# Plus and Pro

## After the top-up, check that it's active

After you submit at [cz.2api.dev](https://cz.2api.dev):

1. Refresh [chatgpt.com](https://chatgpt.com), or fully quit the app and open it again.

2. Click your avatar in the bottom-left corner to open the profile menu. Make sure you're signed in to the account you submitted for the top-up.

3. Open settings and check your current plan under **Billing**. If it shows Plus or Pro, it's active. You can also open the [Codex usage page](https://chatgpt.com/codex/settings/usage), which shows the usage limits for your plan.

**It still shows Free**:

- Make sure the account and the sign-in method match the ones you used for the top-up. See the pitfalls in [Sign in](https://docs.2api.dev/en/guides/login/#sign-in-with-a-chatgpt-account).
- Sign out and sign in again. If you're signed in on several devices, sign in again on each one.
- Check again in a few minutes.
- If it still doesn't work, [contact support](https://docs.2api.dev/en/support/) with your account email and the time of the top-up.

**Once it's active**: [download the app](https://docs.2api.dev/en/guides/install/), [sign in](https://docs.2api.dev/en/guides/login/) with the account you topped up, then read [Using ChatGPT and Codex](https://docs.2api.dev/en/guides/usage/).

## What Plus and Pro include

The table below follows OpenAI's English pricing page. Pro comes in three tiers, which differ mainly in usage.

| | Plus | Pro |
| --- | --- | --- |
| Models | GPT-6 reasoning models | Everything in Plus, plus Pro reasoning based on GPT-6 Astra |
| Codex and Work | Expanded usage | Longer Codex and Work sessions |
| Image generation | More complex, more accurate image generation | Unlimited and faster |
| Deep research | Expanded | Highest tier |
| Memory and context | Expanded | Highest tier |
| Projects, scheduled tasks, custom GPTs | Included | Expanded |
| Other | Early access to new features | Research previews of new features, the always-on assistant Dot, monthly API credits (the amount depends on the tier) |

Context length: on Plus, 54K for instant models and 256K for reasoning models. On Pro, 128K and 400K.

Features listed as "unlimited" still have limits against abuse. Go by what OpenAI says.

## Usage limits

- **Chat**: text chat has no message cap on any plan, but there are limits against abuse.
- **Codex and Work**: Plus counts usage in 5-hour windows, and there may also be a weekly limit. Pro currently has no 5-hour limit. Local tasks and cloud tasks share the same usage, and cloud tasks use it up faster. Generating images uses it 3 to 5 times faster than ordinary conversations.
- Below is roughly how many local messages Plus can send every 5 hours. These are OpenAI's estimates, not fixed caps, and they depend a lot on the size of the task:

  | Model | Every 5 hours |
  | --- | --- |
  | GPT-6 Astra | 5–45 messages |
  | GPT-6.1 Sol | 15–160 messages |
  | GPT-6.1 Terra | 35–285 messages |
  | GPT-6 Sol | 15–150 messages |
  | GPT-6 Luna | 350–3,000 messages |

- **Check remaining usage**: open [chatgpt.com/codex/settings/usage](https://chatgpt.com/codex/settings/usage) to see your current limits and reset times. You can also type `/status` or `/usage` in the Codex CLI.
- **Used it all up**: wait for the reset, or buy extra credits in ChatGPT to keep going. You don't need to upgrade your plan.

## Run Codex on your subscription

Once your plan is active, choose **Sign in with ChatGPT** in Codex. Codex then uses the usage included in your subscription. See [Sign in](https://docs.2api.dev/en/guides/login/).

If your subscription's allowance runs out and you have 2api balance, connect Codex to magpie and pick a model marked · 2api from Codex's model menu. See [Use it with a ChatGPT subscription](https://docs.2api.dev/en/magpie/#use-it-with-a-chatgpt-subscription).

Free and Go can only use Codex (GPT-6 Luna) in the desktop app. Plus and Pro can also use it in the CLI, the IDE extension, on the web and on iOS.

---

This page follows OpenAI's official documentation, checked in October 2026. OpenAI updates often, so button names and menu locations may differ slightly. Go by what you see on screen.