The answer is to reduce the model size and use batch prediction. Switching from a larger model like text-bison@002 to a lighter variant such as text-bison-light directly lowers the per-token compute cost, while batch prediction processes multiple requests in a single job, eliminating the per-request overhead and idle compute time of online inference. This combination is ideal for high-volume, non-real-time workloads like text summarization, where you pay only for the batch job’s compute duration rather than individual predictions. On the Google Cloud Generative AI Leader exam, this question tests your understanding of cost optimization for generative AI by distinguishing between online and batch inference patterns—a common trap is assuming that only model downsizing matters. Remember the mnemonic “Lighter and Together”: use a smaller model and batch your requests to cut costs.
Generative AI Leader Practice Question: Business Strategies for Generative AI Solutions
This Generative AI Leader practice question tests your understanding of business strategies for generative ai solutions. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company is using Vertex AI generative models for a high-volume text summarization service. Which two strategies can reduce operational costs?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use batch prediction instead of online prediction.
Batch prediction reduces costs by processing multiple requests in a single batch job, which avoids the per-request overhead and idle compute time associated with online prediction. This is especially cost-effective for high-volume, non-real-time workloads like text summarization, as you pay only for the compute time used during the batch job rather than for each individual inference.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Increase the model's max output tokens to 2048.
Why it's wrong here
Increasing output tokens increases cost per request.
✗
Implement retry logic with exponential backoff.
Why it's wrong here
Retries increase the number of requests, raising costs.
✗
Lower the temperature parameter to 0.
Why it's wrong here
Temperature does not affect cost; it only changes output randomness.
✓
Use batch prediction instead of online prediction.
Why this is correct
Batch prediction has lower per-request cost for large jobs compared to online prediction.
Related concept
Read the scenario before looking for a memorised answer.
✓
Reduce the size of the model (e.g., switch from text-bison@002 to text-bison-light).
Why this is correct
Smaller models have lower cost per token, reducing operational costs.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Google Cloud often tests the misconception that adjusting inference parameters like temperature or output length can reduce costs, when in reality only reducing model size or switching to batch processing directly lowers operational expenses.
Trap categories for this question
Command / output trap
Increasing output tokens increases cost per request.
Detailed technical explanation
How to think about this question
Batch prediction in Vertex AI leverages asynchronous job execution, where the model processes a file of input instances (e.g., JSONL) in a single job, allowing for better resource utilization and lower per-token pricing compared to online prediction's pay-per-request model. The cost savings are amplified for high-volume workloads because batch jobs can be scheduled during off-peak hours and use preemptible VMs or reduced pricing tiers. Additionally, switching to a smaller model like text-bison-light reduces the number of parameters and computational FLOPs per inference, directly lowering the cost per token generated.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What does this Generative AI Leader question test?
Business Strategies for Generative AI Solutions — This question tests Business Strategies for Generative AI Solutions — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Use batch prediction instead of online prediction. — Batch prediction reduces costs by processing multiple requests in a single batch job, which avoids the per-request overhead and idle compute time associated with online prediction. This is especially cost-effective for high-volume, non-real-time workloads like text summarization, as you pay only for the compute time used during the batch job rather than for each individual inference.
What should I do if I get this Generative AI Leader question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
2 more ways this is tested on Generative AI Leader
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A company is using a generative AI model for internal report generation. They notice costs are high because each request processes large amounts of text. Which business strategy would most effectively reduce costs while maintaining quality?
medium
✓ A.Fine-tune a smaller model on a specialized dataset.
B.Use a more powerful model to reduce retries.
C.Implement caching for repeated requests.
D.Increase the batch size for online predictions.
Why A: Fine-tuning a smaller model on a specialized dataset reduces computational cost per inference because smaller models have fewer parameters and require less memory and processing power. By tailoring the model to the company's specific domain (e.g., internal reports), it can maintain output quality comparable to a larger general-purpose model, directly addressing the cost-per-request issue without sacrificing accuracy.
Variation 2. Which of the following is a key consideration when selecting a GenAI model for a cost-sensitive application?
easy
A.Model size in parameters
✓ B.Latency and throughput requirements
C.Number of training epochs
D.The model's training data source
Why B: For cost-sensitive applications, latency and throughput requirements directly impact infrastructure costs, as lower latency often requires more expensive compute resources (e.g., higher GPU memory, faster inference hardware) and higher throughput may necessitate scaling out instances. Model size in parameters is a secondary factor that influences latency and throughput, but the primary cost driver is the operational performance needed to meet service-level agreements (SLAs).
Last reviewed: Jun 30, 2026
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.