Question 484 of 835
hardMultiple ChoiceObjective-mapped
MLA-C01 Practice Question: A team deploys a machine learning model using a…
A team deploys a machine learning model using a SageMaker endpoint with an ML.T4 instance. After a week, they notice that the endpoint's CPU utilization is consistently below 10% and latency is low. However, the endpoint is incurring high costs. Which action should the team take to reduce costs while maintaining the ability to serve traffic?
⚠ Common exam trap
It's easy for candidates to assume reducing instance count or switching endpoint types (multi-model, async) will lower costs, but they overlook that provisioned instances always incur hourly charges, whereas serverless charges only for actual compute usage, making it the optimal choice for consistently low-utilization endpoints.
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
✓
Migrate to a SageMaker Serverless Inference endpoint
The endpoint's CPU utilization is consistently below 10% with low latency, indicating that traffic is sparse and the instance is severely underutilized. SageMaker Serverless Inference automatically scales compute resources based on request volume and charges only for the compute time consumed per inference, eliminating idle costs. This makes it the most cost-effective choice for low-utilization workloads while still maintaining the ability to serve traffic on demand.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Switch to a multi-model endpoint to share instances across models
Why it's wrong here
Multi-model endpoints still have fixed instances; cost savings are limited.
- ✗
Reduce the number of instances to one
Why it's wrong here
Reducing instances may cause high latency during traffic spikes.
- ✓
Migrate to a SageMaker Serverless Inference endpoint
Why this is correct
Serverless endpoints scale to zero when idle, reducing cost.
- ✗
Implement an asynchronous inference endpoint
Why it's wrong here
Asynchronous inference is for batch processing, not real-time.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
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 →
Last reviewed: Jul 4, 2026
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 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.