MoonshotAI: Kimi K2

由 Moonshotai 提供

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

支持流式输出最大 63K tokens

模型特性

输入模态

  • text

模型参数

最大 Tokens:63K
默认温度:0.7
流式输出:支持

定价信息

积分定价

文本输入:0 积分
图片输入:0 积分
消息输出:0 积分

API 定价

输入价格:$0.140/1K tokens
输出价格:$2.490/1K tokens

使用示例

API 调用示例
curl -X POST "https://chat.chatsking.com/api/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kimi-k2",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "max_tokens": 1000,
    "temperature": 0.7
  }'