Create Azure Open AI

The demand for Azure OpenAI has skyrocketed due to its enterprise-grade security, compliance features, and seamless integration with existing Microsoft ecosystems. This comprehensive tutorial will provide you with everything needed to create and deploy Azure OpenAI services successfully.

Create Azure Open AI

Before diving into the creation process, let me explain why Azure OpenAI has become the preferred choice for many enterprises seeking to integrate AI.

Azure OpenAI Service combines OpenAI’s cutting-edge models (GPT-4, GPT-3.5-turbo, DALL-E, and Codex) with Microsoft Azure’s enterprise-grade infrastructure. This combination provides the advanced AI capabilities your business needs while maintaining the security, compliance, and reliability standards.

Key Benefits

Enterprise Security and Compliance:

• SOC 2 Type II compliance
• HIPAA eligibility for healthcare organizations
• FedRAMP authorization for government contractors
• Data residency within US borders
• Advanced threat protection and monitoring

Business Advantages:

• Integration with existing Microsoft 365 and Azure services
• Enterprise-grade SLA with 99.9% uptime guarantee
• Flexible pricing models for various business sizes
• 24/7 Microsoft support for critical business operations
• Advanced analytics and usage monitoring

Prerequisites

Here are the essential requirements you’ll need before starting:

Account and Subscription Requirements

Technical Prerequisites:

• Valid Azure subscription (Pay-as-you-go, Enterprise Agreement, or CSP)
• Subscription must be in good standing with no billing issues
• Administrator access to submit access requests
• Valid business email address (no personal Gmail/Yahoo accounts)

Method 1: Using Azure Portal

This is the most user-friendly approach I recommend for business users and those new to Azure services.

1. Log in to the Azure Portal (portal.azure.com)
2. Search for “Azure OpenAI”.

3. Click “Create” to start the configuration process.

Configuration Settings:

On the Basics tab, fill in the details below.

Basics Tab:

• Subscription: Select your approved Azure subscription
• Resource Group: Click on the create new link to create a new resource group.
• Region: East US 2 (recommended for the US East Coast)
• Name: Unique name (e.g., mycompany-openai-prod-2025)
• Pricing Tier: Standard S0 (most common for production)

Click on the Next button to navigate to the Networking tab.

Networking Tab:

• Network access: Public endpoint (start here, restrict later)
• Virtual network: Configure if needed for enterprise security

Click on the next button.

Tags Tab:

You can specify the tags like below, but it’s not mandatory. You can leave it as it is if you don’t wish to specify any tag.

• Environment: Production
• Department: IT or specific business unit
• CostCenter: Your internal cost allocation code
• Owner: Technical contact email

Click on the Next button.

Finally, click on the Create button on the Review + Submit screen as shown in the screenshot below.

The Azure Open AI service has been created successfully, as shown in the screenshot below.

Deploy AI Models

After creating the resource, you need to deploy specific AI models. Here’s my recommended approach:

Model Deployment Process:

1. Navigate to your newly created Azure OpenAI resource
2. Click “Model deployments” in the left navigation
3. Click “Create new deployment”
4. Configure your first model:

Recommended Model Configuration:

Deployment Configuration Example:

{
  "deployment_name": "gpt-4-production",
  "model_name": "gpt-4",
  "model_version": "0613",
  "scale_type": "Standard",
  "capacity": 10
}

Method 2: Using Azure CLI

For DevOps teams and automated deployments, I prefer Azure CLI for consistency and version control.

Creating Azure OpenAI Resource via CLI

# Set deployment variables
RESOURCE_GROUP="rg-openai-production-eastus"
LOCATION="eastus2"
OPENAI_NAME="mycompany-openai-prod-2025"
SUBSCRIPTION_ID="your-subscription-id"

# Create resource group
az group create \
  --name $RESOURCE_GROUP \
  --location $LOCATION \
  --subscription $SUBSCRIPTION_ID

# Create Azure OpenAI resource
az cognitiveservices account create \
  --name $OPENAI_NAME \
  --resource-group $RESOURCE_GROUP \
  --location $LOCATION \
  --kind OpenAI \
  --sku S0 \
  --custom-domain $OPENAI_NAME \
  --subscription $SUBSCRIPTION_ID

# Verify creation
az cognitiveservices account show \
  --name $OPENAI_NAME \
  --resource-group $RESOURCE_GROUP \
  --query "{name:name, location:location, sku:sku.name, endpoint:properties.endpoint}"

After executing the above query, I got the expected output as shown in the below screenshot.

The Azure Open AI has been created successfully.

Deploying Models via CLI

# Deploy GPT-4 model
az cognitiveservices account deployment create \
  --name $OPENAI_NAME \
  --resource-group $RESOURCE_GROUP \
  --deployment-name "gpt-4-production" \
  --model-name "gpt-4" \
  --model-version "0613" \
  --model-format OpenAI \
  --sku-capacity 10 \
  --sku-name "Standard"

# Deploy GPT-3.5-turbo model
az cognitiveservices account deployment create \
  --name $OPENAI_NAME \
  --resource-group $RESOURCE_GROUP \
  --deployment-name "gpt-35-turbo-prod" \
  --model-name "gpt-35-turbo" \
  --model-version "0613" \
  --model-format OpenAI \
  --sku-capacity 60 \
  --sku-name "Standard"

# List deployed models
az cognitiveservices account deployment list \
  --name $OPENAI_NAME \
  --resource-group $RESOURCE_GROUP

Method 3: Using PowerShell

We can also use the below powershell script to create the Azure Open AI.

PowerShell Setup and Authentication

# Install Azure PowerShell module
Install-Module -Name Az -Repository PSGallery -Force -AllowClobber

# Connect to Azure
Connect-AzAccount

# Set subscription context
Set-AzContext -SubscriptionId "your-subscription-id"

# Verify connection
Get-AzContext

Creating Resources with PowerShell

# Define deployment variables
$resourceGroupName = "rg-openai-production-eastus"
$location = "East US 2"
$openAIName = "mycompany-openai-prod-2025"
$subscriptionId = "your-subscription-id"

# Create resource group
New-AzResourceGroup `
  -Name $resourceGroupName `
  -Location $location

# Create Azure OpenAI resource
$openAIAccount = New-AzCognitiveServicesAccount `
  -ResourceGroupName $resourceGroupName `
  -Name $openAIName `
  -Location $location `
  -Kind "OpenAI" `
  -SkuName "S0" `
  -CustomSubdomainName $openAIName

# Display resource information
Write-Output "Resource Name: $($openAIAccount.AccountName)"
Write-Output "Endpoint: $($openAIAccount.Endpoint)"
Write-Output "Location: $($openAIAccount.Location)"
Write-Output "Status: $($openAIAccount.ProvisioningState)"

# Get API keys
$keys = Get-AzCognitiveServicesAccountKey -ResourceGroupName $resourceGroupName -Name $openAIName
Write-Output "Primary Key: $($keys.Key1)"
Write-Output "Secondary Key: $($keys.Key2)"

After executing the above PowerShell script, the Azure Open AI service has been created successfully as shown in the screenshot below.

Video Tutorial

Conclusion

The Azure OpenAI landscape continues evolving rapidly, with new models, features, and capabilities launching regularly. Remember that creating Azure OpenAI is just the first step in your AI journey . Start implementing these techniques today, and within weeks, you’ll have a robust, scalable Azure OpenAI deployment in your organization.

You may also like the following articles

• Azure OpenAI Endpoint
• Azure OpenAI Best Practices
• How to Get Azure OpenAI Key
• Azure OpenAI Service Features
• What Is Azure AI Search
• List of Azure AI Services

Rajkishore

I am Rajkishore, and I am a Microsoft Certified IT Consultant. I have over 14 years of experience in Microsoft Azure and AWS, with good experience in Azure Functions, Storage, Virtual Machines, Logic Apps, PowerShell Commands, CLI Commands, Machine Learning, AI, Azure Cognitive Services, DevOps, etc. Not only that, I do have good real-time experience in designing and developing cloud-native data integrations on Azure or AWS, etc. I hope you will learn from these practical Azure tutorials. Read more.