Passer au contenu principal

Kimi K2.7 Code

KimiKimiOpen WeightModified MIT License

Description

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6. It improves real-world long-horizon coding task completion, instruction following, and token efficiency while reducing thinking-token usage by approximately 30% versus Kimi K2.6. The model uses a native multimodal Mixture-of-Experts architecture with 1T total parameters, 32B activated parameters, a 256K-token context window, image and video input support, and forced thinking with preserve_thinking enabled for multi-turn coding agent workflows.

Date de sortie
2026-06-12
Paramètres
1.0T
Longueur du contexte
262K
Modalités
image, text, video

Radar de capacités

28
general
59
coding
90
reasoning
64
science
80
agents
90
multimodal

Classements

Domaine#RangScoreSource
Capacité agentique5
66.0
LS
Classement codage96
77.0
AA
Classement général110
64.0
AA
Raisonnement mathématique42
80.0
LB
Raisonnement30
83.0
LB
Science91
74.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

MCP-Mark81.1%Aut.
Kimi Code Bench v262.0%Aut.
Program Bench53.6%Aut.
Kimi Claw 24/7 Bench46.9%Aut.
MLS-Bench Lite35.1%Aut.

Code

DeepSWE 1.131.0%

Math

LiveBench71.9%

Reasoning

MCP Atlas76.0%Aut.
FrontierCode 1.130.1%

Indices d'évaluation AA

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
90.1
Gpqa(NYU + Cohere + Anthropic (2023))
89.6
Lcr(Artificial Analysis)
79.3
Terminalbench V2 1
67.4
Ifbench(Google Research (2023))
63.1
Coding Index(Artificial Analysis)
60.8
Scicode(UIUC + Argonne National Lab (2024))
47.8
Terminalbench Hard(Stanford × Laude Institute (2026))
44.7
Hle(Center for AI Safety + Scale AI (2025))
35.0
Intelligence Index(Artificial Analysis)
26.3
Tau Banking
20.2

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))
Tool Calling
80
Math
70
Reasoning
50
General
50
Agents
50
Code
50

Tarification

Prix d'entrée$0.95 / 1M tokens
Prix de sortie$4 / 1M tokens
Prix mixte (3:1)$1.712 / 1M tokens
Prix de lecture cache$0.15 / 1M tokens

Vitesse

Tokens/sec44.1
Délai du premier token1.13s
Temps de réponse51.68s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

32 fournisseurs

Moins cher: DeepInfraPlus cher: TensorX
FournisseurEntréeSortie
1DeepInfraMoins cher
$0
$0
2routing.run
$0.275
$1.1
3CrofAI
$0.55
$2.25
4Ambient
$0.69
$3.49
5OpenRouter
$0.71
$3.5
6Venice AI
$0.75
$3.5
7Cortecs
$0.75
$3.5
8ai&
$0.75
$3.5
9GreenPT
$0.9006
$4.389
10KimiPRINCIPAL
$0.95
$4
11302.AI
$0.95
$4
12NanoGPT
$0.95
$4
13OpenCode Go
$0.95
$4
14ZenMux
$0.95
$4
15NovitaAI
$0.95
$4
16Kilo Gateway
$0.95
$4
17GitHub Copilot
$0.95
$4
18OpenCode Zen
$0.95
$4
19AIHubMix
$0.95
$3.9995
20Moonshot AI (China)
$0.95
$4
21Requesty
$0.95
$4
22Vercel AI Gateway
$0.95
$4
23DevPass (LLM Gateway)
$0.95
$4
24Azure
$0.95
$4
25Moonshot AI
$0.95
$4
26Neuralwatt
$0.95
$4
27HPC-AI
$0.95
$4
28EmpirioLabs AI
$0.95
$4
29Ofox
$0.95
$4
30OpenReason
$1.0022
$4.22
31Charm Hyper
$1.03436
$4.3552
32TensorX
$1.25
$4.5

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes