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

# Get Pull Status

> Retrieves the current download progress for a model being pulled

## Query Parameters

<ParamField query="modelName" type="string" required>
  Name of the model being pulled
</ParamField>

<ParamField query="baseUrl" type="string">
  Optional Ollama server URL (defaults to [http://localhost:11434](http://localhost:11434))
</ParamField>

## Response

<ResponseField name="success" type="boolean">
  Indicates if the status was retrieved successfully
</ResponseField>

<ResponseField name="status" type="object">
  Pull status information

  <Expandable title="status properties">
    <ResponseField name="status" type="string">
      Current pull status

      * `pulling` - Downloading model
      * `extracting` - Extracting model files
      * `complete` - Pull completed
      * `error` - Pull failed
    </ResponseField>

    <ResponseField name="progress" type="number">
      Download progress percentage (0-100)
    </ResponseField>

    <ResponseField name="digest" type="string">
      Model digest hash
    </ResponseField>

    <ResponseField name="total" type="number">
      Total bytes to download
    </ResponseField>

    <ResponseField name="completed" type="number">
      Bytes downloaded so far
    </ResponseField>
  </Expandable>
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl --request GET \
    --url 'http://localhost:3000/api/v1/ollama/pull-status?modelName=llama2' \
    --header 'Authorization: Bearer <token>'
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch(
    'http://localhost:3000/api/v1/ollama/pull-status?modelName=llama2',
    {
      method: 'GET',
      headers: {
        'Authorization': 'Bearer <token>'
      }
    }
  );

  const data = await response.json();
  ```

  ```python Python theme={null}
  import requests

  url = "http://localhost:3000/api/v1/ollama/pull-status"
  headers = {"Authorization": "Bearer <token>"}
  params = {"modelName": "llama2"}

  response = requests.get(url, headers=headers, params=params)
  data = response.json()
  ```
</RequestExample>

<ResponseExample>
  ```json 200 - Pulling theme={null}
  {
    "success": true,
    "status": {
      "status": "pulling",
      "progress": 45.7,
      "digest": "sha256:78e26419b446...",
      "total": 3826793677,
      "completed": 1748742390
    }
  }
  ```

  ```json 200 - Complete theme={null}
  {
    "success": true,
    "status": {
      "status": "complete",
      "progress": 100,
      "digest": "sha256:78e26419b446...",
      "total": 3826793677,
      "completed": 3826793677
    }
  }
  ```

  ```json 401 - Unauthorized theme={null}
  {
    "success": false,
    "error": "Unauthorized"
  }
  ```

  ```json 500 - Server Error theme={null}
  {
    "success": false,
    "error": "Failed to get pull status"
  }
  ```
</ResponseExample>

## Notes

* Poll this endpoint periodically to monitor download progress
* The `progress` field is a percentage between 0 and 100
* Status changes from `pulling` → `extracting` → `complete`
* Once status is `complete`, the model is ready to use

## Polling Example

```javascript theme={null}
async function monitorPull(modelName) {
  const interval = setInterval(async () => {
    const response = await fetch(
      `http://localhost:3000/api/v1/ollama/pull-status?modelName=${modelName}`,
      { headers: { 'Authorization': 'Bearer <token>' } }
    );
    const data = await response.json();
    
    console.log(`Progress: ${data.status.progress}%`);
    
    if (data.status.status === 'complete') {
      clearInterval(interval);
      console.log('Model pull completed!');
    }
  }, 2000); // Poll every 2 seconds
}
```