3.1Standard
Reduce monthly inference cost for a summarizer.
Preserve quality, safety, and latency.
Choose two appropriate comparisons.
× Incorrect
Use the same representative and safety inputs, measure token use, and include model price, retries, cache, and quality in total-cost analysis.
Detailed explanation
IncorrectOptimize cost while ignoring safety
Cost reduction can create unacceptable risk.
CorrectInclude price, input/output length, cache, and retries in cost analysis
The total cost drivers become visible.
IncorrectSkip quality testing for a cheaper model
Poor quality can cause rework and harm.
CorrectMeasure quality and token use on the same representative and safety inputs
Outputs and usage are comparable.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock公式料金・モデル比較とAIF-C01 Domain 3.1を確認する。
Official references
What to confirm
モデル単価と総所有コスト、品質の比較方法を説明できる。
Key points
- Price
- Tokens
- Quality
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Total inference cost
The combined expense of model calls, tokens, requests, retries, caching, and supporting resources.
Cost per token
A price applied to model input or output token usage.
Question IDAWS-AIF-180
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue