---
title: "Python"
description: "Get started with Browser Use Cloud API using Python"
icon: "python"
mode: "wide"
---

<img
  src="/images/cloud-banner-python.png"
  alt="Browser Use Python"
  width="full"
/>

> The repository is available on [GitHub](https://github.com/browser-use/browser-use-python).

```sh
pip install browser-use-sdk
```

☝️ Get your API Key at [Browser Use Cloud](https://cloud.browser-use.com/billing)

```python
from browser_use_sdk import BrowserUse

client = BrowserUse(api_key="bu_...")

result = client.tasks.run(
    task="Search for the top 10 Hacker News posts and return the title and url."
)

result.done_output
```

> The full API reference can be found in [api.md](https://github.com/browser-use/browser-use-python/blob/main/api.md).

## Async usage

Simply import `AsyncBrowserUse` instead of `BrowserUse` and use `await` with each API call:

```python
import os
import asyncio
from browser_use_sdk import AsyncBrowserUse

client = AsyncBrowserUse(
    api_key=os.environ.get("BROWSER_USE_API_KEY"),  # This is the default and can be omitted
)


async def main() -> None:
    task = await client.tasks.run(
        task="Search for the top 10 Hacker News posts and return the title and url.",
    )
    print(task.done_output)


asyncio.run(main())
```

Functionality between the synchronous and asynchronous clients is otherwise identical.

## Structured Output with Pydantic

Browser Use Python SDK provides first class support for Pydantic models.

```py
class HackerNewsPost(BaseModel):
    title: str
    url: str

class SearchResult(BaseModel):
    posts: List[HackerNewsPost]

async def main() -> None:
    structured_result = await client.tasks.run(
        task="""
        Find top 10 Hacker News articles and return the title and url.
        """,
        structured_output_json=SearchResult,
    )

    if structured_result.parsed_output is not None:
        print("Top HackerNews Posts:")
        for post in structured_result.parsed_output.posts:
            print(f" - {post.title} - {post.url}")

asyncio.run(main())
```

## Streaming Updates with Async Iterators

```py
class HackerNewsPost(BaseModel):
    title: str
    url: str

class SearchResult(BaseModel):
    posts: List[HackerNewsPost]


async def main() -> None:
    structured_task = await client.tasks.create(
        task="""
        Find top 10 Hacker News articles and return the title and url.
        """,
        structured_output_json=SearchResult,
    )

    async for update in client.tasks.stream(structured_task.id, structured_output_json=SearchResult):
        if len(update.steps) > 0:
            last_step = update.steps[-1]
            print(f"{update.status}: {last_step.url} ({last_step.next_goal})")
        else:
            print(f"{update.status}")

        if update.status == "finished":
            if update.parsed_output is None:
                print("No output...")
            else:
                print("Top HackerNews Posts:")
                for post in update.parsed_output.posts:
                    print(f" - {post.title} - {post.url}")

                break

asyncio.run(main())
```

## Advanced

For more advanced usage of the SDK and contributions to the SDK, see [Github repository](https://github.com/browser-use/browser-use-python).