Kimi API Code Integration — Quickstart Examples 2026

from openai import OpenAI
import os

# Initialize client with Kimi API
client = OpenAI(
    api_key=os.environ.get("KIMI_API_KEY"),
    base_url="https://api.moonshot.cn/v1"
)

# Make a chat completion request
response = client.chat.completions.create(
    model="kimi-k2-5",  # or "kimi-k2" for lower cost
    messages=[
        {
            "role": "system",
            "content": "You are a helpful coding assistant."
        },
        {
            "role": "user",
            "content": "Write a Python function to merge two sorted arrays."
        }
    ],
    temperature=0.3,
    max_tokens=2048
)

print(response.choices[0].message.content)
print(f"Tokens used: {response.usage.total_tokens}")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.KIMI_API_KEY,
  baseURL: 'https://api.moonshot.cn/v1'
});

async function chat(userMessage) {
  const response = await client.chat.completions.create({
    model: 'kimi-k2-5',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: userMessage }
    ],
    temperature: 0.7,
    max_tokens: 2048
  });

  return response.choices[0].message.content;
}

// Usage
const answer = await chat('Explain async/await in JavaScript');
console.log(answer);

curl https://api.moonshot.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $KIMI_API_KEY" \
  -d '{
    "model": "kimi-k2-5",
    "messages": [
      {"role": "user", "content": "Hello, Kimi!"}
    ],
    "temperature": 0.7
  }'

stream = client.chat.completions.create(
    model="kimi-k2-5",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)