QuestionQ70

VerifiedIdentify an implementation and adoption strategy for Microsoft’s AI apps and services

Your company has an AI solution that relies on a prebuilt Azure OpenAI model to generate content.

You need to reduce the cost of the solution while minimizing the impact on the quality of the generated output.

Which two actions should you perform? Each correct answer presents part of the solution.

Note: Each correct selection is worth one point.

Choose two
Explanation

Azure OpenAI usage costs are driven primarily by the model tier selected and the number of tokens processed. Choosing a less expensive but still capable model reduces per-call cost, and refining/shortening prompts reduces the token count charged for each request-response cycle — both approaches lower spend without materially degrading the quality of generated content. Content moderation is a built-in safety feature and does not affect billing; reducing hosting hours applies to dedicated/provisioned throughput deployments rather than typical prebuilt consumption-based usage and can reduce availability rather than target cost efficiently; fine-tuning adds training and hosting costs and is intended to improve output relevance, not reduce expense.

Learn more

Community Discussion

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