alt Hacker NewsWhy does everyone avoid publishing the most important part of the pricing while doing a comparison?
My coding sessions have a >97% input cache rate. DeepSeek got us spoiled. I am not going to use any AI provider with exorbitant or hidden cache rates.
Replies
pkaye • today at 5:01 AM
I know Claude Code now has /usage to see cache hit rate. I usually have >97% also.
makayis • today at 9:04 AM
[flagged]
esafak • yesterday at 2:51 PM
Look at the Intelligence Index vs. Cost per Task. Mistral 4 is not competitive. https://artificialanalysis.ai/#intelligence-efficiency-tabs
➕ show 2 replies
Rodmine • today at 7:34 AM
At this point, are you using Deepseek flash 4.1 or is somebody else paying for your model usage unconstrained or are you a moron?
➕ show 1 reply
They did, I just didn't include it: $0.07 cached input / M
So 10x-20x vs Deepseek v4.1 Flash and I don't have on hand how efficient Mistral is regarding cache hits, etc.
On the other hand, could be some decent competition lowering pricing if the models general performance warrants broad hosting.