Answer-first summary for fast verification
Answer: Deploy the model to a managed online endpoint. During deployment, set the token_auth_mode parameter of the target configuration object to true.
The question requires deploying a model with two key requirements: (1) monitoring costs at endpoint and deployment level, and (2) Microsoft Entra ID authentication. Managed online endpoints provide built-in cost monitoring capabilities at both endpoint and deployment levels, which AKS deployments lack. For Microsoft Entra ID authentication, token-based authentication (token_auth_mode=true) is required, as confirmed by Microsoft documentation and the community discussion where the highest-voted comment (D0ktor) explicitly states that Microsoft Entra ID authentication only works with token authentication. Option D satisfies both requirements: managed online endpoint for cost monitoring and token_auth_mode=true for Entra ID authentication. Option C is incorrect because it doesn't specify token authentication. Options A and B are incorrect because AKS doesn't provide the same level of built-in cost monitoring at deployment level.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You have an Azure Machine Learning workspace and need to deploy a trained model as an online endpoint. You must monitor costs at the endpoint and deployment level, and users are required to authenticate using Microsoft Entra ID.
What should you do?
A
Deploy the model to Azure Kubernetes Service (AKS). During deployment, set the token_auth_mode parameter of the target configuration object to true.
B
Deploy the model to Azure Kubernetes Service (AKS). During deployment, set the auth_mode parameter to configure the authentication type.
C
Deploy the model to a managed online endpoint. During deployment, set the auth_mode parameter to configure the authentication type.
D
Deploy the model to a managed online endpoint. During deployment, set the token_auth_mode parameter of the target configuration object to true.