For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

Deploy Codex CLI, OpenAI’s terminal-based coding agent, pre-configured to use DigitalOcean Gradient AI for inference. Use natural language to write, debug, and refactor code. Code and context stay on your server.

What is Codex CLI?

Codex CLI brings OpenAI’s coding agent into your terminal. It can read, edit, and run code in your project directory. This droplet is pre-configured with DigitalOcean Gradient AI, giving you access to GPT, Claude, DeepSeek, Llama, Kimi, and more using a single Gradient model access key.

• Terminal-first – Native TUI in your shell, no web interface required
• DigitalOcean Gradient AI – Pre-configured inference via Gradient
• Subagents – Parallelize complex tasks with subagents
• Sandboxed execution – Controlled filesystem and network access
• MCP support – Connect third-party tools via Model Context Protocol
• Scriptable – Automate workflows with codex exec

Key Features

• Natural language coding assistance in the terminal
• Pre-configured with DigitalOcean Gradient AI
• Works with existing projects—navigate, edit, and run code
• No IDE required—pure terminal workflow
• Optional ChatGPT subscription auth via codex login

System Requirements

Codex CLI is lightweight; most compute happens at the inference provider.

Included System Components

• Ubuntu 24.04 LTS – Base operating system
• Codex CLI – OpenAI terminal coding agent (version 0.133.0)
• DigitalOcean Gradient AI – Pre-configured inference provider
• Git – Version control
• UFW Firewall – SSH only (rate-limited)

Software Included

This Marketplace listing does not include a detailed software list.

Creating an App using the Control Panel

Click the Deploy to DigitalOcean button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

Creating an App using the API

In addition to creating a Droplet from the Codex CLI 1-Click App using the control panel, you can also use the DigitalOcean API. As an example, to create a 4GB Codex CLI Droplet in the SFO2 region, you can use the following curl command. You need to either save your API access token to an environment variable or substitute it in the command below.

curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image":"codexcli"}' \
        "https://api.digitalocean.com/v2/droplets"

Getting Started After Deploying Codex CLI

Getting Started

1. Deploy the Droplet

1. Select this 1-Click App from the DigitalOcean Marketplace
2. Choose a Droplet size (1 GB RAM minimum)
3. Add your SSH key for secure access
4. Create the Droplet

2. SSH In

ssh root@your-droplet-ip

3. Configure Your Gradient Key

Choose one of these options:

Option A — Droplet environment variables (recommended for automation)

Set at droplet create time:

• GRADIENT_KEY — your Gradient model access key (required)
• GRADIENT_MODEL — optional model id (default: openai-gpt-5.5)

Codex CLI is configured automatically on first boot; no wizard required.

Option B — Edit /opt/codex-cli.env

Set GRADIENT_KEY and optionally GRADIENT_MODEL, then reboot or run:

/opt/apply-gradient-from-env.sh

Option C — First-login setup wizard

On first SSH login, the wizard prompts for your key if it was not pre-configured.

To create a key:

1. Go to https://cloud.digitalocean.com/gen-ai/model-access-keys
2. Click Create Model Access Key
3. Copy the new key and use it with one of the options above

4. Run Codex CLI

cd /path/to/your/project
codex

The default model is GPT-5.5 (openai-gpt-5.5). Change it with codex -m "openai-gpt-5.1-codex-max" or the /model command inside Codex.

Managing Codex CLI

Helper Scripts

Configuration

• Codex config: /root/.codex/config.toml
• API key: /root/.codex/env (MODEL_ACCESS_KEY)
• Droplet env template: /opt/codex-cli.env (GRADIENT_KEY, GRADIENT_MODEL)
• Getting started guide: cat /root/codex_cli_info.txt

Available Models

Use model IDs from the Gradient Model Catalog with codex -m "<model-id>" or edit model in /root/.codex/config.toml.

List all available models:

curl -s -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
  https://inference.do-ai.run/v1/models | jq '.data[].id'

Using ChatGPT Subscription Auth

If you prefer ChatGPT Plus/Pro/Business subscription auth instead of Gradient:

1. Skip the setup wizard (press Enter)
2. Run codex login and follow the OAuth flow

Updating

To update Codex CLI to the latest version:

/opt/update-codex-cli.sh

Troubleshooting

Codex not found in PATH

Run directly:

/usr/local/bin/codex

Auth error or 401

Re-run the setup wizard:

/opt/setup-codex-cli.sh

Or verify your key is exported:

echo $MODEL_ACCESS_KEY
source /root/.codex/env

Model not found or 404

Retrieve current model IDs from the Gradient API and update model in /root/.codex/config.toml.

Additional Resources

• Documentation: https://developers.openai.com/codex/cli
• Config reference: https://developers.openai.com/codex/config-basic
• Gradient + Codex guide: https://docs.digitalocean.com/products/inference/how-to/use-with-coding-agents/
• GitHub: https://github.com/openai/codex

Support

For Codex CLI-specific issues:

• Documentation: https://developers.openai.com/codex/cli
• GitHub: https://github.com/openai/codex

For DigitalOcean Droplet issues:

• DigitalOcean Support: https://www.digitalocean.com/support
• Community Tutorials: https://www.digitalocean.com/community

Note: This 1-Click installs Codex CLI from official GitHub releases and pre-configures DigitalOcean Gradient AI as the inference provider. SSH is the only exposed port; there is no web interface.