OpenAI Codex pricing & limits

How OpenAI Codex usage limits work

Codex is included with ChatGPT Free, Go, Plus, Pro, Business, Edu and Enterprise plans, and it shares usage with ChatGPT Work.

OpenAI gives estimates rather than fixed message counts. Plus and Standard Business get roughly 15-160 local messages per five hours on GPT-6.1 Sol, 5-45 on GPT-6 Astra and 350-3,000 on GPT-6 Luna. Weekly limits may also apply, and cloud tasks can use more of the allowance than local messages.

Pro plans ($100, $200 or $500) currently have no five-hour limit. Fast mode uses included usage at 2.5x and Ultrafast at 8x. Image generation uses limits about 3-5x faster.

When limits reset

Five-hour windows plus weekly limits. OpenAI says to check your usage dashboard for current limits and reset times.

What happens when you hit the limit

An active turn can finish, subject to fair use. Plus and Pro users can buy extra ChatGPT credits, Business/Edu/Enterprise with flexible pricing can buy workspace credits, and anyone can run extra local chats with an API key at standard API rates.

How to check your usage

The Codex usage dashboard shows current limits. During a Codex CLI session, run /status.

Source: https://developers.openai.com/codex/pricing, read 2026-10-20.

Limits by plan

• Free ($0): GPT-6 Luna, desktop app, subject to rollout
• Go ($8): Lightweight tasks, GPT-6 Luna
• Plus ($20): Est. 15-160 messages/5h on GPT-6.1 Sol (local + cloud share allowance); weekly limits may apply
• Pro ($100 / $200 / $500): No 5-hour limit currently; Ultrafast on $500
• Business ($20/user (annual, 2+ users), $25 monthly): Codex across desktop and mobile; same per-5h message estimates as Plus