AIF-C01 Practice Test 5

A medical imaging company runs a model on Amazon SageMaker AI that analyzes high-resolution scans. Each request carries a payload of several hundred megabytes and can take up to 20 minutes to process. Requests arrive unpredictably throughout the day, results are needed within minutes rather than the next day, and the company doesn't want to pay for idle instances when no scans are waiting. Which inference option fits best?