> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Daytona

> Run code evaluators in Daytona's managed development sandboxes.

<div style={{ display: 'flex', alignItems: 'center', gap: '1.5rem', marginTop: '1.5rem', marginBottom: '1.5rem' }}>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/svgs/daytona.svg" alt="Daytona" className="invert-on-dark" style={{ height: '112px', flexShrink: 0 }} />

  <div>
    [**Daytona**](https://www.daytona.io/) runs each evaluation in a managed development sandbox on its own cloud. Sandboxes start from snapshots, which keeps startup fast, and Daytona supports both Python and TypeScript evaluators.
  </div>
</div>

## Setup

1. **Create a Daytona account** at [daytona.io](https://www.daytona.io/) if you don't already have one.
2. **Generate an API key** in the Daytona dashboard.
3. **Add the key to Phoenix.** Open [Settings → Sandboxes](/docs/phoenix/settings/sandboxes), find the **Daytona** row, click the gear icon, and paste the key as `DAYTONA_API_KEY`. You can also set it as an environment variable on the Phoenix server instead.
4. **Create a configuration.** In **Sandbox Configurations**, click **New Sandbox**, pick **Daytona**, choose the language (Python or TypeScript), set the timeout and any environment variables or dependencies, and save.