2.1Standard
Long inputs and outputs increase cost.
Preserve quality within limits.
Choose two designs.
× Incorrect
Set separate input, retrieval, and output budgets with overflow behavior and measure model price, cache, retries, quality, and latency.
Detailed explanation
IncorrectCharacter count exactly estimates token cost
Tokenization varies.
IncorrectAdd every document even when quality falls
Noise and cost increase.
CorrectSet input, retrieval, and output limits and define summarize, omit, or reject behavior
Limits and cost are controlled.
CorrectMeasure unit price, caching, retries, quality, and latency by model
Total cost is comparable.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.1・3.3のトークン、コスト、コンテキストを確認する。
Official references
What to confirm
トークン数と単価だけでなく、再試行・品質・遅延を含む予算を設計できる。
Key points
- Token budget
- Unit price
- Total cost
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
Token budget
A limit on the tokens allocated to instructions, evidence, and generated output.
Context limit
The maximum input and output capacity supported for one model request.
Question IDAWS-AIF-495
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