Azure AI

Before you can use Azure AI as an AI provider, create an Azure resource, deploy a model, and retrieve your credentials.

1. Create an Azure account

• Go to the Azure portal.
• Sign in or create an account.
• Make sure you have an active Azure subscription.

2. Create an Azure AI resource

Azure organizes AI usage through resources.

• Go to Create resource.
• Search for Azure OpenAI or Azure AI Foundry.
• Create a new resource with:
  • Resource group: create or select one.
  • Region: West Europe is recommended; use Sweden Central for the latest models (such as GPT-5.x).
  • Name: use a clear naming convention, for example ai-studio-prod.

This resource contains the models and deployments, API access (endpoint + keys), and monitoring/usage data.

3. Deploy a model

• Open your Azure AI resource.
• Go to Models + Endpoints.
• Create a new deployment and select a model (for example GPT-4o transcribe or GPT-5.x).
• Define a deployment name: this is what you use in Any2Info, not necessarily the model name (though it can be the same).
• Set the Tokens per Minute Rate Limit to 1M (choose Customize in the deployment dialog, or edit the deployment afterwards).

Caution

A new deployment defaults to a rate limit of 150K tokens per minute. That is too low for AI Studio and causes rate-limit errors, so raise it to 1M straight away. If 1M isn’t available, your subscription’s quota for that model and region is lower: request a quota increase in Azure.

4. Retrieve the API key and endpoint

• Open your Azure AI resource.
• Go to Models + Endpoints.
• Select your deployed model to find the API key.

These values are required to connect Azure to Any2Info: see Connections.

5. Cost monitoring

There are two places to monitor usage and cost:

• Model usage (per deployment): open your Azure AI resource, go to Models + Endpoints, select your deployment, then Metrics to see token usage, requests, and performance.
• Azure cost management: available in the Azure portal.

Next steps

Once your Azure AI resource and deployment are set up, create a connection in Data Studio, select Azure AI as the provider, and continue to creating your first agent.