Amazon Bedrock adds explicit prompt caching for open-weight models
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
AWS introduced explicit prompt caching for open-weight models on Amazon Bedrock, letting applications reuse stable prompt prefixes across requests to cut input costs and latency. Guidance indicates savings depend on how often the cached prefix is successfully reused.
Read the full story at AWS Machine Learning Blog ↗
Timeline · 3 reports
- 2026-11-16 15:42 · AWS Machine Learning Blog
Use prompt caching with open-weight models on Amazon Bedrock - 2026-11-16 15:42 · AWS Machine Learning Blog
Introducing explicit prompt caching with open-weight models on Amazon Bedrock - 2026-11-16 12:03 · DEV Community — AI
Amazon Bedrock Prompt Caching: When Does It Pay Off?