Codex CLI

Use OpenAI’s Codex CLI with NanoGPT to access GPT-5.2, Claude Opus 4.5, Gemini 3 Flash Preview, and 400+ AI models through a single API key.

Get started with NanoGPT for pay-as-you-go pricing with no monthly fees. Add credits and start coding immediately.

NanoGPT provides an OpenAI API-compatible endpoint that works seamlessly with Codex CLI. This allows you to:

Use Codex CLI with your NanoGPT credits
Access OpenAI models (GPT-5.2 and more) without a separate OpenAI account
Route to 400+ other models including Claude Opus 4.5, Gemini 3 Flash Preview, and GLM 4.7

Step 1: Install Codex CLI

Recommended Installation Method
Cursor Guided Installation Method

Prerequisites: Node.js 22 or newer

# Install Codex CLI
npm install -g @openai/codex

# Navigate to your project
cd your-awesome-project

# Start Codex
codex

If you are not familiar with npm but have Cursor, you can enter the command in Cursor, and Cursor will guide you through the installation.

https://developers.openai.com/codex/cli/ Help me install Codex CLI

Note: If you encounter permission issues during installation, try using sudo (macOS/Linux) or running the command prompt as an administrator (Windows) to re-execute the installation command.

Step 2: Configure NanoGPT

Get API Key

Go to NanoGPT API
Create an account or log in
Copy your API key

Configure Codex

Set up Codex using one of the following methods:

One-Click Setup (Mac/Linux)
Manual Configuration (All Platforms)
Environment Variables Only (Quick)

Run this command in your terminal:

curl -O "https://nano-gpt.com/install/codex_nanogpt.sh" && bash ./codex_nanogpt.sh

The script will:

Prompt for your API key
Create ~/.codex/config.toml with NanoGPT configuration
Add NANOGPT_API_KEY to your shell profile

The installer now supports browser-based login. When the script starts, choose:

Browser login (recommended) - it will open a verification URL, wait for approval, and then save your key in ~/.codex/config.toml.
Paste API key - manual fallback if you prefer.

If a browser does not open automatically, copy the printed URL into your browser and approve the request.For more details on the browser login flow, see CLI login.

Step 1: Create ~/.codex/config.toml:

model_provider = "nanogpt"
model = "openai/gpt-5.2"

[model_providers.nanogpt]
name = "NanoGPT"
base_url = "https://nano-gpt.com/api/v1"
env_key = "NANOGPT_API_KEY"
wire_api = "chat"

Step 2: Set your API key as an environment variable:macOS/Linux (add to ~/.zshrc or ~/.bashrc):

export NANOGPT_API_KEY="your_nanogpt_api_key"

Windows Cmd:

setx NANOGPT_API_KEY your_nanogpt_api_key

Windows PowerShell:

[System.Environment]::SetEnvironmentVariable('NANOGPT_API_KEY', 'your_nanogpt_api_key', 'User')

Replace your_nanogpt_api_key with your actual API key. Open a new terminal for changes to take effect.

If you just want to override the default OpenAI endpoint without a config file:

export OPENAI_BASE_URL="https://nano-gpt.com/api/v1"
export OPENAI_API_KEY="your_nanogpt_api_key"

This method works but does not persist across terminal sessions unless added to your shell profile.

Step 3: Start Using Codex

Once configured, start Codex in your terminal:

codex

Or specify a model directly:

codex --model openai/gpt-5.2

FAQ

What Models Can I Use?

NanoGPT supports 400+ models. Popular choices for Codex:

Use Case	Recommended Model	Config
Best overall	`openai/gpt-5.2`	`model = "openai/gpt-5.2"`
Best Claude	`anthropic/claude-opus-4.5`	`model = "anthropic/claude-opus-4.5"`
Fast/cheap	`google/gemini-3-flash-preview`	`model = "google/gemini-3-flash-preview"`
Long context	`google/gemini-3-pro-preview`	`model = "google/gemini-3-pro-preview"`
Open model	`zai-org/glm-4.7`	`model = "zai-org/glm-4.7"`

View all available models at nano-gpt.com/models/text.

How Do I Change Models?

Option 1: Edit ~/.codex/config.toml:

model = "openai/gpt-5.2"

Option 2: Use CLI flag:

codex --model openai/gpt-5.2

Configuration Not Working?

Check your API key: Ensure NANOGPT_API_KEY is set
```
echo $NANOGPT_API_KEY
```
Verify config file: Check ~/.codex/config.toml exists and has valid TOML syntax
Open a new terminal: Environment variable changes require a new shell session
Reset configuration: Delete ~/.codex/config.toml and run the setup script again

How Is This Different From Using OpenAI Directly?

Feature	OpenAI Direct	NanoGPT
Pricing	Monthly subscription or API credits	Pay-as-you-go, no minimums
Models	OpenAI only	OpenAI + Claude + 400 other models
Billing	Separate OpenAI account	Single NanoGPT balance
Rate limits	OpenAI limits	NanoGPT limits

Can I Use Both Claude Code and Codex?

Yes. Both can be configured to use NanoGPT simultaneously:

Claude Code: Uses ~/.claude/settings.json with Anthropic API format
Codex CLI: Uses ~/.codex/config.toml with OpenAI API format

Both tools share the same NanoGPT credit balance.

Need Help?

Check your balance at nano-gpt.com/balance
View API usage at nano-gpt.com/usage
Create or manage API keys at nano-gpt.com/api
Contact support via the chat widget on nano-gpt.com

Get Started

Endpoint Examples

API Reference

Miscellaneous

Integrations

Codex CLI

Codex CLI

Step 1: Install Codex CLI

Step 2: Configure NanoGPT

Step 3: Start Using Codex

FAQ

What Models Can I Use?

How Do I Change Models?

Configuration Not Working?

How Is This Different From Using OpenAI Directly?

Can I Use Both Claude Code and Codex?

Need Help?

Get Started

Endpoint Examples

API Reference

Miscellaneous

Integrations

​Codex CLI

​Step 1: Install Codex CLI

​Step 2: Configure NanoGPT

​Step 3: Start Using Codex

​FAQ

​What Models Can I Use?

​How Do I Change Models?

​Configuration Not Working?

​How Is This Different From Using OpenAI Directly?

​Can I Use Both Claude Code and Codex?

​Need Help?

Codex CLI

Step 1: Install Codex CLI

Step 2: Configure NanoGPT

Step 3: Start Using Codex

FAQ

What Models Can I Use?

How Do I Change Models?

Configuration Not Working?

How Is This Different From Using OpenAI Directly?

Can I Use Both Claude Code and Codex?

Need Help?