Question

A media company runs a production summarization service on Amazon Bedrock with a predictable, sustained baseline of roughly 40 requests per second, 24 hours a day, using a single foundation model. They have measured this steady load for six months and expect it to continue. Currently they use on-demand invocation and are frequently throttled during peaks, and their monthly bill is high. The team wants to guarantee capacity for the baseline while minimizing cost over the next year. Which approach best meets these goals?

Accepted Answer

Purchase Provisioned Throughput with a 6-month commitment term sized to the sustained baseline, and route occasional peak overflow to on-demand.

Answer

Purchase Provisioned Throughput with a 1-month no-commitment term and renew it each month to preserve flexibility.

Answer

Stay entirely on on-demand and file a service quota increase to raise the requests-per-minute limit for the model.

Answer

Switch the workload to Bedrock batch inference to avoid throttling and reduce per-token costs.