AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is the maximum output length parameter 'max tokens' used for in Azure OpenAI?
⚠ Common exam trap
Many exam-takers confuse 'max tokens' with input length limits or rate limits, because the term 'maximum' sounds like a general cap, but it specifically applies only to the generated response tokens, not to the prompt or API throughput.
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
✓
The maximum number of tokens in the generated response to control length and cost
The 'max tokens' parameter in Azure OpenAI controls the maximum number of tokens (roughly 0.75 words per token) that the model can generate in a single response. This directly limits the length of the output, which in turn controls both the cost (since Azure OpenAI charges per token) and the response size, preventing excessively long or expensive completions.
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 API requests per second
Why it's wrong here
Maximum API requests per second is a throughput constraint enforced by the Azure OpenAI deployment's rate limit and quota settings, not by the max_tokens parameter. max_tokens is a per-request generation parameter that caps the number of tokens the model can emit in a single completion. Limiting output length does not change how many requests you can send per second; those limits are configured separately in the Azure resource's 'Quotas' and 'Limits' blades. Therefore, this option incorrectly conflates a rate-limit control with an output-length parameter.
- ✓
The maximum number of tokens in the generated response to control length and cost
Why this is correct
max_tokens sets the maximum number of tokens that the model can generate in the response for a single API call, directly controlling how long the output can be and how much that request costs. Because Azure OpenAI billing is token-based, a lower max_tokens value reduces the number of billed completion tokens, making each request cheaper and generally faster. However, if max_tokens is set too low, the model may stop before completing a full answer, leaving the response truncated. This is exactly the intended purpose of the parameter, making it the correct answer.
- ✗
The maximum number of words in the input prompt
Why it's wrong here
The length of the input prompt is determined by the model's context window, which includes both input and output tokens, and is handled separately from max_tokens. max_tokens specifically limits only the model's generated output tokens; it does not truncate, reject, or constrain the prompt you send. You can send a prompt up to the context-window limit regardless of the max_tokens value, though the combined input and output must fit within that window. Thus, this option confuses the role of an output cap with input-length management.
- ✗
The maximum number of concurrent users of the model
Why it's wrong here
The number of concurrent users is managed through Azure OpenAI's rate limits, capacity allocations, and deployment settings—not by the max_tokens parameter. max_tokens is a per-request model generation setting that limits individual response length, and it has no bearing on how many simultaneous sessions or requests the service can handle. Concurrency is influenced by provisioning type, throughput quotas, and latency, not by the token cap set on each request. Therefore, this option incorrectly substitutes a resource-management metric for a text-generation control.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Token
A token is a digital or physical object that represents a set of permissions or access rights, used to verify identity or grant access in computer systems.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
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 →
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.