ChatGPT plans for Codex: Plus, Pro and Business limits

What each plan includes for Codex

• Free and Go: GPT-6 Luna at Standard speed in the ChatGPT desktop app, subject to rollout. Image generation isn't available on Free.
• Plus: Codex on the web, in the CLI, IDE extension and on iOS, cloud integrations like automatic code review and Slack, GPT-6.1 Sol and GPT-6 Luna, and ChatGPT credits to extend usage.
• Pro: everything in Plus, with plans at $100, $200 or $500 a month. Pro 200 includes more usage than Pro 100, and Pro 500 has the most, plus Ultrafast.
• Business: ChatGPT and Codex across desktop and mobile, larger cloud VMs, credits, SAML SSO and MFA, and no training on business data by default.
• API key: Codex in the CLI, SDK or IDE extension at API rates, without cloud features like GitHub code review or Slack.

How Codex usage limits work

Per OpenAI's Codex pricing page, Codex and ChatGPT Work share the same pricing, credits and usage limits. OpenAI publishes estimates of local messages per five-hour period for Plus and Standard Business, says Pro plans currently have no five-hour limit, and notes that weekly limits may also apply. The estimates aren't fixed limits: model choice, context, reasoning, tool use and caching all change how fast you use your allowance, and cloud tasks may use more than local messages. Fast mode uses included limits at 2.5x the Standard rate, and Ultrafast at 8x. Check the usage dashboard, or run /status in the CLI.

Pro 100, Pro 200 and Pro 500

• Pro is billed monthly. Annual billing isn't available.
• Ultrafast is only on Pro 500 among the Pro plans. Buying credits on Pro 100 or Pro 200 doesn't unlock it.
• New Pro 200 subscriptions get a lower usage allowance than Pro 200 used to include. Subscribers who were active between 22 September 2026 and 10 a.m. PT on 29 September 2026 keep the previous allowance through 29 October 2026, per the Pro tiers article.
• Model allowances vary by tier. When a model hits its limit it may be unavailable until its allowance resets, and ChatGPT shows the reset time when it can.

When you hit your limit

• If you hit the limit mid-turn, the agent can finish that turn, subject to fair use limits.
• Plus and Pro users can buy credits. Business, Edu and Enterprise plans with flexible pricing can buy workspace credits.
• Anyone can run extra local chats with an API key, billed at standard API rates.
• Credit rates per million input / cached input / output tokens: GPT-6 Astra 250 / 25 / 1,250, GPT-6.1 Sol 50 / 2.5 / 250, GPT-6 Sol 50 / 5 / 250, GPT-6 Luna 2.5 / 0.25 / 12.5. There's no separate cache-write charge.