🎯 Quick Navigation

Codex is a next-generation AI coding assistant built on the GPT-5 architecture, offering developers powerful code generation and optimization capabilities.

Deployment path: Configure the system environment ➜ Install the CLI tool ➜ Integrate the API ➜ Prepare the development environment

🚀 Quick Setup with CC-Switch (Recommended)

⚠️ Prerequisite

Before configuring Codex with CC-Switch, make sure you have installed the Codex tool globally with npm:

npm install -g @openai/codex@latest

Verify the installation: codex --version

We recommend the CC-Switch quick configuration tool for simple graphical setup without command-line work.

Configuration Steps

1. Launch CC-Switch and switch to the Codex tab

The CC-Switch application with several tabs at the top. A red arrow high…

1. Open the CC-Switch application
2. Click the “Codex” tab at the top
3. Click the orange “+” button in the upper-right corner to add a configuration
4. Enter the Codex provider configuration
5. Provider name: Enter a custom name, such as “gpt-agent”
6. Base URL: Enter https://api.llm-token.cn/v1
7. API Key: Paste your API key
8. Model: Select gpt-5.4 (the latest model when this guide was written was 5.4)
9. Other settings: Adjust reasoning effort, network access, and other parameters as needed
10. Click “Save”

The Add Configuration screen in CC-Switch. Tabs for “Codex Provider” and…

The Edit Provider Configuration screen in CC-Switch. The provider name i…

1. Enable and use the configuration
2. Find the configuration you just created in the configuration list
3. Click “In Use” on the right side of the configuration
4. The configuration will be marked “In Use” with a green label
5. Restart Codex to apply the new configuration
6. Switch quickly from the system tray

CC-Switch lets you switch Codex configurations from the system tray:

• Right-click the CC-Switch icon in the system tray
• Select the Codex category from the menu
• Select the configuration you want to use
• The configuration takes effect immediately without opening the main window

⌨️ Manual Command-Line Setup

If you do not use CC-Switch, follow the steps below to configure Codex manually.

🖥️ Windows

Step One: Install the Codex Command-Line Tool

Launch Command Prompt or PowerShell as an administrator, then run:

npm install -g @openai/codex@latestcodex --version

Create the configuration file: config.toml

model_provider = "gpt-agent"model = "gpt-5.4"model_reasoning_effort = "xhigh"disable_response_storage = trueapproval_policy = "on-request"sandbox_mode = "danger-full-access"model_supports_reasoning_summaries = true[model_providers.gpt-agent]name = "ikun"base_url = "https://api.llm-token.cn/v1"wire_api = "responses"requires_openai_auth = true

Create the authentication file: auth.json

{  "OPENAI_API_KEY": "此处粘贴您的 CodeX 专用令牌"}

Step Three: Initialize the Workspace

mkdir my-codex-projectcd my-codex-projectcodex

🍏 macOS

Install the Codex Tool

npm install -g @openai/codex@latestcodex --version

Integrate the API Service

Create the configuration directory:

mkdir -p ~/.codexcd ~/.codex

Create the config.toml configuration:

cat > config.toml << 'EOF'model_provider = "gpt-agent"model = "gpt-5.4"model_reasoning_effort = "xhigh"disable_response_storage = trueapproval_policy = "on-request"sandbox_mode = "danger-full-access"model_supports_reasoning_summaries = true[model_providers.gpt-agent]name = "ikun"base_url = "https://api.llm-token.cn/v1"wire_api = "responses"requires_openai_auth = trueEOF

Create the auth.json authentication configuration:

cat > auth.json << 'EOF'{  "OPENAI_API_KEY": "此处粘贴您的 CodeX 专用令牌"}EOF

Initialize the Workspace

mkdir my-codex-projectcd my-codex-projectcodex

🐧 Linux

Install the Codex Tool

sudo npm install -g @openai/codex@latestcodex --version

1 2

Integrate the API Service

Create the configuration directory:

mkdir -p ~/.codexcd ~/.codex

Create the config.toml configuration:

cat > config.toml << 'EOF'model_provider = "gpt-agent"model = "gpt-5.4"model_reasoning_effort = "xhigh"disable_response_storage = trueapproval_policy = "on-request"sandbox_mode = "danger-full-access"model_supports_reasoning_summaries = true[model_providers.gpt-agent]name = "ikun"base_url = "https://api.llm-token.cn/v1"wire_api = "responses"requires_openai_auth = trueEOF

Create the auth.json authentication configuration:

cat > auth.json << 'EOF'{  "OPENAI_API_KEY": "此处粘贴您的 CodeX 专用令牌"}EOF

Initialize the Workspace

mkdir my-codex-projectcd my-codex-projectcodex

Where Are the Configuration Files Stored?

• Windows: %USERPROFILE%\.codex\
• macOS/Linux: ~/.codex/

Configured but Unable to Chat?

Try the steps below. If the issue persists, contact support.

The CC Switch interface with the “Guizhou Cloud Computing” row highlight…

The CC Switch Settings screen. Red arrows point to the “Proxy” tab at th…

Proxy-related settings in the Codex deployment guide. The General, Proxy…