Kimi K2.5 API - Moonshot AI's Latest Model with 200K Context

What is Kimi K2.5 API?

Kimi K2.5 is Moonshot AI's latest large language model, released in January 2025. It represents a significant leap in AI capabilities with a massive 200,000 token context window - equivalent to processing 200 novels or analyzing entire codebases in a single request.

The Kimi K2.5 API provides developers with programmatic access to this powerful model through a RESTful API compatible with OpenAI's chat completions format. Simply change your base URL to kimi-api.com/v1 and start using Kimi K2.5 at 40% of official Moonshot API pricing.

Built on Moonshot AI's proprietary transformer architecture, Kimi K2.5 excels at long-form content generation, complex reasoning tasks, multilingual understanding, and code generation. It's optimized for real-world applications requiring deep context awareness.

Kimi K2.5 API Key Features

How to Access Kimi K2.5 API

Kimi K2.5 API Pricing Comparison

Kimi K2.5 API Code Example

Python (OpenAI SDK)

from openai import OpenAI

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

response = client.chat.completions.create(
    model="moonshot-v1-128k",
    messages=[
        {"role": "system", "content": "You are Kimi, an AI assistant by Moonshot AI."},
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
    temperature=0.7,
)

print(response.choices[0].message.content)

cURL

curl https://kimi-api.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $KIMI_API_KEY" \
  -d {
    "model": "moonshot-v1-128k",
    "messages": [
      {"role": "system", "content": "You are Kimi, an AI assistant."},
      {"role": "user", "content": "Write a Python function to calculate Fibonacci numbers"}
    ],
    "temperature": 0.7
  }

Kimi K2.5 vs Competitors

How Kimi K2.5 API compares to other leading language models

Related Resources