API Overview

Service Address

https://api.moonshot.ai

The base_url differs by compatible protocol; see “Protocol Compatibility” below.

Protocol Compatibility

The Kimi API is compatible with three API formats, so you can reuse the corresponding official SDKs and tools:

Compatible API	base_url	Endpoint	SDKs / Tools
OpenAI Chat Completions	`https://api.moonshot.ai/v1`	`/chat/completions`	Official OpenAI SDKs (Python / Node.js), plus third-party tools and frameworks such as LangChain, Dify, and Coze
OpenAI Responses	`https://api.moonshot.ai/v1`	`/responses`	Official OpenAI SDKs (Python / Node.js)
Anthropic Messages	`https://api.moonshot.ai/anthropic`	`/messages`	Official Anthropic SDKs, Claude Code, and similar tools

If your project already uses the official OpenAI or Anthropic APIs, simply replace base_url and the API Key with your Kimi configuration to migrate — no other code changes are needed.

When using the OpenAI-compatible endpoints, some parameters are Kimi-specific extensions: the thinking parameter needs to be passed via the SDK’s extra_body; partial is a field on assistant messages within the messages array ("partial": true), not a top-level request parameter. See Tool Use and Partial Mode for details.

Authentication

All API requests require an API Key in the HTTP header:

Authorization: Bearer $MOONSHOT_API_KEY

API Keys can be created and managed in the Kimi Open Platform Console.

Your API Key is sensitive. Do not expose it in client-side code, public repositories, or logs. Use environment variables to manage it.

When using an official SDK, pass your API Key and the protocol-specific base_url at initialization. OpenAI-compatible endpoints:

import os

from openai import OpenAI

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

const OpenAI = require("openai");

const client = new OpenAI({
    apiKey: process.env.MOONSHOT_API_KEY,
    baseURL: "https://api.moonshot.ai/v1",
});

Anthropic-compatible endpoints:

import os

from anthropic import Anthropic

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

const Anthropic = require("@anthropic-ai/sdk");

const client = new Anthropic({
    apiKey: process.env.MOONSHOT_API_KEY,
    baseURL: "https://api.moonshot.ai/anthropic",
});

Error Handling

Failed requests return a JSON error response with error.type and error.message fields. For the full list of error types, messages, and troubleshooting tips, see Errors.

API Endpoints

Endpoint	Method	Protocol	Description
`/v1/chat/completions`	POST	OpenAI	Create Chat Completion
`/v1/responses`	POST	OpenAI	Responses API
`/anthropic/v1/messages`	POST	Anthropic	Messages API
`/v1/models`	GET	OpenAI	List Models
`/v1/tokenizers/estimate-token-count`	POST	OpenAI	Estimate Tokens
`/v1/users/me/balance`	GET	OpenAI	Check Balance
`/v1/files`	POST	OpenAI	Upload File
`/v1/files`	GET	OpenAI	List Files
`/v1/files/{file_id}`	GET	OpenAI	Get File Info
`/v1/files/{file_id}`	DELETE	OpenAI	Delete File
`/v1/files/{file_id}/content`	GET	OpenAI	Get File Content
`/v1/batches`	POST	OpenAI	Create Batch
`/v1/batches`	GET	OpenAI	List Batches
`/v1/batches/{batch_id}`	GET	OpenAI	Get Batch Details
`/v1/batches/{batch_id}/cancel`	POST	OpenAI	Cancel Batch

Next Steps

Quickstart

Send your first API request

Responses API

OpenAI Responses-compatible endpoint

Messages API

Anthropic Messages-compatible endpoint

List Models

See the currently available models

Using the API

API Reference

Files

Batch API

Service Address

Protocol Compatibility

Authentication

Error Handling

API Endpoints

Next Steps

Quickstart

Responses API

Messages API

List Models

​Service Address

​Protocol Compatibility

​Authentication

​Error Handling

​API Endpoints

​Next Steps

Quickstart

Responses API

Messages API

List Models

Service Address

Protocol Compatibility

Authentication

Error Handling

API Endpoints

Next Steps