How to deploy the AI Inference Starter Kit template

The AI Inference Starter Kit template contains the configurations to create an application with OpenAI-compatible APIs, running directly on Azion’s distributed network. This template simplifies the process of deploying AI models at the edge, eliminating origin dependencies and allowing you to quickly develop intelligent applications.

The deployment of this template creates an application with a function and a domain to facilitate your access and management through Azion Web Platform.

Requirements

• The template uses Application Accelerator, Functions, and AI Inference. This may generate usage-related costs. Check the pricing page for more information.

Deploy the template

1. Access the Azion console.
2. Click the + Create button to open the templates page.
3. Select the AI Inference Starter Kit template.
4. On the template page, type a name for your application and click Deploy.
5. Wait for the application to be available on the domain your-url.map.azionedge.net (or your custom domain).
6. Interact with the model via your application’s OpenAI-compatible endpoint.

During the deployment, you can follow the process through a window showing the logs. When it’s complete, the page shows information about the application and some options to continue your journey.

Manage the template

Considering that this initial setup may not be optimal for your specific application, all settings can be customized any time you need by using Azion’s platform.

Update the function

Follow these steps to update the function according to your needs:

1. Access Azion Console.
2. On the upper-left corner, select Products menu, the icon with three horizontal lines, > Functions.
3. Find the function related to your template and select it. It will have the same name as your application.
   • The list is organized alphabetically. You can also use the search bar located in the upper-left corner of the list; currently, it filters only by Function Name.
4. On the function page, use the tabs to configure your function.
   • On the Main Settings tab, you can rename the function and change some basic settings.
   • On the Code tab, you can update the function’s code.
   • On the Arguments tab, you can define the arguments used by the function.
5. Click the Save button to save your changes.

The code example below includes a simple function ready to run. This function receives a POST request to the desired AI model and returns the response.

This example uses the Qwen3 model. You can change the model and the request parameters according to your preferences. Check the AI models reference for more information about the available models and how to use them in your application.

Manage the application

To manage and edit your application’s settings, follow these steps:

1. Access Azion Console.
2. On the upper-left corner, select Products Menu, the icon with three horizontal lines, > Applications.
   • You’ll be redirected to the Applications page. It lists all the applications you’ve created.
3. Find the application related to your template and select it.
   • The list is organized alphabetically. You can also use the search bar located in the upper-left corner of the list; currently, it filters only by Application Name.

After selecting the application you’ll work on, you’ll be directed to a page containing all the settings you can adjust.

Add a custom domain

The application created during the deployment has an Azion Workload Domain assigned to make it accessible through the browser. The domain has the following format: xxxxxxxxxx.map.azionedge.net/. However, you can add a custom domain for users to access your application through it.