The Vercel Sandbox Python SDK has reached 1.0, stabilizing its public API and bringing feature parity with the TypeScript SDK. Use it to run AI-generated code, test changes, and analyze datasets in isolated sandboxes from your Python application.
The SDK includes context managers for automatic sandbox cleanup and AnyIO-based async support for asyncio and Trio. For synchronous code, use vercel.sandbox.sync.
Install with `uv add 'vercel-sandbox>=1.0'` and [configure authentication](https://vercel.com/docs/sandbox/python-sdk-reference#authentication).
If you’re upgrading from 0.x, review the [1.0 release notes](https://github.com/vercel/vercel-py/releases/tag/vercel-sandbox-v1.0.0) for breaking changes, including the switch to bytes for command input and output.
Learn more in the [Python SDK documentation](https://vercel.com/docs/sandbox/python-sdk-reference).