Hacker News new | ask | show | jobs
by vblanco 9 days ago
Ive been pleasantly surprised with the quality of this model. Its really good at code review and PR review. But right now due to them being so overloaded + this being a big model, its SO slow. It takes forever to do a relatively simple code review.
2 comments
abalashov 9 days ago
Try the OpenRouter route!

https://openrouter.ai/moonshotai/kimi-k3

link
wren6991 9 days ago
Currently this is still just going to Moonshot, since they didn't release the weights yet (scheduled for 27th).
link
abalashov 9 days ago
Oh, okay. Didn't know that, as I haven't tried K3 myself -- I'm quite content with Kimi K2.7-Code for the moment, which OpenRouter serves me to via US-based inference providers. Supposedly.

Obviously, not relevant if your reason for being here is to ferret out the excitement about K3 specifically. But if this is your first time trying Kimi, try K2.6 or K2.7! If my experience is any indication, you'll be blown away by those, too.

link
kzrdude 9 days ago
Kimi K3 is on the opencode-go plan's price list now. I haven't confirmed it, but I guess that means it's available. (Not in Zen.)
link