Kimi K2 Instruct

Moonshot AIMCP Tool Call

moonshotai/kimi-k2-instructOpen Weights

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

Benchmark Pricing$0.40 / 1M in$1.80 / 1M out$0.20 cache read

Context: 131,072 tokens•Max Output: 32,768 tokens•Released: 2025-07-11

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output32,76832.8K tokens

LicenseModified MITSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Kimi K2 Instruct natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Kimi K2 Instruct via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MOONSHOTAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "moonshotai/kimi-k2-instruct",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);