A moth-trap count model is hit in short evening bursts, then silent until the next dusk. Finance flagged last month's always-on real-time bill. A short cold start is acceptable for the field app. Which tradeoff should they make?
Select an answer to reveal the explanation.
Short Explanation
Moth-trap counts hit in short evening bursts, then go silent. Move to serverless so the endpoint scales in from zero. Batch is the wrong jump if each field-app request is still interactive, and Comprehend is not that tradeoff.
Full Explanation
Trade the idle-instance cost of a real-time endpoint against serverless inference that scales in from zero when a short cold start is acceptable. Batch transform is the wrong jump if each request is still interactive. Comprehend is not that tradeoff.