← all releases
Moonshot AI·Jun 12, 2026·v2.7·paid
Kimi K2.7 Code
Kimi K2.7 Code is Moonshot AI's most advanced coding model, designed to handle long-horizon coding tasks with enhanced reliability across various programming languages and scenarios. It offers ultra-long context support and robust reasoning capabilities, excelling in complex problem-solving tasks.
AI AgentsAgentic AILLMsML
overview
Kimi K2.7 Code is Moonshot AI's most advanced coding model, designed to handle long-horizon coding tasks with enhanced reliability across various programming languages and scenarios. It offers ultra-long context support and robust reasoning capabilities, excelling in complex problem-solving tasks.
key features
- 01Long-horizon coding capability breakthrough
- 02Ultra-long context support with 256K context window
- 03Strong reasoning capabilities supporting multi-step tool invocation
related productsbrowse all →
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.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.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.