Codex CLI

Codex CLI
OpenAI's Terminal Coding Agent

Open-source AI coding tool built with Rust, supporting current models like gpt-5.6-sol (verified 2026-09-19), local execution and MCP integration

Updated 2026-09-21

#CodexCLI #OpenAI #AICoding #2026

What Is Codex CLI

Codex CLI is OpenAI's open-source terminal coding agent. It runs on your own machine, reads your code, edits files and executes commands. Written in Rust, installed globally with npm, and it works inside your project directory once you sign in (official repository checked 2026-09-21).

You steer a session with slash commands: /model sets the model and reasoning effort, /permissions decides what it may do, /init writes an AGENTS.md for the repo, /review checks your changes (command names taken from the official CLI docs snapshot archived 2026-08-24).

By 2026 it is no longer terminal-only: the official repository also links the IDE extension, the desktop app and the cloud-based Codex, and the whole repo is open under the Apache-2.0 license (checked 2026-09-21).

Check the dates first

Model names, install steps and the feature list here were checked on 2026-09-21 against the official repository and an archived CLI docs snapshot. Upstream ships fast, so re-read the official page before you rely on it.

Written in Rust
Apache-2.0 licensed
Runs locally
MCP server support

Installation Guide

1

Step 1: Install

Install globally via npm: npm i -g @openai/codex

npm install -g @openai/codex
2

Step 2: Authenticate

Log in with ChatGPT account or API key

export OPENAI_API_KEY=sk-...
3

Step 3: Launch

Run the codex command in your project directory

codex "explain this project"
4

Step 4: Select Model

Use /model to switch among current models (e.g. gpt-6-sol)

Key Features

Sessions and images

Reopen a recent chat from this repository, dig through older local sessions, or paste a screenshot into the prompt.

MCP tool access

Add local or remote MCP servers, check which tools the session can reach, then let Codex use them.

Live web search

Switch to live web search when a task depends on fresh releases, docs or external behavior; the search stays in the transcript.

Project instructions

Run /init to generate an AGENTS.md, then keep build commands and code conventions there for later sessions.

Sandbox and approvals

Decide when it may edit files or run commands without asking, and inspect the active sandbox and writable roots first.

Non-interactive mode

Non-interactive commands fit repeatable workflows, so you can wire them into scripts and pipelines.

Codex CLI vs Claude Code

How the two terminal coding agents differ, row by row (checked 2026-09-21).

Dimension Codex CLI Claude Code
Architecture Rust, runs locally Terminal, IDE, desktop, web
Model Model set via /model Alias or full model name
Context Follows model and effort Extended context, auto-compact
Pricing Part of ChatGPT plans Subscription or token billing
Execution Local terminal plus sandbox Reads, edits, runs commands
Agent features Delegates to sub-agents Sub-agents and agent teams
Voice mode Not verified Built-in /voice dictation
Open source Open source, Apache-2.0 Under Anthropic terms of service

Codex CLI leans on open source and local runs, Claude Code on more clients and parallel agents; the real gap is collaboration.

Use AI Coding Tools via QCode.cc

On-sale ids like gpt-5.6-sol and claude-opus-5 share one API key.

Both ids come from the models page we checked on 2026-09-21.

Released models share one key

On-sale (released) models share one key, switching means editing a name; announced or rumored ids may not answer yet.

Switching is a config edit, not a code change

Switch between gpt-5.6-sol and claude-opus-5 on one account; the models page sets the parameters.

Billed per token, rates on the pricing page

Use the pricing page for the billing model and rates; this page quotes no figures.

One model catalog

On-sale ids sit on one models page, gpt-5.6-sol and claude-opus-5 included; confirm it is still listed before you buy.

Practical tips

Start read-only, run one pass, then allow edits. Keep build commands and conventions in AGENTS.md, and run /review before you commit.

Where it fits

Reworking existing repos

For renames at scale, dependency bumps and test backfill: let it read the layout, propose a plan, then approve each step.

Repeatable pipeline steps

Non-interactive runs fit scripts and pipelines: produce change summaries, run routine checks, replay the same steps.

Checking external behavior

When the answer depends on current version numbers or third-party APIs, live search beats an answer from stale memory.

Codex Ecosystem Expansion

From CLI tool to super app — the OpenAI Codex ecosystem received a comprehensive upgrade in 2026.

New in Q1 2026

Codex Desktop App

Native desktop app for macOS and Windows, supporting parallel management of multiple Agent instances without terminal.

  • macOS + Windows dual platform
  • Parallel management of multiple Agent instances
  • Visual task queue and execution status
Launched 2026-04-06

ChatGPT Super App Merge

On April 6, 2026, ChatGPT, Codex CLI, and Atlas browser merged into the ChatGPT Super App.

  • Unified: Chat + Code + Browse
  • Cross-modal task orchestration
  • Plugin ecosystem fully open

Latest Model Lineup

GPT-5.3-Codex-Spark

Coding-specialized, highest SWE-bench score

GPT-5.4

Flagship model with Codex coding capabilities

GPT-5.5

Dedicated model for Super App multimodal tasks

Start Using AI Coding Tools

Once connected, run the same task on two models and see which one you keep.

UPDATE · 2026-05

2026 Q1-Q2 Major Updates

GPT-5.3-Codex (2026-02-05) became the most capable agentic backend for Codex — SOTA on SWE-Bench Pro / Terminal-Bench / OSWorld / GDPval, 25% faster than 5.2-Codex, with real-time steering. Codex CLI itself added Amazon Bedrock backend support, enhanced /mcp diagnostics (status, timeouts, auth-error breakdown), persisted /goal workflows, and MultiAgentV2 multi-agent coordination. China users access GPT-5.5 / Codex via the QCode gateway with shared subscriptions.

Read the GPT-5.3-Codex complete guide

Create a QCode account

Plans from ¥60 / $8.57. One key across Claude, GPT, and Gemini models.

Try first, then decide

Not sure which tier? Start with Starter ($8.57/mo) and upgrade when you're happy — the unused value of the old plan goes back to your balance.