AI Tools & Models HOTFeaturedAll
AWS Machine Learning BlogOfficialScore70

Four Amazon Bedrock inference choices that affect cost

Summary

Your bill can keep climbing even after prompts and app logic are tuned, because four per-request settings — max tokens, reasoning effort, service tier, and cache duration — all move the cost.

Why this matters

Official source · Covers inference and prompt

Open original ↗

Source: AWS Machine Learning Blog · aws.amazon.com

Topics

Related items