iCreatAI News
Skip to content
Trending storyUpdating

ArisGlobal adjusts Bedrock prompt caching order to reduce costs

1 reports1 sources9 hr agoUpdated

Understand this story

AI overview

ArisGlobal adjusted the prompt caching order for its life sciences AI engine NavaX on Amazon Bedrock: it caches the shared prompt prefix rather than individual source documents, and sends that prefix first, followed by an explicit cache checkpoint. ArisGlobal says this approach lowers effective input costs and supports adding more tenants without cost growing proportionally. Under Bedrock's rules, the cache is valid for 5 minutes by default; some models can extend this to 1 hour by setting "ttl": "1h". For Claude Sonnet 4.5, for example, the minimum number of tokens for caching is 1,024, and model availability varies by region.

AI overview based on source reports · Updated 8 hr ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. AWS Machine Learning Blog
    How ArisGlobal scaled generative AI inference on Amazon Bedrock

    ArisGlobal's NavaX AI engine on Amazon Bedrock reversed its prompt order to cache the shared prompt prefix instead of the per-case document, after the shared prefix grew about 150% over six months and per-case inference costs rose more than 200%. According to ArisGlobal's production metrics, 65% of input tokens are now served from cache, cutting effective input cost by roughly 50% and overall monthly inference spend by about 40% at more than 19 billion tokens per month, while EU cross-Region inference routing stayed unchanged.

Activity for this story

Current comparable activity
8
Peak comparable activity
10Nov 18 01:00
Change in the past 24 hours
–

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.