moonshotai/Kimi-K3.1-Pro: Open-weight natively multimodal agentic model with a 1M-token context window

huggingface.co7 min read

Moonshot AI has released Kimi K3.1 Pro, an open-weight, natively multimodal agentic model featuring 2.8 trillion total parameters and a 1-million-token context window. Post-trained with large-scale joint reinforcement learning across hundreds of domains, the Mixture-of-Experts model delivers improved performance in coding, 3D creation, financial research, and factual accuracy. The model is available via the Kimi platform with an OpenAI- and Anthropic-compatible API. Open article →

More on this topic