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

# Delete custom model

Delete a specific custom model from your organization.

<Note>
  **Important**: This action is permanent and cannot be undone. Only custom models (`source: "db"`) can be deleted. Hardcoded models synced from code cannot be deleted as they will be recreated on the next deployment.
</Note>

## Path parameters

<ParamField path="model_name" type="string" required>
  The model's unique name to delete.

  <Accordion title="Example">
    ```
    my-custom-gpt-4
    ```
  </Accordion>
</ParamField>

## Response

Returns no content on successful deletion.

<ResponseExample>
  ```text 204 No Content theme={"system"}
  ```

  ```json 403 Forbidden theme={"system"}
  {
    "detail": "Cannot delete hardcoded models. They are synced from code and will be recreated on next deployment. Only database-only models can be deleted."
  }
  ```

  ```json 404 Not Found theme={"system"}
  {
    "detail": "Not found."
  }
  ```

  ```json 401 Unauthorized theme={"system"}
  {
    "detail": "Authentication credentials were not provided."
  }
  ```
</ResponseExample>

<RequestExample>
  ```python Python theme={"system"}
  import requests

  model_name = "my-custom-gpt-4"
  url = f"https://api.keywordsai.co/api/models/{model_name}/"
  headers = {
      "Authorization": "Bearer YOUR_API_KEY"
  }

  response = requests.delete(url, headers=headers)
  print(f"Status code: {response.status_code}")
  ```

  ```typescript TypeScript theme={"system"}
  const modelName = 'my-custom-gpt-4';
  const url = `https://api.keywordsai.co/api/models/${modelName}/`;
  const headers = {
      'Authorization': 'Bearer YOUR_API_KEY'
  };

  const response = await fetch(url, {
      method: 'DELETE',
      headers: headers
  });

  console.log(`Status code: ${response.status}`);
  ```

  ```bash cURL theme={"system"}
  curl -X DELETE "https://api.keywordsai.co/api/models/my-custom-gpt-4/" \
    -H "Authorization: Bearer YOUR_API_KEY"
  ```
</RequestExample>