moonshotai/kimi-k2-thinkingOpen WeightsThinking Kimi model for slower research passes, planning, and hard technical questions
TECHNICAL SPECIFICATIONS
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Kimi K2 Thinking 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 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
STANDARDIZED BENCHMARKS & EVALS
API CALL INVOCATION EXAMPLE
// Example: Calling Kimi K2 Thinking 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-thinking",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
This model supports prompt caching at $0.15 / 1M tokens, saving up to 75% on repetitive MCP tool definitions and system instructions.
MODEL RESOURCES
More Models by Moonshot AI
Alternative and family models from the same lab
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code
Earlier Kimi frontier model for long-context agents, coding, and multimodal work