I don't see why I would be interested in this model, considering the price difference. They advertise that it's the same as Kimi K3 in half the tokens. But the pricing is double the pricing of K3. So why do I care if it uses fewer tokens, if I'm paying double per token?
K3 TOS says they must sell no lower than what Moonshot charges. If you have a provider selling for less than $15/mtok, they are violating TOS from Moonshot.
looks like the underlying vendor is charging correct prices <a href="https://inference.net/models/kimi-k3/" rel="nofollow">https://inference.net/models/kimi-k3/
however the listing on open router has a `/fp4` suffix, so perhaps this is an unlisted, quanted model for a lower price?
soerxpso · · focus · HN ↗
verdverm · · focus · HN ↗
tyingq · · focus · HN ↗
<a href="https://openrouter.ai/moonshotai/kimi-k3" rel="nofollow">https://openrouter.ai/moonshotai/kimi-k3
polski-g · · focus · HN ↗
verdverm · · focus · HN ↗
however the listing on open router has a `/fp4` suffix, so perhaps this is an unlisted, quanted model for a lower price?