AI-901: Microsoft Azure AI Fundamentals

By Microsoft · Question Mode

QuestionQ12

Implement AI solutions by using Microsoft Foundry

You have a Microsoft Foundry project with a generative AI model deployment.

You need to ensure that responses generated by the model minimize costs and stay within a defined length.

Which parameter should you configure?

Explanation

Max Completion Tokens sets an upper bound on the tokens generated for a completion, including visible output and reasoning tokens. Limiting generated tokens constrains response length and helps control token-based generation costs.

Learn more

Community Discussion

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