← all releases
Moonshot AI·Jan 27, 2026·Kimi K2.5·open source
Kimi K2.5
Kimi K2.5 is an advanced open-source visual agentic intelligence model developed by Moonshot AI. It integrates a large Mixture of Experts (MoE) language backbone with a native vision encoder and a parallel multi-agent system called Agent Swarm, enabling efficient execution of complex tasks through coordinated sub-agents.
LLMsAgentic AIAI Agents
overview
Kimi K2.5 is an advanced open-source visual agentic intelligence model developed by Moonshot AI. It integrates a large Mixture of Experts (MoE) language backbone with a native vision encoder and a parallel multi-agent system called Agent Swarm, enabling efficient execution of complex tasks through coordinated sub-agents.
key features
- 01Native multimodal training on 15 trillion mixed visual and text tokens
- 02Agent Swarm system capable of managing up to 100 sub-agents executing 1,500 coordinated steps
- 03Strong performance in coding, multimodal reasoning, and deep web research benchmarks
related productsbrowse all →
llmockopen sourcellmock is a deterministic mock LLM server designed for testing purposes. It provides a real HTTP server with authentic SSE streams, allowing developers to simulate interactions with various LLM APIs like OpenAI, Claude, and Gemini without incurring costs or dealing with non-deterministic results.AIBuildAIopen sourceAIBuildAI is an AI agent that autonomously constructs AI models. Given a specific task, it initiates an agent loop to analyze the problem, design models, and execute training processes, all without human intervention.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.