Kimi K2.5

Kimi K2.5 is a native multimodal mixture-of-experts model with 1 trillion total parameters and 32 billion active parameters, built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It delivers state-of-the-art performance in visual coding, agentic tool use, and multi-agent orchestration — supporting both instant and thinking modes, agent swarm coordination of up to 100 sub-agents, and seamless integration of vision and language across conversational and agentic workflows.