Skip to content
aicoolies logo
Kimi Code logo

Kimi Code

AI coding agent by Moonshot AI

Terminal-based AI coding agent from Moonshot AI, powered by Kimi K2.5 with a 256K context window that achieves 76.8% on SWE-Bench Verified. Reads and edits code, executes shell commands, fetches web pages, and autonomously plans multi-step development workflows through natural language. Moonshot's entry into the AI coding agent market, leveraging their strength in large-context language models.

About Kimi Code

Kimi Code is an AI-powered coding assistant developed by Moonshot AI that operates as a terminal-based agent, helping developers complete software development tasks and terminal operations through natural language interaction. Built on Moonshot's advanced Kimi K2.5 model with a 256K context window, it solves the problem of context-limited AI coding assistance by providing deep understanding of large codebases while supporting autonomous planning and execution of multi-step development workflows. Kimi Code represents Moonshot AI's entry into the competitive AI coding agent market, leveraging their strength in large-context language models.

Kimi Code CLI differentiates itself with its ability to read and edit code, execute shell commands, search and fetch web pages, and autonomously plan and adjust actions during execution, all powered by one of the highest-performing coding models available. The underlying Kimi K2.5 model achieves a 76.8% score on SWE-Bench Verified, placing it among the top-tier coding models globally. Kimi Code supports Agent Client Protocol out of the box, enabling integration with any ACP-compatible editor or IDE, and offers a dedicated VS Code extension for developers who prefer a graphical environment.

Kimi Code targets developers who want a capable, cost-effective AI coding agent with strong performance on real-world software engineering tasks, particularly those working with large codebases that require extensive context understanding. It is especially appealing to developers in the Asia-Pacific region where Moonshot AI has strong presence, and to cost-conscious teams attracted by Kimi K2.5's competitive API pricing at $0.60 per million input tokens. Kimi Code integrates with popular development tools and workflows, providing a practical alternative to Claude Code and GitHub Copilot for terminal-based AI-assisted development.

Pricing & Platform Specs

Pricing Summary

Freemium AI coding intelligence platform and API powered by Moonshot AI. Free web and mobile app tier ($0/mo) provides basic web search, code generation, and interactive assistant capabilities. Moonshot AI Developer API offers pay-as-you-go token billing across moonshot-v1 tiers (8k, 32k, 128k, up to 2M context) ranging from ¥12 to ¥60 per 1M tokens (~$0.001–$0.008/1k tokens), with a ¥15 free trial credit for new developer accounts.

full pricing breakdown →

Supported Platforms

CLI, VS Code, Cursor, Zed

Explore categories, tags & use cases

Open-source terminal AI agent by Alibaba

Open-source AI coding assistant CLI with multi-model support and subagent capabilities in the terminal.

Open Source

Open-source AI coding agent for the terminal

Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.

Open Source

Side-by-Side Comparisons

Claude Code logo
Claude Code
vs
Kimi Code logo
Kimi Code

Claude Code vs Kimi Code: Mature Agent Workflow vs Lower-Cost Kimi Flexibility

Claude Code and Kimi Code are terminal-centered coding agents that can inspect repositories, edit files, and run development commands, but they represent different buying paths. Claude Code is Anthropic’s mature first-party workflow with broad plan and organization support; Kimi Code is Moonshot AI’s newer agent, bundled with Kimi membership and compatible with several coding clients. The decision is primarily about governance and ecosystem maturity versus price, speed options, and provider flexibility.

Claude CodeKimi Code

Community experience

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is Kimi Code?

Terminal-based AI coding agent from Moonshot AI, powered by Kimi K2.5 with a 256K context window that achieves 76.8% on SWE-Bench Verified. Reads and edits code, executes shell commands, fetches web pages, and autonomously plans multi-step development workflows through natural language. Moonshot's entry into the AI coding agent market, leveraging their strength in large-context language models.

Is Kimi Code free?

Kimi Code offers a free tier alongside paid plans. Freemium AI coding intelligence platform and API powered by Moonshot AI. Free web and mobile app tier ($0/mo) provides basic web search, code generation, and interactive assistant capabilities. Moonshot AI Developer API offers pay-as-you-go token billing across moonshot-v1 tiers (8k, 32k, 128k, up to 2M context) ranging from ¥12 to ¥60 per 1M tokens (~$0.001–$0.008/1k tokens), with a ¥15 free trial credit for new developer accounts.

Is Kimi Code still maintained?

Yes — Kimi Code is active. Its listing was last verified on September 6, 2026.

What are the best Kimi Code alternatives?

The first editor-selected Kimi Code alternatives are Qwen Code, OpenCode.

How does Kimi Code score in our review?

The published editorial review lists Kimi Code at 78/100 overall across speed, privacy, and developer experience. Check the review's evidence status and test metadata for its verification level.