Chat Models
Kimi
Kimi K2.6
Best Overall
General-purpose model for stable long-horizon coding, instruction following, and self-correction.
Long horizonSelf-correction
Same provider
More from Kimi
Kimi
Kimi K3
Flagship model for long-horizon coding and end-to-end knowledge work with 1M context.
Kimi
Kimi K2.7 Code
Coding-focused model with high success rates in long contexts and a 256K window.
Kimi
Kimi K2.7 Code HighSpeed
Same model as K2.7 Code at roughly 180 tokens per second, reaching 260 in short contexts.
Kimi
Kimi K2.5
Previous-generation flagship with Agent Swarm, 1T MoE, and 128K context.