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 K3 is now officially available — Kimi’s most capable model to date, with a 1M-token context window and native visual understanding. It is well suited for programming agent scenarios such as Codex, Claude Code, Cline, and RooCode, as well as knowledge work and deep reasoning.

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:

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 K3; you can also choose Kimi K2.7 Code or Kimi K2.6 for specific scenarios.

Kimi K3

Kimi K3 is our flagship model for long-horizon coding and end-to-end knowledge work — 2.8 trillion parameters, a 1M-token context window, and industry-leading intelligence.

Kimi K2.7 Code

A coding-focused model with a 256K context window, text/image/video input, and thinking mode. Choose kimi-k2.7-code-highspeed when you need higher output speed.

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 you are not sure which model to choose, start with kimi-k3. If your task is mainly code generation, code editing, or programming agents and you need higher output speed, choose kimi-k2.7-code-highspeed.
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 K3 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.
The examples on this page use the latest model kimi-k3 by default. K3 uses the top-level reasoning_effort field (currently only "max"). To use another model such as kimi-k2.6 or kimi-k2.5, just replace the model field — parameter configurations differ across models. See the Model Parameter Reference.
To use the high-speed model for coding scenarios, replace kimi-k3 in the examples with kimi-k2.7-code-highspeed; to call Kimi K2.6, replace it with kimi-k2.6.
Before running the examples, prepare:
  1. Python 3.8 or later, or Node.js 18 or later.
  2. OpenAI SDK 1.0.0 or later. Kimi API is compatible with the OpenAI API format, so you can call Kimi directly with the OpenAI Python or Node.js SDK.
  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:
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. Useful for chat, code generation, and long-form text output.

Multi-turn chat

Maintain a messages list to preserve context history, letting the model remember the conversation.

Multimodal input

Kimi K3, Kimi K2.7 Code, and Kimi K2.6 all support text, image, and video input.

Tool calls

Let the model call external functions or APIs for Agent tasks, web search, and complex workflows.

JSON Mode

Force the model to output valid JSON for structured data extraction and downstream integration.

Thinking models

Use reasoning capabilities for complex tasks, multi-step tool use, and Agent workflows.

Streaming output

Multimodal input

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 K3 model

View Kimi K3 capabilities, calling examples, and best practices.

Kimi K2.7 Code model

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

Kimi K2.6 model

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

Model list

View currently available model names and descriptions.

Join the Kimi Developer Community

Ask questions, share feedback, and showcase what you are building with Kimi.