Skip to content
TraeIDE

Search

Popular pages

No matching pages

Try a tool name or a topic such as pricing or MCP.

English

Codex Guide

OpenAI’s coding agent, available through CLI, IDE and cloud workflows.

Last verified: · How we verify
Coding agentOpenAImacOSWindowsLinuxWeb

Suitable workflows

Developers evaluating a coding agent without making it their editor.

Limitations and billing

ChatGPT access and API billing are separate options. Features and limits depend on sign-in method.

Capabilities we verified

Agent workflowCLI surfaceMCPSkillsCloud agents

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

Paid from $8/mo

ChatGPT plan or API usage. The cost of metered usage or an external agent can be separate from the subscription.

Check official pricing ↗

Models & access

Model access varies by ChatGPT plan or API credentials.

Verified families: GPT.

Official model information ↗

Install and start the CLI

npm for the command below; standalone installers are also available for each desktop platform.

Installation command · npm

npm install -g @openai/codex

Open your project folder in a terminal, then run:

codex
Official installation instructions ↗

Account and authentication

Run codex in your repository and complete the ChatGPT or API-key sign-in flow.

Project configuration and tools

Use AGENTS.md for project instructions and codex mcp to manage external tools. Review permissions before automation.

First task to try

Locate the project’s test command, explain the main modules, then review one small diff.

Script usage

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

codex exec "Summarize the project structure without modifying files."
Official configuration reference ↗

Related CLI tools

All AI CLI tools →

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.