3.3Basic
Some users send many requests.
Protect latency and budget for everyone.
Choose two controls.
× Incorrect
Set concurrency, request, and token limits per user, API, or model, and design backoff, priority, and alarms when limits are reached.
Detailed explanation
IncorrectRetry without a limit
Load and cost can amplify.
CorrectDefine backoff, waiting, priority, and alert behavior at the limit
Load and user experience are managed.
CorrectSet concurrency, requests-per-minute, and token limits by user, API, or model
Excess use is bounded.
IncorrectGive everyone an unlimited shared quota
One user can consume the resource.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.3のスロットリング、可用性、費用制御を確認する。
Official references
What to confirm
過剰なAI利用を制限し、制限時も再試行の増幅を防げる。
Key points
- Rate limit
- Concurrency
- Backoff
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
Rate limit
A cap on requests or processing during a defined time window.
Concurrency limit
A cap on the number of requests processed at the same time.
Question IDAWS-AIF-341
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