Skip to content

Kimi K2 Thinking

by Moonshot AIRank #367Score 40.0

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

性能概览

评分
40.0
排名
#367
24小时变化
0
7天变化
0
状态
stable
置信度
high

信号评分

信号标准化权重贡献新鲜度
Capabilities
capability
66.730%20.02026-11-07T03:34:36.833Z
Pricing
pricing_tier
97.525%24.42026-11-07T03:34:36.833Z
Context Window
context_window
86.015%12.92026-11-07T03:34:36.833Z
Recency
recency
66.315%9.92026-11-07T03:34:36.833Z
Output Capacity
output_capacity
79.815%12.02026-11-07T03:34:36.833Z

主要驱动因素

positive
Pricing
$2.50/M output tokens
$2.50
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 98K output tokens per request
98K

功能

功能支持
视觉否
推理是
JSON模式是
流式输出是
函数调用是
网页搜索否

价格

输入/百万令牌
$0.60
输出/百万令牌
$2.50
上下文窗口
262K
最大输出
98K

相关模型

相关

Kimi K2 Thinking Tracker - Performance History | LM Market Cap