News for hackers. Stuff that matters.

A comment on Tencent Hy4. Parent comment

Re:Tencent Hy4 by joshheitzman on Wednesday November 04, 2026 @01:43PM (#50369792)
It highly depends on the task. So far, on the tasks I personally benchmark, DS v4.1 Flash @ deepinfra.com is always cheaper because their cached input price for it is so very low and their cache hit rate is so very high.
[ Parent | on HN ]
Re:Tencent Hy4 by nextaccountic on Thursday November 05, 2026 @04:12PM (#50384510)
do you generally favor deepinfra or you are mentioning them because it's 50% off on openrouter?

I really want to see some comparison on deepseek 4.1 flash 1017 providers, like, what's more trustworthy to not quantize without disclosing it, etc

also I can't find the official DeepSeek provider on openrouter https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017

[ Parent | on HN ]
Re:Tencent Hy4 by joshheitzman on Saturday November 07, 2026 @01:17PM (#50406701)
I use deepinfra directly. They have had a deep discount listed on their site for as long as I've been using them for that model and for v4.0 before that. I've used the DS v4.x Flash model from a number of provides and the inference quality at deepinfra seems to be as good as anyones.
[ Parent | on HN ]