Kimi K3 (Max)
KimiKimiOpen WeightKimi K3 License · Commercial OK
Description
Kimi K3 is Moonshot AI's flagship open Mixture-of-Experts model for long-horizon coding, knowledge work, and reasoning. It has 2.8 trillion total parameters, activates 16 of 896 experts, and combines Kimi Delta Attention, Attention Residuals, and Stable LatentMoE. The model supports a 1M-token context window, native image and video understanding, tool calling, structured output, and always-on reasoning with max thinking effort at launch.
Release Date
2026-07-16
Parameters
2.8T
Context Length
1.0M
Modalities
image, text, video
Capability Radar
44
general
74
coding
93
reasoning
72
science
70
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 42 | 52.0 | LS |
| Code Ranking | 8 | 95.0 | AA |
| General Ranking | 31 | 74.0 | AA |
| Math Reasoning | 47 | 84.0 | LB |
| Multimodal Ranking | 13 | 67.0 | LS |
| Reasoning | 11 | 91.0 | LB |
| Science | 12 | 87.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
AA-Briefcase
1548.00 / 3000
Program Bench
77.8%SR
DECK-Bench
73.5%SR
Toolathlon
73.2%SR
Kimi Code Bench v2
72.9%SR
OfficeQA Pro
63.3%SR
Job Bench
52.9%SR
MLS-Bench Lite
48.3%SR
PostTrainBench
36.6%SR
SpreadsheetBench 2
34.8%SR
AutomationBench
30.8%SR
Code
FrontierSWE
81.2%SR
DeepSWE 1.1
69.0%
DeepSWE
67.5%SR
SWE-Marathon
42.0%SR
Math
MathVision
97.8%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
93.5%SR
CharXiv-R
91.3%SR
BrowseCompOpenAI (2025)
91.2%SR
Terminal-Bench 2.1
88.3%SR
MCP Atlas
84.2%SR
Humanity's Last Exam
56.0%SR
APEX-Agents
37.6%SR
Search
DeepSearchQA
95.0%SR
Vision
OmniDocBench
91.1%SR
BabyVision
85.7%SR
MMMU-Pro (with tools)
83.4%SR
MMMU-Pro
81.6%SR
PerceptionBench
58.5%SR
WorldVQA
51.0%SR
ZEROBench
0.41 / 100SR
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))93.5
Lcr(Artificial Analysis)88.7
Terminalbench V2 185.0
Coding Index(Artificial Analysis)76.2
Scicode(UIUC + Argonne National Lab (2024))59.5
Hle(Center for AI Safety + Scale AI (2025))46.9
Tau Banking46.0
Intelligence Index(Artificial Analysis)43.6
Terminalbench V4 012.6
LLM Stats Category Scores
(LLM Stats (zeroeval))Productivity100
Agents92
Reasoning78
General60
Physics90
Search90
Biology90
Chemistry90
Math80
Multimodal80
Code70
Tool Calling70
Vision70
Systems40
Pricing
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$6 / 1M tokens
Cache Read Price$0.21 / 1M tokens
Speed
Tokens/sec38.7
Time to First Token2.54s
Time to Answer54.22s
Provider Price Ranking
Provider Price Ranking
34 providers
Cheapest: DeepInfraMost Expensive: Tinfoil
ProviderInputOutput
1DeepInfraCheapest
$0
$0.00001
2Fireworks
$0
$0.00002
3Together
$0
$0.00002
4Moonshot AI
$0
$0.00002
5Novita
$0
$0.00002
6Kenari
$0.85714
$8.57143
7engy
$1.95
$9.75
8Boundless
$2.3
$11.4
9Vancine
$2.4
$12
10Alibaba (China)
$2.827
$14.133
11Moonshot AI (China)
$2.9879
$14.9395
12KimiPRIMARY
$3
$15
13302.AI
$3
$15
14Alibaba
$3
$15
15Moark
$3
$15
16OpenCode Go
$3
$15
17Vivgrid
$3
$15
18GitHub Copilot
$3
$15
19OpenCode
$3
$15
20Ollama Cloud
$3
$15
21AIHubMix
$3
$15
22Requesty
$3
$15
23DigitalOcean
$3
$15
24Cortecs
$3
$14.999
25DevPass (LLM Gateway)
$3
$15
26Neuralwatt
$3
$15
27Neon
$3
$15
28EmpirioLabs AI
$3
$15
29Opper
$3
$15
30Melious
$3.19628
$15.98138
31Charm Hyper
$3.2664
$16.332
32Venice AI
$3.75
$18.75
33GreenPT
$3.762
$18.81
34Tinfoil
$4
$20
Compare pricing across different API providers for this model.