Kimi K2.6 (Non-reasoning)
KimiKimi开源权重Modified MIT License
描述
Kimi K2.6 is Moonshot AI's open-source, native multimodal agentic model focused on state-of-the-art coding, long-horizon execution, and agent swarm capabilities. It scales horizontally to 300 sub-agents executing 4,000 coordinated steps, dynamically decomposing tasks into parallel, domain-specialized subtasks. K2.6 unifies text, image, and video input with thinking and non-thinking modes, supports a 256K context, and powers proactive 24/7 background agents that manage schedules, execute code, and orchestrate cross-platform operations without human oversight.
发布日期
2026-04-20
参数规模
1.0T
上下文长度
262K
支持模态
image, text, video
能力雷达图
70
general
60
coding
80
reasoning
60
science估算
60
agents
80
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
MCP-Mark
55.9%自报
Toolathlon
50.0%自报
Finance Agent v2
44.9%
Code
Claw-Eval
80.9%自报
FrontierSWE
27.0%
Math
AIME 2026
96.4%自报
MathVision
93.2%自报
HMMT Feb 26
92.7%自报
IMO-AnswerBench
86.0%自报
LiveBench
72.2%
Multimodal
OSWorld-Verified
73.1%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
90.5%自报
LiveCodeBench v6
89.6%自报
CharXiv-R
86.7%自报
BrowseCompOpenAI (2025)
86.3%自报
SWE-Bench Verified
80.2%自报
SWE-bench Multilingual
76.7%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
66.7%自报
OJBench
60.6%自报
SWE-Bench ProPrinceton NLP (2024)
58.6%自报
SciCode
52.2%自报
Humanity's Last Exam
36.4%自报
APEX-Agents
27.9%自报
Search
DeepSearchQA
83.0%自报
WideSearch
80.8%自报
Vision
V*
96.9%自报
MMMU-Pro
80.1%自报
BabyVision
68.5%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Math80
Multimodal80
Search80
Frontend Development80
Vision80
Physics70
Reasoning70
General70
Biology70
Chemistry70
Agents60
Code60
Tool Calling60
Finance40
定价
输入价格$0.95 / 1M tokens
输出价格$4 / 1M tokens
混合价格(3:1)$1.4375 / 1M tokens
缓存读取价格$0.15 / 1M tokens
速度
Tokens/秒40.4
首Token延迟2.87s
首回答延迟2.87s
供应商价格排行
供应商价格排行
18 个供应商
最便宜: NanoGPT最贵: Phala
供应商输入输出
1NanoGPT最便宜
$0.5
$2.6
2OpenRouter
$0.65
$3.41
3Kilo Gateway
$0.65
$3.41
4DeepInfra
$0.75
$3.5
5FastRouter
$0.75
$3.5
6Novita AI
$0.8
$3.4
7NEAR AI Cloud
$0.81
$3.85
8IteraCompute
$0.87
$3.51
9Kimi主要
$0.95
$4
10Novita
$0.95
$4
11Fireworks
$0.95
$4
12Moonshot AI
$0.95
$4
13ZenMux
$0.95
$4
14Vercel AI Gateway
$0.95
$4
15Ofox
$0.95
$4
16TokenGo
$0.95
$4
17TensorX
$1
$4
18Phala
$1.09
$4.6
比较该模型在不同 API 供应商之间的定价。