AIF-C01 · Question #212
A company has created a custom model by fine-tuning an existing large language model (LLM) from Amazon Bedrock. The company wants to deploy the model to production and use the model to handle a…
The correct answer is D. Purchase Provisioned Throughput for the model on Amazon Bedrock. Provisioned Throughput is priced lower per request when you have a predictable, steady volume of calls. By committing to a fixed throughput level, you secure the necessary capacity at a reduced unit cost compared to on-demand, making it the most cost-effective choice for steady-
Question
A company has created a custom model by fine-tuning an existing large language model (LLM) from Amazon Bedrock. The company wants to deploy the model to production and use the model to handle a steady rate of requests each minute. Which solution meets these requirements MOST cost-effectively?
Options
- ADeploy the model by using an Amazon EC2 compute optimized instance.
- BUse the model with on-demand throughput on Amazon Bedrock.
- CStore the model in Amazon S3 and host the model by using AWS Lambda.
- DPurchase Provisioned Throughput for the model on Amazon Bedrock.
How the community answered
(49 responses)- A6% (3)
- B31% (15)
- C16% (8)
- D47% (23)
Explanation
Provisioned Throughput is priced lower per request when you have a predictable, steady volume of calls. By committing to a fixed throughput level, you secure the necessary capacity at a reduced unit cost compared to on-demand, making it the most cost-effective choice for steady-
Topics
Community Discussion
No community discussion yet for this question.