AI is everywhere right now. It’s in your apps, in your meetings, possibly even in your fridge reminding you to buy more milk. But maybe you don’t want to pay for an expensive Copilot license, or you prefer something more customizable than the default Copilot Chat. Maybe you’d like to work with a GPT model instead. Or perhaps Whisper for speech-to-text? Sora for video? DALL·E for images?

Honestly, it doesn’t matter which one you choose — because in this article, you’ll learn how to set up any of over 40 different AI models in Azure. Once deployed, you can:

• Use the model directly in the Playground.
• Create a Web App with a chat interface in just a few clicks.
• Or connect to it via API (Logic Apps, PowerShell, Power Automate, etc.).

And yes, it’s surprisingly quick. You don’t need a PhD in Computer Science — just an Azure subscription and the ability to click “Create” without fear.

Prerequisites

An

• Azure Subscription

…That’s it. Seriously.

Step-by-Step Guide

1. Open the Azure Portal and Search for “AI Foundry”

Once you’re there, click Azure OpenAI → Create.

2. Choose Your Settings

Select your Subscription and Resource Group.

Pick your Region, Name, and Pricing Tier.

Then click through like you’re speedrunning Azure.

3. Network Settings

If you don’t have special networking requirements, just select All networks. Then hit Create Resource.

4. Access the Foundry Portal

From here, you can browse all available models.

5. Choose Your Model

Find the one you want and click Use this Model.

6. Deploy the Model

Click Deploy, wait a few seconds, and voilà — your model is ready. You can now use it directly in the Playground to start chatting.

That’s it. You’ve just built your very own AI instance in Azure, without a single line of code.