Q97 — AWS AIF-C01 Ch.1

Question 97 of 100 | ← Chapter 1

A company wants to evaluate the inference cost associated with using a large language model (LLM); the company plans to use Amazon Bedrock. Which factor drives inference cost upward?

• A. Number of tokens consumed ✓
• B. Temperature value
• C. Volume of data used to train the LLM
• D. Total training time

Correct Answer: A. Number of tokens consumed

Explanation

When evaluating inference cost for large language models (LLMs), the number of tokens consumed is the primary driver of cost increase. Token count directly determines computational and storage resource usage during inference—more tokens mean higher processing demands. Temperature affects output creativity and diversity but not cost directly. Training data volume and total training time impact training costs—not inference costs—and are not directly assessed via Amazon Bedrock.