What it does
- Implement changes across a repository
- Diagnose failures and run tests
- Review code and proposed changes
- Delegate coding tasks to cloud environments
What it costs in the US
Included in ChatGPT plans; Plus $20/mo; Pro from $100/mo; extra credits may be available
Free and Go include limited trial access. Plus is $20 per month. Pro starts at $100 per month, with current tiers offering 5× or 20× Plus usage. Business is $20 per user monthly when billed annually or $25 month to month, with at least two users. Enterprise and Edu use sales-led pricing. OpenAI's newer rate card says Plus, Pro, and Business accounts plus most Enterprise-family accounts use token-based rates, while its Codex pricing page still says only Business and new Enterprise accounts have migrated; check the Usage panel for the meter that applies to your account. Some Plus and Pro users can add credits, while others may need to upgrade or wait for a reset. All users can run extra local tasks with an API key at standard API rates. Credit use depends on the model, input and output token mix, speed, and any additional agents. OpenAI publishes a cross-plan planning estimate of roughly $100–$200 per developer per month, with large variance; it does not define an included allowance or predict an individual bill.
From the company · collected Open pricing page (opens in a new tab)
Where you can use it
- Access
- Available through Codex in ChatGPT, the desktop app, CLI, IDE extension, web, and iOS, subject to plan, platform, and workspace settings. The Codex IDE extension also supports Cursor and Windsurf; OpenAI documents separate integrations for Xcode and JetBrains IDEs. Local CLI, IDE, and SDK use can instead authenticate with an API key; API-key access does not include cloud features such as GitHub code review or Slack.
- Platforms
- Web · macOS · Windows · Linux · iOS · Terminal · VS Code
- Processing
- Local workflows run commands on the user's device under configurable sandbox, approval, and network policies; the CLI can also use OSS models served by Ollama or LM Studio. Cloud tasks run in isolated OpenAI-managed environments; setup scripts have internet access, while agent internet access is off by default unless configured.
Questions to settle
- Should work run locally, in an OpenAI-managed cloud environment, or both?
- Which commands, files, network destinations, and changes must require approval?
- Will ChatGPT plan limits, purchased credits, or API billing be easier to govern?
Limits to check
- Free and Go include limited trial access. Usage varies by plan, model, task size, context, tools, and whether work runs locally or in the cloud.
- OpenAI's newer rate card says Plus, Pro, and Business accounts plus most Enterprise, Edu, Health, Gov, and Teachers accounts use token-based rates; its Codex pricing page still says only Business and new Enterprise accounts have migrated. A small subset of Enterprise accounts remains on legacy message rates. Check the Usage panel for the meter that applies to your account.
- Codex draws from an agentic usage and credit pool shared with other eligible ChatGPT agent features. Credit use varies by model, input and output token mix, speed, and any additional agents. OpenAI publishes a cross-plan planning estimate of roughly $100–$200 per developer per month, with large variance; it does not define an included allowance or predict an individual bill.
- Codex cloud requires ChatGPT sign-in. API-key authentication supports local CLI, IDE, and SDK use but excludes cloud features.
- For Plus and Pro, OpenAI may use Codex content to improve models. ChatGPT conversations and Codex tasks can be opted out through ChatGPT data controls or the privacy portal, but full-environment Codex training has a separate control in Codex Settings; changing the general controls does not change that full-environment setting. Business, Enterprise, Edu, and API inputs and outputs are not used for training by default; eligible API organizations can opt in.
- Sandboxing, approvals, and network controls reduce risk but require configuration and review; cloud agent internet access is off by default.
Using sensitive material
This profile does not establish whether the product is appropriate for confidential work. Check the company’s current data-use terms and your organization’s requirements before uploading it.
Sources
- Codex product pageFrom the company · collected (opens in a new tab)
- Codex IDE extensionFrom the company · collected (opens in a new tab)
- Codex pricingFrom the company · collected (opens in a new tab)
- Codex rate cardFrom the company · collected (opens in a new tab)
- Using Codex with your ChatGPT planFrom the company · collected (opens in a new tab)
- AuthenticationFrom the company · collected (opens in a new tab)
- SandboxingFrom the company · collected (opens in a new tab)
- Cloud environmentsFrom the company · collected (opens in a new tab)
- OSS mode and local providersFrom the company · collected (opens in a new tab)
- Code reviewFrom the company · collected (opens in a new tab)
- OpenAI data controls and trainingFrom the company · collected (opens in a new tab)
- ChatGPT Plus pricingFrom the company · collected (opens in a new tab)