This PMLE practice question tests your understanding of monitoring ml 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.
Your team deploys a model using Vertex AI Endpoints with autoscaling. Which TWO metrics are most important to monitor in order to optimize cost and performance? (Choose two.)
Number of active nodes in the endpoint.
Why wrong: Result of scaling, not a primary input for optimization.
Number of requests per minute.
Indicates traffic patterns.
CPU utilization of the serving containers.
Indicator of whether resources are over/under-provisioned.
Error rate (HTTP 4xx/5xx).
Why wrong: Reliability metric.
P99 prediction latency.
Why wrong: More about performance than cost.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Number of requests per minute.
Option B is correct because the number of requests per minute directly drives autoscaling behavior in Vertex AI Endpoints. Monitoring this metric allows you to right-size the number of serving nodes to match traffic patterns, avoiding over-provisioning (cost) or under-provisioning (performance). Option C is correct because CPU utilization of the serving containers indicates whether the model is compute-bound or idle; high CPU suggests the need for more nodes, while low CPU suggests over-provisioning, directly impacting both cost and latency.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Number of active nodes in the endpoint.
Why it's wrong here
Result of scaling, not a primary input for optimization.
Number of requests per minute.
Why this is correct
Indicates traffic patterns.
Related concept
Read the scenario before looking for a memorised answer.
CPU utilization of the serving containers.
Why this is correct
Indicator of whether resources are over/under-provisioned.
Related concept
Read the scenario before looking for a memorised answer.
Error rate (HTTP 4xx/5xx).
Why it's wrong here
Reliability metric.
P99 prediction latency.
Why it's wrong here
More about performance than cost.
Common exam traps
Google Cloud often tests the distinction between metrics that are direct inputs to autoscaling decisions (requests per minute, CPU utilization) versus metrics that are outcomes of scaling (active nodes, latency, error rate), leading candidates to mistakenly select outcome metrics as primary optimization drivers.
Detailed technical explanation
Vertex AI Endpoints use a target CPU utilization (default 60%) to trigger autoscaling. When requests per minute increase, CPU rises, and the autoscaler adds nodes; monitoring requests per minute helps predict scaling events before latency spikes. In practice, a sudden burst of requests can cause cold-start latency if the autoscaler lags, so combining requests per minute with CPU utilization allows proactive node allocation, reducing both cost (by avoiding over-provisioning) and performance degradation (by preventing under-provisioning).
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
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
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Monitoring ML solutions — study guide chapter
Learn the concepts, then practise the questions
Monitoring ML solutions practice questions
Targeted practice on this topic area only
All PMLE questions
506 questions across all exam domains
Google Professional Machine Learning Engineer study guide
Full concept coverage aligned to exam objectives
PMLE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PMLE questions linked to Scaling prototypes into ML models.
Practise PMLE questions linked to Automating and orchestrating ML pipelines.
Practise PMLE questions linked to Collaborating within and across teams to manage data and models.
Practise PMLE questions linked to Architecting low-code ML solutions.
Practise PMLE questions linked to Collaborating to manage data and models.
Practise PMLE questions linked to Serving and scaling models.
Practise PMLE questions linked to Monitoring ML solutions.
Practise PMLE questions linked to Solving business challenges with ML.
Practise PMLE questions linked to PMLE fundamentals.
Practise PMLE questions linked to PMLE scenario.
Practise PMLE questions linked to PMLE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Monitoring ML solutions — This question tests Monitoring ML solutions — Read the scenario before looking for a memorised answer..
The correct answer is: Number of requests per minute. — Option B is correct because the number of requests per minute directly drives autoscaling behavior in Vertex AI Endpoints. Monitoring this metric allows you to right-size the number of serving nodes to match traffic patterns, avoiding over-provisioning (cost) or under-provisioning (performance). Option C is correct because CPU utilization of the serving containers indicates whether the model is compute-bound or idle; high CPU suggests the need for more nodes, while low CPU suggests over-provisioning, directly impacting both cost and latency.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
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 →
Keep practising
Last reviewed: Jun 30, 2026
This PMLE 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 PMLE 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.