How is Codex billed? How to check its relationship with a ChatGPT subscription
Signing in to Codex with a ChatGPT account gives you the features and limits included in your plan; API key access is billed separately. Compare official monthly prices by entry point, and check current limits through the usage dashboard link on the pricing page or with /status.
Codex (OpenAI's coding assistant) is included in several ChatGPT plans. When you sign in with a ChatGPT account, you get the features and limits that correspond to your plan. If you authenticate with an API (application programming interface) key, usage is billed separately at API rates; a subscription cannot be treated as API credit.
If I already have a subscription, do I need to buy Codex separately?
The official OpenAI pricing page states that Free, Go, Plus, Pro, Business, Edu and Enterprise all include Codex, but the entry points and usage differ.
First confirm which authentication method the tool in use relies on: signing in with a ChatGPT account uses plan limits; API key authentication is charged at API prices. Even for the same tool, you must first distinguish the authentication method before determining where the cost falls.
What is the official monthly price, and how do I choose by entry point?
As of October 15, 2026, the official pricing page above lists the following monthly prices for individual plans, in US dollars:
Plan
Official monthly price
Codex usage scope
Free
0
GPT-6 Luna in the desktop app, Standard speed, subject to gradual rollout
Go
8
GPT-6 Luna in the desktop app, Standard speed, subject to gradual rollout
Plus
20
Supports web, command line, code editor extensions and iOS
Pro
100, 200 or 500
Includes Plus features, with different usage tiers
First confirm whether the models, speeds and desktop entry currently available on Free and Go meet the task; if you need entry points such as web or command line, compare Plus and Pro next.
Among team plans, Business requires at least two people; annual billing works out to USD 20 per person per month, and monthly billing is USD 25 per person per month. Enterprise and Edu require contacting sales. These are all official prices and apply separately from this site's RMB retail prices.
Where can I check current limits and reset times?
Web or desktop users can check as follows:
Open the official pricing page above and find "Where can I see my current usage limits?" in the FAQ.
Click the "usage dashboard" link under that question to view your current limits and reset time.
When running Codex CLI (command-line tool), you can also enter /status to view remaining limits.
Whether a plan is sufficient should be judged from the dashboard and actual consumption. The message counts on the pricing page are estimates, not fixed numbers; task complexity, context and tool use all affect consumption, so you cannot estimate from prompt length alone.
Does switching entry points give me a separate quota?
Local messages and cloud tasks share plan usage; cloud tasks may consume more and may also be subject to weekly limits. ChatGPT Work and Codex also share usage, so counting usage on only one entry point may not explain changes in remaining limits.
Before comparing plans, record your usual entry points, task scale and dashboard changes. Higher usage does not mean unlimited.
If I run out of quota, do I have to upgrade?
Not necessarily. Check the reset time first: if you can wait, plan your work around it; if you need to keep working, Plus and Pro users can buy additional credits without upgrading first. Business, Edu and Enterprise workspaces on flexible billing can also buy additional workspace credits.
The price of credits depends on your plan or agreement; API unit prices cannot be used to infer how many tasks a subscription includes. You should also compare needs beyond coding; see the ChatGPT subscription cost overview.
FAQ
If I have a ChatGPT subscription, do I need to buy Codex separately?
No. Signing in to Codex with a ChatGPT account uses the limits and features of your plan; only API key authentication is billed separately based on API usage, and a subscription cannot be treated as API credit.
What is the monthly Codex cost for each plan?
According to the official pricing page as of October 15, 2026: Free USD 0, Go USD 8, Plus USD 20, and Pro USD 100, 200 or 500. These are official prices and apply separately from this site's RMB retail prices.
How can I check how much quota I have left?
Web or desktop users can find "Where can I see my current usage limits" on the official pricing page and click the usage dashboard link there to view limits and reset times; when running Codex CLI, you can also enter /status.
Are local and cloud usage counted as separate quotas?
No. Local messages and cloud tasks share plan usage; cloud tasks may consume more and may also be subject to weekly limits. ChatGPT Work and Codex also share usage.
Do I have to upgrade if I run out of quota?
Not necessarily. Check the reset time first; if you can wait, schedule your work accordingly. If you need to keep working, Plus and Pro users can buy additional credits without upgrading first.
Many people search for "Codex top-up" only after running into a usage-limit notice, and then are unsure whether Codex requires buying a separate membership. That order is backwards and often leads to unnecessary spending. The right order is to understand how Codex is billed first, then decide whether to wait, top up, or upgrade the plan.
Where you check your ChatGPT renewal date depends on where you subscribed: web subscriptions in your account settings, Apple in-app purchases in the system subscription list, Google Play on the Play Store subscriptions page, and self-serve Business in the workspace billing page. This article distinguishes the next charge date from the expiration date, gives the lookup steps for each channel, the 24-hour cancellation cutoff, and the order to troubleshoot in when you cannot find the date.
According to the OpenAI official supported countries list verified on 2026-11-20, Hong Kong is not included. The official rule is that the API is unavailable in locations outside the list, and access from outside the list may result in an account being banned or suspended. This article shows Hong Kong users how to check eligibility in three layers — official list, network exit, account status — and explains the order in which to handle a regional error and why a proxy is not a solution.
ChatGPT Business is OpenAI's self-serve ChatGPT workspace plan for teams, priced per seat: a minimum of 2 seats, with Standard seats at 25 USD per person per month on monthly billing or 20 USD per person per month on annual billing, and Premium seats at 125 USD per person per month on monthly billing or 100 USD per person per month on annual billing; API usage and credits beyond the included allowance are billed separately.
Gemini's cost is a subscription fee charged through Google One storage membership and Google AI plans. Every account starts with up to 15GB of free storage, paid tiers start at 100GB, and Google AI plans with AI features start at 200GB. Tiers are based on storage capacity and billed monthly or annually, and the final amount is determined by the tier, the billing cycle, and the billing location. This article checks the storage and availability of each tier and the steps to upgrade, change, or cancel. It also explains the ChatGPT top-up path that readers in Hong Kong and Taiwan can complete with Alipay or WeChat Pay.
The ChatGPT registration region restriction is a rule under which OpenAI only allows users to register accounts and create API keys in countries or regions on its official supported list. This article explains what error you see when registering outside the list, how OpenAI determines the registration region, and why phone number or identity verification must be completed by the account holder. It also sets out the boundary of our top-up service: we handle payment only, not registration or verification.
ChatGPT subscription fees are non-refundable by default. Only a few exceptions may be approved: billing errors confirmed by OpenAI, verified unauthorized charges, documented service or access failures, and an unused individual subscription within 7 days that meets the conditions. The EU, UK, Turkey, South Korea, and Brazil also have statutory refund rights. Accidental purchases, forgetting to cancel, dissatisfaction, and switching plans are not, in themselves, grounds for a refund. This article sets out, by channel and region, the situations in which you can and cannot apply.
Netflix bills monthly only, with no annual plan. Based on the Hong Kong page verified on 2026-11-18, the three ad-free tiers cost HK$78 (Basic), HK$98 (Standard) and HK$118 (Premium) per month, and each extra member costs HK$31 per month. If you only want 4K for yourself, the official service sells you a whole household with 4 slots, whereas our Hong Kong Premium 4K shared slot sells a single position for ¥33 per month and accepts Alipay and WeChat Pay, which is better suited to one person's own use.
MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources; it solves the problem of manually copying and pasting data from tools into the AI. This article explains what it is for, gives the four commands for adding, checking, using, and removing a server in Claude Code, a comparison table of the four connection methods, and the troubleshooting order when a connection fails. It closes with how readers in Hong Kong and Taiwan can complete the payment step for AI tool subscriptions using Alipay, WeChat, and RMB.
An AI Agent is an AI program that can break down a task itself, call tools and work through multiple steps until the job is done, which is quite different from a chatbot that only handles one question and one answer. This article explains the difference and a three-step way to tell them apart, gives the steps for anyone to start using their first agent, and explains how readers in Hong Kong and Taiwan can subscribe to ChatGPT with Alipay or WeChat when they have no usable foreign-currency credit card.
There is no fixed completion time for a top-up: account status, official risk control, queue conditions, and payment confirmation together determine how fast it goes. We do not make a fixed promise; the status on the order page is authoritative. This article breaks down the four factors and explains when to keep waiting and when to contact support.
A GPT version number is a model name; it is not the same as the list your account can actually call. Which models you can use is decided jointly by your plan tier, whether the model has been retired, and the allowance available at the time: older models such as 4o are being retired, Go does not include older models, Think uses GPT-5.6 Luna, and only Pro 500 includes Ultrafast. Always verify against the model picker.