Skip to content

Kimi K2 Thinking

by Moonshot AIRank #222Score 53.3

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
53.3
排名
#222
24小时变化
0
7天变化
-64
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
66.720%13.32026-08-08T13:39:50.253Z
Benchmarks
benchmark
50.730%15.22026-08-08T13:39:50.253Z
Pricing
pricing_tier
97.515%14.62026-08-08T13:39:50.253Z
Context Window
context_window
86.010%8.62026-08-08T13:39:50.253Z
Recency
recency
82.715%12.42026-08-08T13:39:50.253Z
Output Capacity
output_capacity
83.110%8.32026-08-08T13:39:50.253Z

主要驱动因素

neutral
Benchmarks
positive
Pricing
$2.50/M output tokens
$2.50
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
9mo ago

功能

功能支持
视觉
推理
JSON模式
流式输出
函数调用
网页搜索

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
100K

相关模型

相关

Kimi K2 Thinking Tracker - Performance History | LM Market Cap