4 articles
Browse 4 articles, tool introductions and practical notes about Moonshot AI, ordered by publication date.
Kimi K3's full weights and 47-page technical report are out. We unpack its 2.8T MoE, 104B active parameters, 1M context, agent RL, deployment demands, and license limits.
Kimi K3 launches with 2.8 trillion parameters, native multimodality, a 1M-token context window, and API pricing well below GPT-5.6 Sol and Claude Fable 5. Here is what matters.
Kimi K2.5 review: Beats GPT-5.2 in vision (9/17 benchmarks), approaches Claude 4.5 in coding, exclusive Agent Swarm 4.5x faster. Full comparison vs top AI models reveals strengths & gaps.
Kimi K2 by Moonshot AI: A trillion-parameter open-source model with MuonClip optimizer, advanced data rephrasing, and efficient sparse MoE architecture. Discover the core innovations and engineering behind this SOTA AI model.