. It shows how much of the 5-hour and weekly windows you have used.
- **In ChatGPT:** open the usage page in Codex settings (`chatgpt.com/codex/settings/usage`) for the same numbers plus any credit balance.
- **Continuously:** if Codex routes through [Headroom](/), the app tracks both windows from your live traffic, so the menu bar shows how much runway is left before you hit either limit.

## Usage limits are not the context limit

Two different meters get conflated. The **context window** is how much a single conversation can hold before the model starts compacting or forgetting; it resets with every new session and no plan upgrade changes it. The **usage limit** is how many tokens you can push through Codex across all sessions in 5 hours or a week. The "context used" meter in the CLI is about the former; the limit messages that stop you working are the latter. Confusingly, shrinking what goes into context helps both.

## Why you hit limits sooner than expected

Most usage gets eaten by content you did not write: tool output, file content Codex reads on its own, repeated conversation history, and large search results. A single failing build or a few large file reads can use as much of your budget as a long thoughtful prompt. Under token metering this is not a rounding error; it is usually the majority of the bill.

The same window mechanics exist on the Anthropic side; if you run both agents, the [Claude Code usage limits guide](/claude-code-usage-limits) is the mirror of this page. If your question is why the bill (rather than the limit) feels high, see [Why is Codex so expensive?](/why-is-codex-expensive), and [Codex is now in ChatGPT](/codex-in-chatgpt) explains the app merger itself.

## Stretch your plan instead of upgrading

When you hit a limit, OpenAI offers two paid outs: buy extra credits or upgrade the plan. The third option is sending fewer tokens per request. [Headroom](/) intercepts your Codex traffic locally, compresses repetitive logs and boilerplate, and forwards a leaner request: about 50% fewer tokens on the noisy items it compresses, typically 25-50% across a session, so noise-heavy work can stretch the same windows up to twice as far. Same workflow, no account changes.

For the full set of tools and tactics, see the [Codex cost guide](/reduce-codex-costs), including [Ponytail](/ponytail-claude-code), the skill that attacks the output side by making Codex write less code.