AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ96

VerifiedPlan and manage an Azure AI solution

You have a Microsoft Foundry project.

You need to deploy a model from the model catalog to support real-time inference. The solution must meet the following requirements:

  • Use key-based authentication.
  • Support real-time REST API access.
  • Must NOT consume the vCPU quota of the virtual machines in the Azure subscription.

Which type of deployment should you use?

Explanation

Serverless API (Models-as-a-Service) deployments in Azure AI Foundry are hosted and billed on a pay-as-you-go basis by Microsoft rather than being provisioned onto dedicated VM instances in the customer's subscription, so they do not draw from the subscription's vCPU quota. They expose a real-time REST API endpoint and are authenticated using an API key (key-based authentication), satisfying all stated requirements. In contrast, standard (managed compute) and self-hosted container deployments provision dedicated VM instances that consume subscription vCPU quota, and batch deployments are designed for asynchronous/offline processing rather than real-time REST calls.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!