Kimi K2.5 is available via API at $0.60/1M input tokens — 25x cheaper than Claude Opus. Here’s how to set it up.

Update (April 21, 2026): Kimi K2.6 is now available on the same API endpoints. Just change the model name to kimi-k2.6. Same pricing, same OpenAI-compatible format. K2.6 adds preserve_thinking mode for multi-turn agent loops.

Get your API key

Sign up at kimi.com or platform.moonshot.cn and generate an API key.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.moonshot.cn/v1",
    api_key="your-kimi-api-key"
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "system", "content": "You are a senior developer."},
        {"role": "user", "content": "Write a rate limiter in Go"}
    ],
    temperature=0.3,
    max_tokens=4096
)
print(response.choices[0].message.content)

JavaScript/TypeScript

import OpenAI from 'openai';
const client = new OpenAI({
  baseURL: 'https://api.moonshot.cn/v1',
  apiKey: 'your-kimi-api-key',
});

const response = await client.chat.completions.create({
  model: 'kimi-k2.5',
  messages: [{ role: 'user', content: 'Refactor this to use async/await' }],
});

Via OpenRouter

If you prefer OpenRouter (one key for all models):

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="your-openrouter-key"
)
response = client.chat.completions.create(
    model="moonshot/kimi-k2.5",
    messages=[{"role": "user", "content": "Hello"}]
)

With coding tools

# Aider
aider --model moonshot/kimi-k2.5 --openai-api-base https://api.moonshot.cn/v1

# Claude Code (Anthropic-compatible endpoint)
export ANTHROPIC_BASE_URL="https://api.moonshot.cn/v1"
export ANTHROPIC_API_KEY="your-kimi-key"
claude

Pricing

Model	Input	Output
Kimi K2.5	$0.60/1M	$2.50/1M
Kimi K2.5 (thinking)	$0.60/1M	$2.50/1M

Compare: Claude Opus is $15/$75, GPT-5.4 is $10/$30. Kimi is 10-25x cheaper.

Related: Kimi K2.5 Complete Guide · Kimi CLI Complete Guide · Best Free AI APIs 2026 · How To Use Qwen 3 6 Api