Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 76 discussion

Bedrock pricing is based on the number of tokens processed, which includes both input tokens (from the prompt) and output tokens (generated by the model). By decreasing the number of tokens in the prompt, you directly reduce the cost associated with each invocation of the model.

B. Decrease the number of tokens in the prompt: In a few-shot learning scenario, the number of tokens used in the prompt contributes directly to the cost, as you're billed based on the number of tokens processed during each invocation. By decreasing the number of tokens in the prompt, the company can reduce the cost per invocation while still maintaining the model's performance. This can be done by reducing the number of examples or making the examples more concise.

D. Use Provisioned Throughput To lower the monthly cost, the company can use Provisioned Throughput (PT) to scale their model's resource utilization. This allows them to pay only for the actual compute time used by the model, rather than paying a fixed monthly fee.