Skip to content

AWS blog explains four options that affect Bedrock inference costs

What happened

From the reports

Amazon Bedrock 的缓存时长、服务层级、推理强度和 maxTokens 四项请求级设置会在不改模型和提示词的情况下影响推理成本。以 Claude Sonnet 5 和 Claude Opus 5 为例,5 分钟缓存写入按输入价 1.25 倍计费、1 小时写入 2 倍、缓存读取 0.1 倍,1 小时缓存需每小时至少 3 次请求才划算。

From AWS Machine Learning Blog

Timeline

Follow the reports to see the event from each side.

Nov 13
  1. AWS Machine Learning Blog
    Four Amazon Bedrock inference choices that affect cost

    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.

Heat of this event

Current heat 3·Peak in the comparable range 9(Nov 13 07:00)·Change over 24 hours in the comparable range -49%

02.557.510Nov 1307:00Nov 1322:00Nov 1413:00Nov 1504:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.