# Vercel Sandbox Python SDK 1.0 is now available

> Source: <https://vercel.com/changelog/vercel-sandbox-python-sdk-1-0-is-now-available>
> Published: 2026-11-16 00:00:00+00:00

**Key takeaway:** The 1.0.0 release stabilizes the public API and changes command input and output to bytes, so 0.x users must update their code when upgrading to vercel-sandbox>=1.0.

The [Vercel Sandbox Python SDK](https://pypi.org/project/vercel-sandbox/1.0.0/) 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](https://github.com/agronholm/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).
