Moonshot AI's Kimi series. Kimi is known for handling extremely long contexts (up to 2M tokens) and strong performance on Chinese-language tasks. The K2/K3 variants are competitive with frontier models on reasoning.
chatreasoningcoding
pros
extremely long context support
strong Chinese language ability
good reasoning quality
aggressive pricing
cons
less known outside China
limited English documentation
newer — less battle-tested
use this model on surp.ivc.lol
Reference this model in a custom combo to always get the cheapest price for it: