> ## Documentation Index
> Fetch the complete documentation index at: https://docs.livepeer.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Python

> Learn how to run your first AI inference job using the Livepeer AI Python SDK.

<Steps>
  <Step title="Prerequisites">
    To get the most out of this guide, you’ll need to:

    * [Choose an AI Gateway](/ai/builders/gateways)
    * **Optional**: Get an API key (required for some gateways).
  </Step>

  <Step title="Install the SDK">
    Get the Livepeer AI Python SDK.

    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    pip install livepeer-ai
    ```
  </Step>

  <Step title="Initialize the SDK">
    The first step is to initialize the SDK (with your API key if required).

    ```python theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    from livepeer_ai import Livepeer

    s = Livepeer(
        http_bearer="<YOUR_BEARER_TOKEN_HERE>",
    )
    ```
  </Step>

  <Step title="Use the SDK">
    Now that you have the SDK installed and initialized, you can use it to request one of the [available AI services](/ai/pipelines/overview).

    ```python theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    from livepeer_ai import Livepeer

    s = Livepeer(
        http_bearer="<YOUR_BEARER_TOKEN_HERE>",
    )

    res = s.generate.text_to_image(request={
        "prompt": "<value>",
    })

    if res.image_response is not None:
        # handle response
        pass
    ```
  </Step>

  <Step title="Try it yourself">
    <Card title="Python Examples" href="https://github.com/livepeer/livepeer-ai-python/tree/main/docs/sdks/generate#generate" icon="arrow-up-right-from-square">
      See the examples on GitHub.
    </Card>
  </Step>
</Steps>

## Next steps

Checkout Livepeer AI [API Reference](/ai/api-reference) to learn more about the
Livepeer AI API and the Python SDK.