Skip to main content
Kimi API lets you interact with Kimi models and is compatible with the OpenAI API format. Prepare an API Key, choose a model, and configure base_url to make requests through the HTTP API, Python SDK, or Node.js SDK.
Kimi K2.7 Code is now officially available. It is Kimi’s strongest coding model to date. The high-speed variant, kimi-k2.7-code-highspeed, is also available and is well suited for programming agent scenarios such as Codex, Claude Code, Cline, and RooCode.

Get started

1

Get an API Key

Visit the Kimi API Platform, sign in, then go to API Keys to create and copy an API Key.Keep your API Key secure. Do not share it with others or hard-code it directly in your application. We recommend storing it in an environment variable:
export MOONSHOT_API_KEY="YOUR_KIMI_API_KEY"

Kimi API Platform

Sign in to the platform to access the console, development workspace, and user center.

API Keys

Create, copy, and manage the keys used for API calls.
2

Choose a model

For a quickstart, we recommend starting with Kimi K2.7 Code or Kimi K2.6.

Kimi K2.7 Code

Kimi’s strongest coding model, with a 256K context window, text/image/video input, and thinking mode. For programming agents, long-running coding tasks, and software engineering workflows, start with kimi-k2.7-code-highspeed.

Kimi K2.6

A powerful general-purpose model with a 256K context window, text/image/video input, and both thinking and non-thinking modes. Use it for general chat, agent tasks, visual understanding, and complex reasoning.
If your task is mainly code generation, code editing, or programming agents, choose kimi-k2.7-code-highspeed first. If your task is more focused on general chat, multimodal understanding, or switching between thinking and non-thinking modes, choose kimi-k2.6.
3

Choose an integration method

Kimi API is compatible with the OpenAI API format, so you can choose the integration method that best fits your technology stack.

HTTP API

A standard REST API for any language or custom server-side integration.

OpenAI Python SDK

Use the OpenAI Python SDK to call Kimi from scripts, backend services, data workflows, and prototypes.

OpenAI Node.js SDK

Use the OpenAI Node.js SDK for web services, frontend engineering workflows, and Node.js applications.

Playground

Test prompts, model behavior, and business examples without writing code.
4

Make your first call

The following examples use the Kimi K2.7 Code model. Replace MOONSHOT_API_KEY with the API Key you created on the platform, or set an environment variable with the same name before running the examples.
To use the faster high-speed variant, replace kimi-k2.7-code in the examples with kimi-k2.7-code-highspeed. To call Kimi K2.6, replace it with kimi-k2.6.
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MOONSHOT_API_KEY"],
    base_url="https://api.moonshot.ai/v1",
)

completion = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[
        {"role": "system", "content": "You are Kimi, an AI assistant provided by Moonshot AI. You are especially good at conversations in Chinese and English. You provide users with safe, helpful, and accurate answers. You also refuse to answer any questions involving terrorism, racism, pornography, violence, or similar harmful content. Moonshot AI is a proper noun and must not be translated into other languages."},
        {"role": "user", "content": "Hi, my name is Li Lei. What is 1+1?"}
    ]
)

print(completion.choices[0].message.content)
When running the examples with the OpenAI SDK, make sure you are using Python 3.7.1 or later, Node.js 18 or later, and OpenAI SDK version 1.0.0 or later.To run the code successfully, you may need:
  1. A Python or Node.js environment. We recommend Python 3.8 or later.
  2. The OpenAI SDK. Kimi API is compatible with the OpenAI API format, so you can call Kimi directly with the OpenAI Python or Node.js SDK.
    pip install --upgrade 'openai>=1.0' # Python
    npm install openai@latest # Node.js
    
  3. An API Key. Create an API Key in the Kimi API Platform, then pass it to the OpenAI Client so the platform can identify your account.
If the code runs successfully without errors, you will see output similar to:
Hello, Li Lei! 1+1 equals 2. This is a basic arithmetic question. If you have any other questions or need help, feel free to let me know.
Note: Because Kimi models are nondeterministic, the actual response may not exactly match the example above.

Explore more features

Streaming output

Enable stream to receive tokens as they are generated. This is useful for chat, code generation, and long-form text generation.

Multimodal input

Both Kimi K2.7 Code and Kimi K2.6 support text, image, and video input.

Thinking models

Use thinking capabilities for complex reasoning, multi-step tool use, and agent tasks.

Streaming output

{
  "model": "kimi-k2.7-code-highspeed",
  "messages": [
    {
      "role": "user",
      "content": "Please explain what recursion is and give a Python example."
    }
  ],
  "stream": true
}

Multimodal input

{
  "model": "kimi-k2.6",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,..."
          }
        },
        {
          "type": "text",
          "text": "Please describe this image."
        }
      ]
    }
  ]
}
For larger videos, or images and videos that need to be referenced multiple times, we recommend using file uploads. Images should be no larger than 4K resolution, and videos should be no larger than 1080p.

Kimi K2.7 Code model

View Kimi K2.7 Code capabilities, calling examples, and best practices.

Kimi K2.6 multimodal model

View Kimi K2.6 capabilities, image/video understanding examples, and tool calling guidance.

Model list

View currently available model names and descriptions.

Playground

Try Kimi model capabilities interactively in the browser.