> ## Documentation Index
> Fetch the complete documentation index at: https://statsig-4b2ff144-serverless-cloudflare.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Model Client

In order to invoke Azure AI methods, you'll need to instantiate a Model Client.  You have two ways of instantiating a Model Client

## Option 1: (Recommended) Using Statsig Dynamic Config

Using Statsig's Dynamic Config is a clean way to configure your AI Client, which provides maximum flexibility in being able to adjust the AI invocation parameters and even the endpoint without needing to modify code.

In your Statsig console, create a new **Dynamic Config** by going to: [https://console.statsig.com/dynamic\_configs](https://console.statsig.com/dynamic_configs), and clicking on **Create** button.

<Frame>
  <img src="https://github.com/user-attachments/assets/29357d6f-c356-461c-afc7-e1673ba97f92" alt="Dynamic Config creation interface" />
</Frame>

Once created, you can fill in the properties of this deployment like this:

<Frame>
  <img src="https://github.com/user-attachments/assets/e4d20573-9d1f-4d62-af11-408435d02f90" alt="Dynamic Config properties configuration screen" />
</Frame>

The JSON of this looks like this:

```
{
  endpoint: "https://FILL_IN_YOUR_ENDPOINT",
  key: "FILL_IN_YOUR_KEY",
  completion_defaults: {
    frequency_penalty: 0,
    presence_penalty: 0,
    temperature: 1,
    top_p: 1,
    max_tokens: 0,
    stop: [],
    seed: 0,
  },
}
```

Once this is done, you can instantiate your Model Client directly by using the **id** of this Dynamic Config like this:

<Tabs>
  <Tab title="NodeJS">
    ```js theme={null}
    const client = AzureAI.getModelClient("<dynamic_config_id>");
    ```
  </Tab>

  <Tab title="Python">
    ```python theme={null}
    client = AzureAI.get_model_client("<dynamic_config_id>")
    ```
  </Tab>

  <Tab title=".NET">
    ```csharp theme={null}
    var client = Server.GetModelClient("<dynamic_config_id>");
    ```
  </Tab>
</Tabs>

## Option 2: Using hard-coded endpoint and key

This is the most direct way of instantiating an AI model client.  However, this would mean you'll have to embed the endpoint and key in your code, or use another way (like an environment variable) to get the model endpoint and key into the process.

<Tabs>
  <Tab title="NodeJS">
    ```js theme={null}
    const modelClient = AzureAI.getModelClientFromEndpoint(
        "<DEPLOYMENT_ENDPOINT_URL>",
        "<DEPLOYMENT_KEY>"
    );
    ```
  </Tab>

  <Tab title="Python">
    ```python theme={null}
    modelClient = AzureAI.get_model_client_from_endpoint("<DEPLOYMENT_ENDPOINT_URL>", "<DEPLOYMENT_KEY>")
    ```
  </Tab>

  <Tab title=".NET">
    ```csharp theme={null}
    var modelClient = Server.GetModelClientFromEndpoint(
        "<DEPLOYMENT_ENDPOINT_URL>",
        "<DEPLOYMENT_KEY>"
    );
    ```
  </Tab>
</Tabs>