Bedrock + ML cost
Identify ML/Bedrock cost patterns.
5 lessons.
Read in order, or jump to what you need.
The ML cost landscape
By the end of this lesson, you will be able to map ML/Bedrock cost surface to specific optimization levers, identify the major cost drivers, and recognize which Bedrock rule applies to each pattern.
Bedrock rules RC-1601..1610
By the end of this lesson, you will be able to apply the 10 Bedrock rules, prioritize by impact , and execute customer-side remediation.
Model selection trade-offs
By the end of this lesson, you will be able to pick the right model for a workload, trade off cost vs capability, and execute a mixed-routing pattern.
Batch processing for cost reduction
By the end of this lesson, you will be able to convert real-time inference to batch when latency permits, calculate the ~50% savings, and combine batch with model selection for compounding savings.
Provisioned throughput optimization
By the end of this lesson, you will be able to decide between on-demand and provisioned throughput, right-size provisioned capacity, and schedule provisioned throughput for time-aware optimization.