OpenAI Codex CLI

What is OpenAI Codex CLI?

OpenAI Codex CLI is OpenAI's terminal-native coding agent: an open-source (Apache-2.0), locally-run command-line tool that inspects code, edits files, runs commands and automates repeatable engineering work without leaving the shell. It installs as a standalone binary (curl script, npm, Homebrew) with IDE extensions for VS Code, Cursor and Windsurf, plus a desktop app and a cloud-hosted agent at chatgpt.com/codex. It draws on the same GPT-5.6 model family and credit pool as ChatGPT, so it is bundled into Free, Go, Plus and Pro ChatGPT plans rather than sold as its own subscription — though since June 24, 2026, new Business workspaces (or ones that never previously added a Codex seat) can no longer get one, and Enterprise remains a custom, sales-led add-on.

What does OpenAI Codex CLI do?

From the terminal, the desktop app, or an IDE panel, you hand Codex a task and it explores the repo, plans, edits files and runs real commands; /permissions controls exactly when it may act without asking and which directories stay writable. It defaults to GPT-5.6 Sol at medium reasoning effort, switchable per session via /model. Built-in extras include codex resume to reopen a past session, codex --image for visual context, delegated subagents for focused sub-tasks, codex --search for live web lookups, MCP server connections to external tools, a skills/plugin system for packaging team instructions, and a code-review mode (running GPT-5.3-Codex) that flags issues in uncommitted changes before you commit. codex cloud hands a task to OpenAI’s hosted infrastructure to run asynchronously instead of on your own machine. Since April 2, 2026, usage is metered as credits mapped directly to input, cached-input and output tokens rather than flat per-message estimates, drawn from the same pool as ChatGPT Work and Workspace Agents where those are enabled on your plan.

Key features

• Configurable sandbox + permissions: /permissions sets exactly when Codex may edit files or run commands without asking, and which directories stay writable, inspectable before every run.
• Subagents, skills and MCP: Delegate focused sub-tasks to subagents, package team instructions as reusable skills/plugins, and connect external tools over MCP.
• Built-in code review: A dedicated review mode (running GPT-5.3-Codex) scores uncommitted changes and surfaces prioritized findings before you commit.
• Local, desktop and cloud surfaces: The same agent runs in the terminal, as a native desktop app, inside VS Code/Cursor/Windsurf, or asynchronously in the cloud via codex cloud.
• Token-metered credits: Since April 2026, usage bills as credits mapped to input/cached-input/output tokens per task, replacing the older flat per-message estimate.

What are OpenAI Codex CLI's use cases?

• Terminal-driven feature work: A developer already paying for ChatGPT Plus hands Codex a scoped feature ticket from the shell and reviews the diff before committing.
• Pre-commit code review: Before opening a PR, a developer runs Codex’s review mode against their uncommitted changes to catch issues a human reviewer would flag.
• Async cloud delegation: A developer kicks off a longer task via codex cloud and comes back to a finished diff instead of babysitting a local terminal session.

What does OpenAI Codex CLI integrate with?

• VS Code, Cursor and Windsurf IDE extensions
• MCP servers (external tool connections)
• Ollama, LM Studio and Amazon Bedrock (built-in local/alternate providers)
• OpenAI API key auth (bypasses ChatGPT billing entirely)
• GitHub (via `codex cloud` PR workflows)

Why use OpenAI Codex CLI?

• No separate subscription, Codex access is bundled into the ChatGPT plan you may already pay for, from a limited Free tier up through Enterprise.
• The CLI itself is genuinely open-source (Apache-2.0, 99.6k GitHub stars) even though the models it calls are OpenAI’s proprietary GPT-5.x family.
• Granular, inspectable sandbox and permission controls, not just an all-or-nothing autonomy toggle.
• One agent across four surfaces, terminal, desktop app, IDE extension, and an async cloud runner, without switching tools.

Pros & cons

OpenAI Codex CLI pricing

• FreeFree
• Go$8 / /month
• Plus$20 / /month
• Pro$100 / /month (5x Plus usage) or $200/month (20x Plus usage)
• Business$20-$25 / /month per seat ($20 billed annually, $25 billed monthly; 2-seat minimum)
• API keyUsage-based

See current pricing on developers.openai.com ↗Compare OpenAI Codex CLI alternatives →

OpenAI Codex CLI review

Codex CLI’s biggest advantage isn’t a feature — it’s bundling: because it draws on the same plan and credit pool as ChatGPT, a developer who already pays for Plus, Pro or Business gets a capable, actively-maintained terminal coding agent with no separate subscription decision to make, and even the Free plan gets limited access to try it. The tool itself is well-built and open-source, with granular permission controls, subagents, MCP support and a genuinely useful built-in code-review mode running across terminal, desktop and IDE surfaces. The honest catches are real: switching to a non-OpenAI model takes manual config beyond the built-in Ollama/LM Studio/Bedrock options, OpenAI’s own numbers put typical cost at $100-$200/developer per month for regular use, and a large, currently-open GitHub issue documents a real rate-limit consumption regression from June 2026 that was still unresolved as of this listing’s last check. Pick Codex CLI if you already live in the ChatGPT ecosystem and want a terminal agent without a new bill; pick Claude Code instead if you want a lower, more predictable entry price, or Windsurf/Juggler if free multi-model switching matters more to you than OpenAI’s specific model lineup.

A genuinely capable, actively-shipped terminal agent whose real edge is distribution, it rides on a ChatGPT subscription you may already have, but watch the credit-based billing and the still-open June 2026 rate-limit regression before committing to heavy daily use.

Frequently asked questions