Exams / AIF-C01 / AWS generative AI services / Question 5
AIF-C01 practice question: AWS generative AI services (5 of 5)
Fundamentals of Generative AI A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.
A media company runs a summarisation feature on Amazon Bedrock. For the first three months it expects low, unpredictable traffic while it tests the market. Later it expects steady, high volume that needs guaranteed capacity. Which pricing approach is MOST cost-effective for each phase?
Choose one answer.
- AA. Provisioned Throughput during testing, then on-demand for the steady phase
- BB. On-demand during testing, then Provisioned Throughput for the steady phase
- CC. Provisioned Throughput with a long commitment for both phases
- DD. Batch inference for both phases, because it is always the cheapest
Show the answer and explanation
Answer: B
- A. Wrong: This is the wrong way round. Paying for reserved capacity while traffic is low and unpredictable wastes money.
- B. Right: Correct. On-demand charges only for tokens used, which suits uncertain traffic. Provisioned Throughput gives dedicated capacity at a fixed cost for steady, high volume.
- C. Wrong: A long commitment before demand is known risks paying for capacity that is not used during testing.
- D. Wrong: Batch inference is asynchronous and returns results later. A live summarisation feature needs responses straight away.
Explanation
On-demand pricing charges per input and output token with no commitment, so it suits experimentation and variable traffic. Provisioned Throughput buys dedicated model capacity at a fixed hourly cost, with lower rates for longer commitments, so it suits predictable, high-volume workloads that need consistent performance.
Study
Keep practising
Answer questions with a score at the end, or practise just this topic with the explanation after each one. No sign-up needed.