AI-102 Implement generative AI solutions Practice Question
Which THREE factors should you consider when selecting a model for a generative AI solution on Azure?
⚠ Common exam trap
Many exam-takers confuse internal model architecture (like transformer layers) with selection criteria, when in fact Azure abstracts those details and you only need to consider cost, capability, latency, and deployment options.
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
✓
Cost per token and deployment options.
Option A is correct because cost per token and deployment options (such as pay-as-you-go versus provisioned throughput) directly affect the total cost and scalability of a generative AI solution on Azure. Option B is correct because the model's capability and modality determine whether it can handle the required task, such as text generation, code completion, or image creation. Option C is correct because latency and throughput requirements dictate whether the chosen model and deployment type can meet the application's performance and concurrency needs. Option D is not a primary selection factor because the number of transformer layers is an internal architectural detail that influences capability but is not a decision criterion by itself. Option E is not a primary selection factor because training data source and licensing are legal and compliance considerations, not core factors for selecting a model for a generative AI solution on Azure.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Cost per token and deployment options.
Why this is correct
Token pricing directly determines running cost at scale, while deployment options (serverless versus provisioned throughput) govern quota and capacity planning. Both are explicit selection factors for generative AI models on Azure, letting architects balance budget against the throughput the workload demands.
- ✓
Model capability and modality (text, code, image).
Why this is correct
Matching model capability and modality to the task is essential: text, code and image inputs require different model families. Choosing a model whose supported modality and reasoning capability fit the scenario prevents redesign later, satisfying the requirement to align model choice with workload type.
- ✓
Latency and throughput requirements.
Why this is correct
Latency and throughput dictate whether a model meets interactive response targets or bulk processing volumes. These performance characteristics vary across models and deployment types, so they must be evaluated against the solution's real-time or batch constraints before selection.
- ✗
Number of transformer layers in the model.
Why it's wrong here
Transformer layer count is an internal architecture detail that does not map to task fit, latency, cost or accuracy requirements. It is tempting because deeper stacks are associated with richer reasoning, but model selection should weigh capability benchmarks, context window, regional availability and pricing against the scenario.
- ✗
Training data source and licensing.
Why it's wrong here
Training data source and licensing governs legal reuse of weights and datasets, not model selection criteria such as task fit, latency, context window or cost. It is tempting because provenance matters when fine-tuning or redistributing a model, where licence terms and data origin genuinely constrain what you may deploy.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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-102 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-102 exam.