Does OpenAI Codex CLI work with Standard Compute?

Use standardcompute launch codex. The launcher handles the SC connection after browser sign-in.

What base URL do I use for OpenAI Codex CLI?

The SC launcher configures the endpoint for you. Run standardcompute launch codex.

Do I need to change my code or model names?

No. The request and response format is identical to OpenAI's, and "standardcompute" is a single model identifier that routes to the best frontier model for each request — so you never pick or update model names.

← All integrations

SC Launcher · Browser Sign-in

Terminal coding agent

Use Standard Compute with OpenAI Codex CLI

OpenAI’s open-source terminal coding agent with sandboxed local execution. Install the SC launcher, approve your browser sign-in, and start your agent using your monthly compute budget.

Connect Codex CLI →

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Connect and launch

Use the same SC sign-in across supported terminal agents.

1. Install once

Install Codex CLI first if needed: npm install -g @openai/codex. Then install or update the SC launcher below.

curl -fsSL https://standardcompute.com/cli/install.sh | sh

Open a new terminal after installation. Requires Node.js 20 or newer.

2. Launch from your project folder

standardcompute launch codex

Choose an API key and approve the connection in your browser when prompted. Codex CLI opens automatically.

Use this command each time. We’ll remember your selected key.

Check the connection

Ask it to reply “OK”, then check Request Logs for the successful request and model used.

Requests use your Standard Compute budget.

Setup details for Codex CLI

Your sign-in is shared across SC launch commands.

Install Codex CLI, then install the Standard Compute launcher.
Run standardcompute launch codex and approve the browser connection.
Uses SC for this invocation, preserving your normal Codex settings.

Full in-dashboard guide →Codex CLI docs ↗

Get more out of Codex CLI

More tasks to run, more code to test, more work to ship. Standard Compute helps your AI spend cover more of it.

Make your AI spend go further

Get more compute for the work you want to do. Standard Compute compares provider prices and performance automatically, so you spend less time shopping for inference.

More work from your compute

Routine agent steps can use efficient models, while demanding tasks get frontier intelligence. Smart routing puts those options to work together to stretch your compute.

Keep your agent and your projects

Connect Standard Compute using the setup below. Your coding workflow stays familiar, with one subscription and more capacity available as your agent use grows.