ChatGPT Plus vs Pro: price, limits and who needs Pro

Plus vs Pro at a glance

Here is how ChatGPT Plus and the three ChatGPT Pro tiers compare side by side. If you just want the $20 tier details, see the full ChatGPT Plus price breakdown.

Pro 100, Pro 200 and Pro 500

Pro 200 includes more usage than Pro 100, and Pro 500 offers the highest included usage of the three, though OpenAI no longer publishes fixed usage multiples versus Plus. Pro 100 and Pro 500 now get twice their previous Work and Codex allowance (and OpenAI canceled the Pro 200 reduction it announced on September 29, keeping all Pro 200 accounts on the higher allowance at $200 a month), while Plus usage is unchanged. Weekly GPT-6 Pro message limits in Chat are separate from your Work and Codex allowance.

If you're comparing Pro 100 vs Pro 200 or looking at the $500 tier, the table below shows what changes as you move up.

Codex limits on each plan

Your Codex usage limits depend on whether you're on Plus or Pro and which speed mode you run:

• On Plus, estimated local messages per five hours are 15 to 160 for GPT-6.1 Sol, 5 to 45 for GPT-6 Astra, and 350 to 3,000 for GPT-6 Luna.
• Pro plans have no five-hour limit right now, though weekly limits may apply.
• Fast mode burns through your included usage at 2.5x the Standard rate, and Ultrafast burns it at 8x (then uses credits at 6x the Standard credit rate).
• Both Plus and Pro users can buy extra credits to keep working in Codex, ChatGPT Work, and ChatGPT for Word, Excel and PowerPoint after the included allowance runs out.

Who should pick which

Picking between Plus and the three Pro tiers comes down to how often you hit the five-hour wall and how much Codex pricing headroom you need:

• Plus: You use ChatGPT for regular chat, research and a few focused coding sessions a week.
• Pro 100: You hit Plus limits often, or you want the 400K reasoning context and Pro reasoning powered by GPT-6 Astra.
• Pro 200: You do daily heavy Codex or ChatGPT Work sessions and need a larger included allowance plus $200 in monthly API credits.
• Pro 500: You need Ultrafast mode (GPT-6 Astra Ultrafast and GPT-6.1 Sol Ultrafast) or the highest included usage and $500 in monthly API credits.

Claiming Pro's API credits

Pro 100, Pro 200 and Pro 500 include $100, $200 and $500 of monthly credits you can put toward an OpenAI API key without adding an API payment method:

1. Keep your paid Pro subscription active for at least 7 days.
2. Make sure you use the exact same email address on both ChatGPT and the OpenAI API platform.
3. Open ChatGPT, go to Settings, Billing, and start the API credits claim.
4. Pick the single API organization you want to link to your subscription.
5. Check your API billing dashboard to confirm the credits landed in your account.

Call Plus or Pro from your own code

Plan2API connects your existing Plus or Pro subscription through Codex using a one-time device code and gives you a single p2a_ key for a ChatGPT subscription API at https://api.plan2api.com/v1. You call standard OpenAI Chat Completions (POST /v1/chat/completions) with your key in the Authorization: Bearer header and pass Codex models as openai/<model> (or codex/<model>), such as openai/gpt-6-astra, openai/gpt-6.1-sol and openai/gpt-6-luna.

Every request counts against your ChatGPT plan's own Codex allowance, so a bigger Pro allowance means you can run more requests before hitting an HTTP 429 subscription_quota_exhausted error (which returns a Retry-After header in seconds). Plan2API never raises your underlying plan limits and never bills per token, and if you connect several ChatGPT accounts on one p2a_ key, a request that hits a limit on one account fails over to the next before output starts. You can start on the Free plan at $0 (no card needed) with 1 connected subscription and 50 chat requests a day, or upgrade to Pro at $12 a month (3 subscriptions, no daily request cap) or Scale at $29 a month for up to 25 connected subscriptions.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.plan2api.com/v1",
  apiKey: process.env.PLAN2API_KEY,
});

const stream = await client.chat.completions.create({
  model: "openai/gpt-6-astra",
  messages: [{ role: "user", content: "Review this SQL migration for locking issues: ..." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}