Courseiva

AI-900 Practice Question: Describe features of generative AI workloads on Azure

What is 'max_tokens' parameter in Azure OpenAI and how does it affect responses?

⚠ Common exam trap

Watch out — candidates often confuse 'max_tokens' with the model's total context window limit, leading candidates to mistakenly think it caps the input prompt length instead of the output generation.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

A limit on the model's generated response length — stopping output at the specified token count

The 'max_tokens' parameter in Azure OpenAI sets a hard limit on the number of tokens (words or subwords) the model can generate in its response. Once this token count is reached, the model stops producing further output, effectively controlling response length. This is distinct from input processing limits, as 'max_tokens' applies solely to the generated completion.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • The maximum number of tokens in the input prompt the model can process

    Why it's wrong here

    This describes the input context window — the maximum total number of tokens (prompt + generation) a model can accept, often 8k, 16k, or 32k depending on the model deployment. max_tokens is a separate parameter that limits only the output portion; the input limit is enforced by the model's architecture and is not something you set via max_tokens. Setting a high max_tokens value does not increase how many tokens the model can read in the prompt.

  • A limit on the model's generated response length — stopping output at the specified token count

    Why this is correct

    The max_tokens parameter in Azure OpenAI service directly caps the number of tokens the model can generate in a single completion response. Once this count is reached, generation stops mid-sequence if necessary — this is a hard per-request limit that prevents unbounded output, which is essential for controlling latency, cost, and response predictability. It applies only to the generated text, not to the prompt or any historical context.

  • The total number of API calls allowed per Azure subscription per hour

    Why it's wrong here

    This describes a rate limit, such as requests per minute (RPM) or tokens per minute (TPM), which governs how many API calls your Azure subscription can make in a given time window. max_tokens is a per-request generation control, not a subscription-level quota; you can set a high max_tokens value on a single call regardless of how many calls you make per hour. Mixing these two concepts confuses a model parameter with an infrastructure throttling policy.

  • The maximum number of conversation turns before the session resets

    Why it's wrong here

    Conversation turn limits are determined by the application developer, not by the model API parameter. In Azure OpenAI, multi-turn chat is managed by sending the full conversation history as messages in each request; max_tokens does not count turns nor impose any session reset. This misconception likely arises from chat completions' 'messages' array, but max_tokens is purely about the length of the current response generated by the model.

About these practice questions

Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.