Bedrock open-weight models support explicit prompt caching
Understand this story
Open-weight models in Amazon Bedrock now support explicit prompt caching. Users enable the feature by setting mode to explicit via prompt_cache_options in the Chat Completions API and adding a prompt_cache_breakpoint to mark a reusable prefix. On pricing, cache reads are billed at a lower price than standard input, and savings accumulate each time the prefix is reused; however, for some models cache writes may be billed at a higher price than standard input, and content after the last breakpoint is still billed at the standard input price. Model availability and prompt caching support vary by AWS Region, and users should check the model card to confirm supported Regions.
AI overview based on source reports · Updated 4 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogIntroducing explicit prompt caching with open-weight models on Amazon Bedrock
Amazon Bedrock now supports explicit prompt caching for open-weight models, letting applications mark reusable prompt prefixes with cache breakpoints so repeated context is read from cache instead of reprocessed, reducing input costs and latency. The post demonstrates implicit and explicit caching through the Chat Completions API, shows how to read cache usage fields from each response, and applies implicit caching to an OpenCode coding agent session. It closes with best practices such as placing static content first, keeping prefixes above the model's minimum token length, and confirming cache hits via usage fields and runtime metrics.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 17 01:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.