Question

A media company runs two distinct Bedrock workloads. Workload 1 generates SEO metadata for a backlog of 4 million archived articles that must all complete within 48 hours, with no user waiting on individual results. Workload 2 is an interactive editorial assistant where writers expect responses within a couple of seconds. The team wants to minimize total cost across both workloads while meeting each workload's requirements. Which combination of Bedrock inference approaches should they adopt?

Accepted Answer

Use Bedrock batch inference for Workload 1 and on-demand (streaming) InvokeModel for Workload 2.

Answer

Use on-demand InvokeModel for both workloads and request a service quota increase to handle Workload 1's volume.

Answer

Use Provisioned Throughput with a 6-month commitment for both workloads to guarantee capacity.

Answer

Use Bedrock batch inference for both workloads and poll for Workload 2 results every few seconds.