Q38 — AWS AIF-C01 Ch.1

Question 38 of 100 | ← Chapter 1

A company is using few-shot prompting on a hosted foundation model on Amazon Bedrock. The model currently uses 10 examples in its prompt. The model performs well with this configuration. The company wants to reduce monthly costs. Which solution meets these requirements?

• A. Fine-tune a custom model.
• B. Reduce the number of tokens in the prompt. ✓
• C. Increase the number of prompts.
• D. Use 'provisioned throughput'.

Correct Answer: B. Reduce the number of tokens in the prompt.

Explanation

This question tests understanding of cost optimization for models on Amazon Bedrock. Model invocation costs on Amazon Bedrock are typically directly proportional to the number of tokens in the prompt. Reducing token count lowers per-invocation cost, thereby reducing monthly expenses. Fine-tuning a custom model, increasing prompt count, or using provisioned throughput do not directly reduce invocation costs. Therefore, option B is the correct solution.