Kimi Code Overview

What is Kimi Code

Kimi Code is an intelligent programming service for developers included in Kimi membership benefits. Built on Kimi's latest flagship models, it provides AI-assisted capabilities—such as code reading, file editing, and command execution—through product forms like CLI and VS Code extension. Subscribers can also obtain an API Key to integrate Kimi Code's model capabilities into third-party development tools and platforms.

Core Advantages

• Continuous model upgrades: Stay current with Kimi's latest flagship models and continuously gain cutting-edge code understanding, reasoning, and generation capabilities
• Standard / HighSpeed tiers: the same model at two speeds — HighSpeed delivers roughly 5–6× the output speed of Standard and switches on demand
• Broad compatibility: Seamlessly works with Kimi Code CLI, VS Code, Claude Code, and various other development tools
• Ultra-fast response: Output speed up to 100 Tokens/s
• High-frequency concurrency: Supports approximately 300–1,200 requests per 5-hour window, with up to 30 concurrent requests

Getting Started

Kimi Code allows members to use their benefits in both the official client and third-party platforms, covering different development scenarios.

Using the Official Client

Choose the client that fits you and install with one click:

For developers who prefer terminal operations. Chat with AI in the terminal, letting it read code, edit files, execute commands, search the web, and autonomously complete development tasks.

📢 CLI Upgraded

Kimi Code CLI has gone through a major version upgrade — moving from Python/uv to Node.js, bringing a simpler install experience, faster startup, and a redesigned terminal UI. The legacy version will no longer be maintained. See Version Upgrade for details and migration instructions, or refer to the legacy Python-based Kimi Code docs if needed.

# macOS / Linux
curl -fsSL https://code.kimi.com/kimi-code/install.sh | bash

# Windows (PowerShell)
irm https://code.kimi.com/kimi-code/install.ps1 | iex

After installation, run kimi in the terminal to start; on first use, log in to the Kimi Code platform with the /login command to complete the connection — no need to manually manage an API Key.

For developers who prefer the VS Code editor. Collaborate with AI in the editor sidebar, supporting code completion, file editing, web search, and automated tasks.

VS Code Plugin Compatibility Notice

Kimi Code for VS Code is currently only open for new installations to legacy Python CLI users. Existing users who upgrade to the new CLI can still continue using the plugin; new installations are not supported for TS version CLI users.

Search for "Kimi Code" in the VS Code Extensions marketplace to install, or visit Visual Studio Marketplace. After installation, complete the connection via the login button in the sidebar — no need to manually manage an API Key.

If the extension doesn't appear after installation, restart VS Code or run "Developer: Reload Window" from the Command Palette (Mac: Cmd+Shift+P, Windows/Linux: Ctrl+Shift+P).

Other editors such as JetBrains and Zed can connect via CLI's ACP protocol. See Using Kimi Code CLI in IDEs for details.

API Access

When integrating Kimi Code into third-party development tools, you need to manually configure an API Key to complete authentication.

Service Endpoint

The Kimi Code API is compatible with both OpenAI and Anthropic protocols. Different tools have different requirements for address configuration:

• Base URL: Some tools (e.g., Claude Code) only require the Base URL, and the tool will automatically append the subsequent path.
• Full Endpoint: Some tools (e.g., Trae) require the complete API request address.

Choose the corresponding address as needed:

Protocol	Base URL	Common Endpoint Example
OpenAI Compatible	https://api.kimi.com/coding/v1	https://api.kimi.com/coding/v1/chat/completions
Anthropic Compatible	https://api.kimi.com/coding/	https://api.kimi.com/coding/v1/messages

Both protocols accept two model IDs: kimi-for-coding (Standard) and kimi-for-coding-highspeed (HighSpeed).

Obtaining an API Key

Kimi members can create and manage API Keys in the Kimi Code Console (up to 5 keys; each is shown only once upon creation—please keep it safe).

Configuring in Third-Party Tools

After obtaining an API Key, configure the corresponding Base URL and API Key in the environment variables of the respective tool to start using it. For configuration details, see Using in Other Coding Agents.

Note: Please maintain the tool's real identity identifier when using. Tampering with the client identifier (User-Agent) is considered a violation and may result in suspension of membership benefits.

How to Switch Models

The HighSpeed model is now available. Kimi Code now offers two tiers—Standard and HighSpeed—built on the same model with identical coding ability, and sharing the same Base URL, API Key, and membership benefits. HighSpeed delivers roughly 5–6× the output speed of Standard, so when you want instant responses and fast iteration, a one-click switch gives you a smoother coding experience. The main differences:

Item	Standard	HighSpeed
Model ID	kimi-for-coding	kimi-for-coding-highspeed
Output speed	Baseline	~5–6× faster than Standard
Quota usage	Baseline	~3× that of Standard
Coding ability	Full	Same as Standard
Best for	Everyday coding tasks	Instant responses, fast iteration
Membership	Available to all Kimi Code members	Requires an Allegretto plan or above

Ways to switch to the target model:

• Official Kimi Code CLI: type /model in a session to switch directly between Standard and HighSpeed—no config changes needed.
• Kimi Code for VS Code: pick the target model from the dropdown menu in the input bar; if HighSpeed isn't listed yet, restart VS Code or reinstall the extension.
• Third-party tools: set the tool's Model ID to the target model; all other settings stay the same. For where to find it in each tool, see Using in Other Coding Agents.

Usage notes

• Stable model IDs: Both IDs are stable identifiers; the backend updates the model they map to as models improve, with no client config changes needed.
• Enter it exactly: The high-speed ID must be kimi-for-coding-highspeed. If mistyped or set to another value, the request silently falls back to the standard kimi-for-coding — no error, but no acceleration either.
• 401 without access: If your plan doesn't include HighSpeed access, calling it returns a 401; upgrade to Allegretto or above (see Error Reference).

Why doesn't the whole task feel 5–6× faster?

"5–6×" refers to model output speed (how fast text/code is generated). A coding task's total time is made up of "model output + tool calls (reading/writing files, running commands, web lookups, etc.) + script execution"—how long tool calls and script execution take depends on your project and commands, and HighSpeed doesn't change that part. So if the overall task doesn't feel 5–6× faster, it's usually because tool calls / script execution took up most of that turn, not because model generation slowed down.

Platform Comparison

Kimi Code membership benefits are designed specifically for programming scenarios. If you need to call large model capabilities in your own product, or require team collaboration and usage management, please visit the Kimi Platform.

Comparison Item	Kimi Code Platform	Kimi Platform
Base URL	OpenAI Compatible: https://api.kimi.com/coding/v1 Anthropic Compatible: https://api.kimi.com/coding/	https://api.moonshot.cn/v1
Billing	Membership subscription, monthly/annual payment, with rate limiting	Pay-as-you-go, top up and use
Best For	Terminal/IDE Agent programming, multi-file engineering tasks	Product integration, enterprise-level calls, multimodal application development

Next Steps

• Kimi Code CLI Quick Start – Install, log in, and start your first conversation
• Kimi Code for VS Code Quick Start – Install the extension, log in, and typical workflows
• Using in More Third-Party Tools – Claude Code, Roo Code, and more
• Membership Benefits – Quota refresh and rate limits, quota sharing, Extra Usage, and more
• FAQ – Common issues with installation, login, and usage