返回首页
AWS ML Blog··官方实验室

Four Amazon Bedrock inference choices that affect cost

中文摘要

Amazon Bedrock 的四种推理设置(缓存时长、服务层级、推理强度和 maxTokens)通过影响 Token 处理量和费率来改变成本。

English Summary

Four Amazon Bedrock settings—cache duration, service tier, reasoning effort, and maxTokens—impact costs by influencing token processing volume and applied rates.

原文节选

Your Amazon Bedrock inference bill can keep climbing even after you tune prompts and application logic. Four request-level choices (cache duration, service tier, reasoning effort, and maxTokens) change how many tokens the service processes and the rate applied. We show how we tested each and how to verify the effect.