DistillPrep
Python
GenAI
GenAI Frameworks
NLP
Deep Learning
Machine Learning
ML Libraries
Statistics
SQL
MLOps
Cloud
System Design
Blog
Learn
Practice
Test
Live Engine
Select Topic
Cloud ML Fundamentals
(15)
Aws Sagemaker
(15)
Gcp Vertex Ai
(15)
Azure ML
(15)
Managed Vs Custom Training
(15)
Serverless Inference
(15)
Cloud Storage For ML
(15)
Managed Vector Databases Cloud
(15)
LLM Apis And Cloud
(15)
Cloud Security For ML
(15)
Cost Optimization Patterns
(15)
easy
Serverless Inference
A team wants to deploy a scikit-learn model that receives ~50 requests per day with no predictable pattern. They want zero idle cost. Which AWS deployment option is most appropriate?
A
SageMaker Real-Time Endpoint with minimum 1 instance — it provides consistent latency
B
AWS Lambda with the model loaded as a layer or from S3 — it charges only per invocation and scales to zero when idle
C
SageMaker Serverless Endpoint — it scales to zero between requests and charges per invocation
D
EC2 Spot Instance running a Flask server — it auto-terminates when idle
Previous
Back
Next