Gemini CLI vs Codex CLI

Gemini CLI is Google's open-source terminal agent for Gemini models. Codex CLI is OpenAI's open-source agent for OpenAI models. Both use Apache-2.0 and offer headless runs and MCP.

Where they differ

Free access. Google ended free Code Assist for individuals and Google AI Pro and Ultra access on 2026-06-18 and points them to Antigravity CLI. Codex CLI is included in a ChatGPT free tier with usage limits.
Sign-in. Gemini CLI uses a Code Assist licence, a paid Gemini API key or Vertex AI. Codex CLI uses a ChatGPT plan or an OpenAI API key, and API-key use excludes cloud features.
Sandboxing. Gemini CLI documents macOS Seatbelt, Docker or Podman, and gVisor on Linux. Codex CLI has a sandbox and a native Windows sandbox.
Maturity. Gemini CLI is version 0.x and not optimised for the newest Gemini models, per its README.

Which fits

Pick Gemini CLI if your team holds a Gemini Code Assist licence or a paid Gemini or Vertex key.
Pick Codex CLI if you have a ChatGPT plan or OpenAI key.

	Gemini CLI	Codex CLI
platforms	macOSWindowsLinux	macOSWindowsLinux
price	FreeThe CLI is free (Apache-2.0), but the free consumer route has ended (seen 2026-10-28).	FreeThe CLI itself is free (Apache-2.0). Model cost comes from your OpenAI account (seen 2026-10-28): sign in with a ChatGPT plan, where Codex is…
source	Open source	Open source
MCP	✓ yes	✓ yes
Multi-agent	✓ yes	✓ yes
Headless / CI	✓ yes	✓ yes
Sandbox	✓ yes	✓ yes
Local models	? not verified	? not verified
Your own API key	✓ yes	✓ yes
Git worktrees	? not verified	? not verified
SSH	? not verified	? not verified

Gemini CLI

Codex CLI

platforms

macOSWindowsLinux

price

FreeThe CLI is free (Apache-2.0), but the free consumer route has ended (seen 2026-10-28).

FreeThe CLI itself is free (Apache-2.0). Model cost comes from your OpenAI account (seen 2026-10-28): sign in with a ChatGPT plan, where Codex is…

source

Open source

MCP

✓ yes

Multi-agent

✓ yes

Headless / CI

✓ yes

Sandbox

✓ yes

Local models

? not verified

Your own API key

✓ yes

Git worktrees

? not verified

SSH

? not verified

Codex CLI is stronger at

Apache-2.0 with a very active repo (release published 2026-10-27)

Two sign-in routes: ChatGPT plan (including a $0 Free tier listed on the pricing page) or an API key

Documented codex exec for CI/scripts, local and remote MCP servers, subagents, and a permissions command showing the active sandbox

Native Windows sandbox documented, plus standalone installers for macOS, Linux and Windows

Gemini CLI is stronger at

Apache-2.0 with weekly stable/preview and daily nightly releases (v0.66.0 on 2026-10-27)

Documented headless mode (-p with json and stream-json output) and MCP server configuration

Three sandbox options: macOS Seatbelt, Docker/Podman containers, and gVisor on Linux

Multiple auth routes: Google login, Gemini API key, Vertex AI

which to pick

pick Codex CLI if

ChatGPT subscribers or OpenAI API users who want an open-source, sandboxed terminal agent.

pick Gemini CLI if

Teams with a Gemini Code Assist licence or a paid Gemini/Vertex API key who want an open-source CLI agent.

skip Codex CLI if

Anyone who needs to run it on non-OpenAI or local models and wants that officially documented.

skip Gemini CLI if

Individuals looking for a free tier or the newest Gemini models; Google steers them to Antigravity CLI.

Gemini CLI vs Codex CLI: what differs

Where they differ

Which fits

More

Codex CLI is stronger at

Gemini CLI is stronger at

which to pick