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

# Cursor

> Use Edgee with Cursor to access any model through a single API key, with cost tracking and token compression.

Edgee's OpenAI-compatible API works with Cursor, letting you route AI requests through Edgee to gain observability, cut costs, and access any provider's models from one place.

## Edgee CLI setup (recommended)

The fastest way to route Cursor through Edgee is the CLI. It authenticates, starts a local Edgee relay, and opens Cursor routed through it, no manual API key or base URL to configure.

<Steps>
  <Step title="Install the Edgee CLI">
    <Tabs>
      <Tab title="macOS / Linux">
        ```bash theme={"dark"}
        curl -fsSL https://edgee.ai/install.sh | bash
        ```
      </Tab>

      <Tab title="Homebrew (macOS)">
        ```bash theme={"dark"}
        brew install edgee-ai/tap/edgee
        ```
      </Tab>

      <Tab title="Windows (PowerShell)">
        ```powershell theme={"dark"}
        irm https://edgee.ai/install.ps1 | iex
        ```
      </Tab>
    </Tabs>
  </Step>

  <Step title="Launch Cursor through Edgee">
    ```bash theme={"dark"}
    edgee launch cursor
    ```

    The CLI authenticates, starts a local Edgee relay, and opens Cursor routed through it. Token compression is enabled automatically.
  </Step>
</Steps>

Prefer starting Cursor from your app menu? Install a desktop wrapper once with `edgee alias cursor`, then open **Cursor (Edgee)** like any other app. See the [Edgee CLI](/docs/features/cli) page for details.

## Manual setup (advanced)

You can also point Cursor at Edgee directly through its settings.

<Steps>
  <Step title="Open Cursor Settings">
    In Cursor, go to **Settings → Cursor Settings → Models**.
  </Step>

  <Step title="Configure your API key">
    Scroll down to the **API Keys** section and do the following:

    1. Enable **OpenAI API Key**
    2. Paste in your **Edgee API key**
    3. Enable **Override OpenAI Base URL**
    4. Set the base URL to:

    ```
    https://edgee.io/v1
    ```

    <Note>
      You can find your Edgee API key in the [Edgee Console](https://www.edgee.ai).
    </Note>
  </Step>

  <Step title="Add a model">
    Scroll up to **Add or search model** and enter any model from the [Edgee model list](/docs/api-reference/models).

    Click **Add**, then toggle it on.

    <Warning>
      You must use model IDs from the Edgee model list. Cursor lets you type any string, but only models supported by Edgee will work.
    </Warning>
  </Step>
</Steps>

You're set. Cursor will now route requests through Edgee.

<Note>
  Token compression is only available when routing through Edgee. You can use your own provider keys via [BYOK](/docs/features/byok) — compression still applies as long as requests go through Edgee.
</Note>

## Benefits

<CardGroup cols={2}>
  <Card title="Any model, one key" icon="key">
    Access models from OpenAI, Anthropic, Mistral, and more using a single Edgee API key.
  </Card>

  <Card title="Cost reduction" icon="dollar-sign">
    Edgee's token compression reduces costs by up to 50% on supported models with no change to output quality.
  </Card>

  <Card title="Observability" icon="chart-line">
    Every request is logged in the Edgee Console with token counts, latency, and cost breakdowns.
  </Card>

  <Card title="Reliability" icon="shield-check">
    Automatic retry and fallback across providers keeps your Cursor sessions running even when a provider has issues.
  </Card>
</CardGroup>

## Next Steps

* Browse the [model list](/docs/api-reference/models) to see all available models
* Set up [observability](/docs/features/observability) to monitor usage and costs
* Explore [retry and fallback](/docs/features/retry-and-fallback) for resilient routing