AWS · AIP-C01
Cost optimization
AIP-C01 · Lesson 18 of 23 · 2:28:06
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AIP-C01 exam (AWS Certified Generative AI Developer - Professional). In this lesson: token efficiency with CountTokens and CloudWatch, cost-effective model selection, batch inference and the Flex tier, capacity planning and Provisioned Throughput, prompt caching, request hashing, semantic caching with ElastiCache, edge caching, and cost visibility with application inference profiles and Cost Anomaly Detection. Includes three original practice questions.
Preview the topics
- Every night, AnyCompany generates new descriptions for twenty thousand products, and nobody waits for the results. How can it cut the cost of this job most?
- Hundreds of customers ask, in slightly different words, how to track their order, and each question calls the model. What reduces these calls most?
- Finance wants AnyCompany’s Bedrock costs split by feature, for the shopping assistant, the support agent, and product content, without changing models. What should the team set up?