Guide
Codex Plus and Pro rate limits
ChatGPT Plus and Pro both meter Codex. Neither plan publishes a fixed request cap. The honest number is the official used-percent Codex already writes on your Mac.
Does ChatGPT Plus have a Codex limit?
Yes. Codex on Plus shares ChatGPT's agentic-usage pool. That pool has a 5-hour window and a weekly window. OpenAI does not publish a fixed request or token ceiling for Plus, so any page that quotes one is guessing. The number that is real is the `used_percent` Codex writes into its local rollout logs.
How Pro differs
Pro uses the same two windows — 5-hour and weekly — on a larger pool. JP does not invent a Plus-vs-Pro request count. It reads the official used-percent for whichever plan is on this Mac and labels it `official`. Dollar figures stay notional list price, because Codex is a subscription.
How to read the official number
Codex writes a `rate_limits` block (`used_percent`, `resets_at`) under `~/.codex/sessions`. That is the same number OpenAI enforces. JP the Cat reads it automatically with no login. If the file is missing, the honest UI is no gauge — not an estimate from tokens.
Common questions
- Is there a Codex limit on the Plus plan?
- Yes. Plus meters Codex against a 5-hour and a weekly pool. There is no published request cap; read the official used-percent Codex already stores locally.
- What are Codex rate limits for Pro users?
- The same two windows as Plus, on a larger pool. JP shows Pro's official used-percent from the local rollout logs. It will not print a guessed Pro ceiling.
- Does JP need my OpenAI login to show Plus or Pro limits?
- No. It reads the local Codex rollout logs — no credentials, no network.
See your real numbers with JP the Cat
A light, local menu-bar meter for Claude Code, Codex, Grok, and Muse Spark — real cost, honest limits.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat