moonshotai logo
moonshotai

MoonshotAI: Kimi K2.6

Description de la source (anglais)

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Présentation

Caractéristiques du modèle

Contexte
262 144 tokens
Sortie maximale
235 929 tokens
Architecture
text+image->text
Tokenizer
Other
Limite des connaissances
Non indiqué
Modéré
Non
OPENROUTER

Tarification complète

Tarifs synchronisés depuis OpenRouter, par million de tokens.

Entrée
$0.95
par million de tokens
Sortie
$4
par million de tokens
Lecture du cache
$0.16
par million de tokens
API

Configuration du modèle

Raisonnement

Raisonnement obligatoire
Non
Paramètres par défaut
Oui
API

Démarrage rapide

Définissez OPENROUTER_API_KEY localement. Python nécessite requests ; JavaScript s’exécute dans Node.js. Gardez la clé côté serveur.

Documentation de l’API

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/kimi-k2.6","messages":[{"role":"user","content":"Hello!"}]}'
Capacités et modalités

EntréeSortie

Entrée
textimage
Sortie
text
Raisonnement

Oui

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Fournisseurs disponibles

21 fournisseurs

Vérifié: 7 septembre 2026

Fournisseurs en direct sur OpenRouter

Disponibilité, latence, débit et routage évoluent en continu. Consultez la source pour les données en temps réel.

OpenRouter

Inceptron

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.56
Sortie
$3.39
Lecture du cache
$0.17
Écriture du cache
Non indiqué

Chutes

int4
Contexte
262K
Sortie maximale
66K
Entrée
$0.58
Sortie
$3.4
Lecture du cache
$0.058
Écriture du cache
Non indiqué

Decart

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.5865
Sortie
$2.4696
Lecture du cache
$0.0988
Écriture du cache
Non indiqué

StreamLake

fp8
Contexte
256K
Sortie maximale
230K
Entrée
$0.5985
Sortie
$2.52
Lecture du cache
$0.1008
Écriture du cache
Non indiqué

CoreWeave

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.65
Sortie
$3.41
Lecture du cache
$0.15
Écriture du cache
Non indiqué

Crusoe

bf16
Contexte
262K
Sortie maximale
236K
Entrée
$0.7
Sortie
$3.5
Lecture du cache
$0.35
Écriture du cache
Non indiqué

DeepInfra

fp4
Contexte
262K
Sortie maximale
16K
Entrée
$0.75
Sortie
$3.5
Lecture du cache
$0.15
Écriture du cache
Non indiqué

Venice

int4
Contexte
256K
Sortie maximale
66K
Entrée
$0.75
Sortie
$3.5
Lecture du cache
$0.16
Écriture du cache
Non indiqué

Parasail

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.75
Sortie
$3.5
Lecture du cache
$0.16
Écriture du cache
Non indiqué

SiliconFlow

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.77
Sortie
$3.4
Lecture du cache
$0.14
Écriture du cache
Non indiqué

Novita

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$0.8
Sortie
$3.4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

GMICloud

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.855
Sortie
$3.6
Lecture du cache
$0.144
Écriture du cache
Non indiqué

DigitalOcean

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.19
Écriture du cache
Non indiqué

Baidu

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

AtlasCloud

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

Cloudflare

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

Moonshot AI

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

Phala

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$1.09
Sortie
$4.6
Lecture du cache
$0.37
Écriture du cache
Non indiqué

BaseTen

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

Fireworks

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué

BaseTen

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.95
Sortie
$4
Lecture du cache
$0.16
Écriture du cache
Non indiqué
moonshotai

4 modèles

Tous les modèles
moonshotai logomoonshotai

MoonshotAI: Kimi K3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Contexte
1.0M
Entrée
text · image · video
Sortie
text
Entrée: $3Sortie: $15par million de tokens
Voir la fiche du modèle
moonshotai logomoonshotai

MoonshotAI: Kimi K3 (batch)

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Contexte
1.0M
Entrée
text · image · video
Sortie
text
Entrée: $2.28Sortie: $11.4par million de tokens
Voir la fiche du modèle
moonshotai logomoonshotai

MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Contexte
262K
Entrée
text · image
Sortie
text
Entrée: $0.7062Sortie: $3.3par million de tokens
Voir la fiche du modèle
moonshotai logomoonshotai

MoonshotAI: Kimi K2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Contexte
262K
Entrée
text · image
Sortie
text
Entrée: $0.45Sortie: $2.25par million de tokens
Voir la fiche du modèle