Exams / AIF-C01 / Generative AI concepts / Question 1
AIF-C01 practice question: Generative AI concepts (1 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 legal firm uses a text model on Amazon Bedrock with on-demand pricing. Staff have started pasting entire 80-page contracts into every prompt, and the monthly bill has risen sharply even though the answers are short. What is the MOST likely reason?
Choose one answer.
- AA. On-demand text models are billed per prompt, and longer prompts count as several prompts
- BB. Input tokens are billed, so very long prompts cost more even when the answers are short
- CC. Bedrock charges a fixed fee for each page of a document that is uploaded
- DD. Long prompts force Bedrock to switch the account to Provisioned Throughput
Show the answer and explanation
Answer: B
- A. Wrong: Text models on demand are billed by tokens, not by a fixed charge per prompt.
- B. Right: Correct. On-demand text inference charges for input and output tokens, so a long contract in every prompt drives up input cost.
- C. Wrong: There is no per-page fee for text in a prompt. The cost comes from the tokens the text is split into.
- D. Wrong: Provisioned Throughput is something a customer chooses to buy. Prompt length does not switch pricing models.
Explanation
Text foundation models break input and output into tokens, and on-demand pricing charges for both input tokens and output tokens (output tokens usually cost more each). Very long prompts therefore cost more and can add latency. Retrieving only the relevant passages (RAG) or caching a repeated prefix are common ways to cut input tokens.
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.