OpenAI Codex CLI Setup Guide

Overview

Codex CLI is OpenAI's terminal-based coding agent that reads, writes, and runs code in your project through sandboxed, reviewable patches. Point its custom provider at UnoRouter's base URL and you can drive it with any model from the catalog, not just OpenAI's.

Quick Config

Drop these values into the client. Your key auto-fills when you are signed in.

Base URL: https://api.unorouter.com/v1
API Key: YOUR_API_KEY

Compatibility

Step-by-step setup

1. 1
   Install Codex CLI

   Install the Codex CLI globally with npm.

   bash

   npm install -g @openai/codex

   Sign in to auto-fill your API key

2. 2
   Configure the model provider

   Edit `~/.codex/config.toml` to point Codex at UnoRouter. Set your model id and add a custom provider with UnoRouter's base URL using the responses wire API.

   toml

   # ~/.codex/config.toml
   model = "YOUR_MODEL_ID"
   
   [model_providers.custom]
   base_url = "https://api.unorouter.com/v1"
   wire_api = "responses"

   Sign in to auto-fill your API key

3. 3
   Add your API key

   Write your UnoRouter API key into `~/.codex/auth.json` so Codex authenticates every request.

   json

   // ~/.codex/auth.json
   {
     "OPENAI_API_KEY": "YOUR_API_KEY"
   }

   Sign in to auto-fill your API key

4. 4
   Start Codex

   Run `codex` in your project directory and start coding.

   bash

   codex

   Sign in to auto-fill your API key

$env:OPENAI_BASE_URL="https://api.unorouter.com/v1"
$env:OPENAI_API_KEY="YOUR_API_KEY"

codex

Recommended models

Free models that work well here. Paste any model id into the client.

Gotchas

• !If Codex reports an unsupported endpoint, confirm `wire_api` is set to `responses` and the base URL ends in `/v1`.
• !A 401 means the key in `~/.codex/auth.json` is missing or stale. Paste a fresh key from your UnoRouter dashboard and rerun.