Passer au contenu principal

Kimi K3 (max)

KimiKimiOpen WeightKimi K3 License · Usage Commercial

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.

Date de sortie
2026-07-16
Paramètres
2.8T
Longueur du contexte
1.0M
Modalités
image, text, video

Radar de capacités

57
general
74
coding
93
reasoning
72
science
70
agents
80
multimodal

Classements

Domaine#RangScoreSource
Capacité agentique9
63.0
LS
Classement codage2
98.0
AA
Classement général6
95.0
AA
Classement multimodal7
70.0
LS
Science8
93.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

AA-Briefcase1548.00 / 3000
Program Bench77.8%Aut.
DECK-Bench73.5%Aut.
Toolathlon73.2%Aut.
Kimi Code Bench v272.9%Aut.
OfficeQA Pro63.3%Aut.
Job Bench52.9%Aut.
MLS-Bench Lite48.3%Aut.
PostTrainBench36.6%Aut.
SpreadsheetBench 234.8%Aut.
AutomationBench30.8%Aut.

Code

FrontierSWE81.2%Aut.
DeepSWE 1.169.0%
DeepSWE67.5%Aut.
SWE-Marathon42.0%Aut.

Math

MathVision97.8%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)93.5%Aut.
CharXiv-R91.3%Aut.
BrowseCompOpenAI (2025)91.2%Aut.
Terminal-Bench 2.188.3%Aut.
MCP Atlas84.2%Aut.
Humanity's Last Exam56.0%Aut.
APEX-Agents37.6%Aut.

Search

DeepSearchQA95.0%Aut.

Vision

OmniDocBench91.1%Aut.
BabyVision85.7%Aut.
MMMU-Pro (with tools)83.4%Aut.
MMMU-Pro81.6%Aut.
PerceptionBench58.5%Aut.
WorldVQA51.0%Aut.
ZEROBench0.41 / 100Aut.

Indices d'évaluation AA

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
93.5
Terminalbench V2 1
85.0
Lcr(Artificial Analysis)
82.7
Coding Index(Artificial Analysis)
76.2
Intelligence Index(Artificial Analysis)
59.7
Scicode(UIUC + Argonne National Lab (2024))
58.7
Hle(Center for AI Safety + Scale AI (2025))
46.9
Tau Banking
46.0

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))
Productivity
100
Agents
92
Reasoning
78
General
60
Physics
90
Search
90
Biology
90
Chemistry
90
Math
80
Multimodal
80
Code
70
Tool Calling
70
Vision
70
Systems
40

Tarification

Prix d'entrée$3 / 1M tokens
Prix de sortie$15 / 1M tokens
Prix mixte (3:1)$6 / 1M tokens
Prix de lecture cache$0.3 / 1M tokens

Vitesse

Tokens/sec36.4
Délai du premier token3.56s
Temps de réponse58.53s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

25 fournisseurs

Moins cher: FireworksPlus cher: Tinfoil
FournisseurEntréeSortie
1FireworksMoins cher
$0
$0.00002
2Moonshot AI
$0
$0.00002
3Together
$0
$0.00002
4Novita
$0
$0.00002
5CrofAI
$2
$8
6Requesty
$2.25
$11.25
7Vancine
$2.4
$12
8DevPass (LLM Gateway)
$2.83
$14.13
9DigitalOcean
$2.85
$14.25
10KimiPRINCIPAL
$3
$15
11OpenCode Go
$3
$15
12Vivgrid
$3
$15
13GitHub Copilot
$3
$15
14OpenCode Zen
$3
$15
15AIHubMix
$3
$15
16Moonshot AI (China)
$3
$15
17Cortecs
$3
$14.999
18Neuralwatt
$3
$15
19Neon
$3
$15
20EmpirioLabs AI
$3
$15
21CoralBricks
$3
$15
22Charm Hyper
$3.2664
$16.332
23Venice AI
$3.75
$18.75
24GreenPT
$3.762
$18.81
25Tinfoil
$4
$20

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes