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

# Cursor

> Add a Valkyrie model to Cursor as a custom OpenAI-compatible model.

Cursor lets you add custom models that speak the OpenAI API. Because Valkyrie is
[OpenAI-compatible](/connect/openai-compatible), you can use a Valkyrie deployment as
a model in Cursor.

## Configure the model

<Steps>
  <Step title="Open Cursor settings">
    Go to **Cursor Settings → Models**.
  </Step>

  <Step title="Set the OpenAI base URL">
    Enable a custom OpenAI base URL and set it to your deployment's endpoint:

    ```
    https://valkyrie-back.azumo.com/{deployment_slug}/v1
    ```

    Or, with an [alias](/guides/aliases):

    ```
    https://valkyrie-back.azumo.com/{account_slug}/{alias}/v1
    ```
  </Step>

  <Step title="Set the API key">
    Use your Valkyrie API key as the OpenAI API key.
  </Step>

  <Step title="Add the model name">
    Add a model whose name matches your deployment slug (or alias), and select it.
  </Step>
</Steps>

<Note>
  Some Cursor features assume a specific frontier model's capabilities. A
  self-hosted open model may not support every feature; use it where its size and
  capabilities fit.
</Note>

<Tip>
  Point Cursor at an [alias](/guides/aliases) so you can swap the underlying
  deployment without reconfiguring the editor.
</Tip>