Skip to main content

Kimi K2.6 (Non-reasoning)

KimiKimiOpen WeightModified MIT License

Description

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.

Release Date
2026-04-20
Parameters
1.0T
Context Length
262K
Modalities
image, text, video

Capability Radar

23
general
60
coding
79
reasoning
61
science
60
agents
80
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability35
52.0
LS
Code Ranking190
68.0
AA
General Ranking194
54.0
AA
Math Reasoning44
84.0
LB
Multimodal Ranking52
57.0
LS
Reasoning43
79.0
LB
Science217
56.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

MCP-Mark55.9%SR
Toolathlon50.0%SR
Finance Agent v244.9%

Code

Claw-Eval80.9%SR
FrontierSWE27.0%

Math

AIME 202696.4%SR
MathVision93.2%SR
HMMT Feb 2692.7%SR
IMO-AnswerBench86.0%SR
LiveBench72.2%

Multimodal

OSWorld-Verified73.1%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)90.5%SR
LiveCodeBench v689.6%SR
CharXiv-R86.7%SR
BrowseCompOpenAI (2025)86.3%SR
SWE-Bench Verified80.2%SR
SWE-bench Multilingual76.7%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)66.7%SR
OJBench60.6%SR
SWE-Bench ProPrinceton NLP (2024)58.6%SR
SciCode52.2%SR
Humanity's Last Exam36.4%SR
APEX-Agents27.9%SR

Search

DeepSearchQA83.0%SR
WideSearch80.8%SR

Vision

V*96.9%SR
MMMU-Pro80.1%SR
BabyVision68.5%SR

AA Evaluation Indices

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
93.9
Gpqa(NYU + Cohere + Anthropic (2023))
78.8
Lcr(Artificial Analysis)
69.7
Ifbench(Google Research (2023))
44.3
Terminalbench Hard(Stanford × Laude Institute (2026))
37.9
Intelligence Index(Artificial Analysis)
23.6
Hle(Center for AI Safety + Scale AI (2025))
19.6

LLM Stats Category Scores

(LLM Stats (zeroeval))
Math
80
Multimodal
80
Search
80
Frontend Development
80
Vision
80
Physics
70
Reasoning
70
General
70
Biology
70
Chemistry
70
Agents
60
Code
60
Tool Calling
60
Finance
40

Pricing

Input Price$0.95 / 1M tokens
Output Price$4 / 1M tokens
Blended Price (3:1)$1.712 / 1M tokens
Cache Read Price$0.15 / 1M tokens

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

Provider Price Ranking

17 providers

Cheapest: DeepInfraMost Expensive: TensorX
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2Fireworks
$0
$0
3Novita
$0
$0
4Moonshot AI
$0
$0
5NanoGPT
$0.5
$2.6
6OpenRouter
$0.65
$3.41
7Kilo Gateway
$0.65
$3.41
8Lilac
$0.7
$3.5
9FastRouter
$0.75
$3.5
10NovitaAI
$0.8
$3.4
11KimiPRIMARY
$0.95
$4
12ZenMux
$0.95
$4
13Vercel AI Gateway
$0.95
$4
14Ambient
$0.95
$4
15Ofox
$0.95
$4
16TokenGo
$0.95
$4
17TensorX
$1
$4

Compare pricing across different API providers for this model.

External Sources