AI Token Hub

CodeX Deployment Guide

๐Ÿ“‹ Prerequisites

Please complete the Node.js environment setup first and make sure Node.js 18+ is installed correctly.

๐ŸŽฏ Quick Navigation

CodeX is a next-generation intelligent coding assistant built on the GPT-5 architecture, providing developers with outstanding code generation and optimization capabilities.

Deployment path: System environment setup โžœ CLI tool installation โžœ API integration โžœ Development environment ready

๐Ÿš€ Quick Setup with CC-Switch (Recommended)

โš ๏ธ Prerequisite

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

npm install -g @openai/codex@latest

Verify the installation:

codex --version

We recommend using the CC-Switch quick configuration tool for graphical setup. It is simple, fast, and does not require manual command-line operations.

Configuration Steps

  1. Launch CC-Switch and switch to the Codex tab.
CC-Switch Codex tab
  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 new configuration.
  4. Fill in the CodeX provider configuration.
  5. Provider Name: custom name, such as gpt-agent
  6. Base URL: https://gpt-agent.cc/v1
  7. API Key: paste the dedicated CodeX token you received from support (starts with sk-)
  8. Model: choose gpt-5.4 (latest model at the time this document was written)
  9. Other settings: adjust reasoning level, network access, and other parameters as needed
  10. Click the Save button.
CC-Switch provider configuration

๐Ÿ’ก Tips

  • CC-Switch will automatically create ~/.codex/config.toml and auth.json.
  • You can add multiple provider configurations and switch between them at any time.
  • After switching configurations, close and restart CodeX for the new configuration to take effect.
  1. Enable the configuration and start using it.
  2. Find the configuration you just created in the configuration list.
  3. Click the Currently in Use button on the right side of that configuration.
  4. The configuration will be marked as Currently in Use (green label).
  5. Restart CodeX and the new configuration will take effect.
  6. Quick switching from the system tray.

CC-Switch also supports quick CodeX switching from the system tray:

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

โš ๏ธ Notes

  • Be sure to obtain a dedicated key for the codex token group from support.
  • CodeX tokens are not interchangeable with Claude Code tokens.
  • After switching configurations, you need to restart CodeX for the change to take effect.
  • You can test the API endpoint speed directly inside CC-Switch.

โŒจ๏ธ Manual Command-Line Configuration

If you do not use CC-Switch, you can manually configure CodeX by following the steps below.

๐Ÿ–ฅ๏ธ Windows Platform

Step 1: Install the CodeX CLI Tool

Run Command Prompt or PowerShell as Administrator and execute:

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

Step 2: Write the configuration file: config.toml

model_provider = "gpt-agent"
model = "gpt-5.4"
model_reasoning_effort = "xhigh"
disable_response_storage = true
approval_policy = "on-request"
sandbox_mode = "danger-full-access"
model_supports_reasoning_summaries = true

[model_providers.gpt-agent]
name = "ikun"
base_url = "https://api.ikuncode.cc/v1"
wire_api = "responses"
requires_openai_auth = true

Step 3: Write the authentication file: auth.json

{
  "OPENAI_API_KEY": "Paste your dedicated CodeX token here"
}

Step 4: Initialize the workspace

mkdir my-codex-project
cd my-codex-project
codex

๐Ÿ macOS Platform

Install the CodeX Tool

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

Integrate the API Service

Create the configuration directory:

mkdir -p ~/.codex
cd ~/.codex

Write the config.toml configuration:

cat > config.toml << 'EOF'
model_provider = "gpt-agent"
model = "gpt-5.4"
model_reasoning_effort = "xhigh"
disable_response_storage = true
approval_policy = "on-request"
sandbox_mode = "danger-full-access"
model_supports_reasoning_summaries = true

[model_providers.gpt-agent]
name = "ikun"
base_url = "https://api.ikuncode.cc/v1"
wire_api = "responses"
requires_openai_auth = true
EOF

Write the auth.json authentication configuration:

cat > auth.json << 'EOF'
{
  "OPENAI_API_KEY": "Paste your dedicated CodeX token here"
}
EOF

Initialize the workspace

mkdir my-codex-project
cd my-codex-project
codex

๐Ÿง Linux Platform

Install the CodeX Tool

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

Integrate the API Service

Create the configuration directory:

mkdir -p ~/.codex
cd ~/.codex

Write the config.toml configuration:

cat > config.toml << 'EOF'
model_provider = "gpt-agent"
model = "gpt-5.4"
model_reasoning_effort = "xhigh"
disable_response_storage = true
approval_policy = "on-request"
sandbox_mode = "danger-full-access"
model_supports_reasoning_summaries = true

[model_providers.gpt-agent]
name = "ikun"
base_url = "https://api.ikuncode.cc/v1"
wire_api = "responses"
requires_openai_auth = true
EOF

Write the auth.json authentication configuration:

cat > auth.json << 'EOF'
{
  "OPENAI_API_KEY": "Paste your dedicated CodeX token here"
}
EOF

Initialize the workspace

mkdir my-codex-project
cd my-codex-project
codex

Configuration File Location

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