Use OpenAI Codex with Pluely

Connect the OpenAI Codex CLI and the Pluely overlay answers with GPT-5.1-class models on your own ChatGPT plan, locally.

1. Install and sign in

Install Codex (for example npm install -g @openai/codex) and run codex once in your terminal to sign in with your ChatGPT account. If it answers there, Pluely can use it.

2. Connect it in Pluely

1. Open the dashboard → Dev space → Connect your CLI.
2. Pluely detects Codex automatically. Click Connect.
3. It appears at the top of the overlay's model picker as Your CLI.

Pluely runs Codex non-interactively and handles its git-repository check for you — no setup flags needed.

3. Pick a model

The Model panel sits right under the connected row:

• Default (CLI decides) — your Codex default. Always works.
• GPT-5.1 Codex, GPT-5.1, GPT-5 Codex Mini — one click each.
• Custom model id — any model your plan includes.

Images work

Codex takes attached screenshots and images directly (Pluely passes them through its image input), so visual questions work end to end.

Thinking models work

Reasoning output is filtered automatically — only the final answer reaches you.

Troubleshooting

• "Your CLI couldn't answer" — run codex exec "hello" in a terminal; if it fails there (sign-in, plan), fix it there first.

Related

• Connect a local CLI (all options)
• Choosing your AI