moonshotai logo
moonshotai

MoonshotAI: Kimi K2.6

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. $0.53 per million input tokens, $3.39 per million output tokens. 262,144 token context window, maximum output of 262,144 tokens. Higher uptime with 20 providers. Includes independent benchmarks from Artificial Analysis.

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
$0.53
/M tokens
Sortie
$3.39
/M tokens
Lecture du cache
$0.17
/M tokens
API

Configuration du modèle

Raisonnement

Modéré
Non
Paramètres par défaut
Oui
API

Démarrage rapide

Appelez ce modèle via l’API compatible OpenAI d’OpenRouter.

curl 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

20 fournisseurs

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
$0.530
Sortie
$3.39
Lecture du cache
$0.170
Écriture du cache
Non indiqué

Decart

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.537
Sortie
$2.26
Lecture du cache
$0.090
Écriture du cache
Non indiqué

Chutes

int4
Contexte
262K
Sortie maximale
66K
Entrée
$0.580
Sortie
$3.40
Lecture du cache
$0.058
Écriture du cache
Non indiqué

StreamLake

fp8
Contexte
256K
Sortie maximale
230K
Entrée
$0.598
Sortie
$2.52
Lecture du cache
$0.101
Écriture du cache
Non indiqué

CoreWeave

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.650
Sortie
$3.41
Lecture du cache
$0.150
Écriture du cache
Non indiqué

Crusoe

bf16
Contexte
262K
Sortie maximale
236K
Entrée
$0.700
Sortie
$3.50
Lecture du cache
$0.350
Écriture du cache
Non indiqué

DeepInfra

fp4
Contexte
262K
Sortie maximale
16K
Entrée
$0.750
Sortie
$3.50
Lecture du cache
$0.150
Écriture du cache
Non indiqué

Venice

int4
Contexte
256K
Sortie maximale
66K
Entrée
$0.750
Sortie
$3.50
Lecture du cache
$0.160
Écriture du cache
Non indiqué

Parasail

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.750
Sortie
$3.50
Lecture du cache
$0.160
Écriture du cache
Non indiqué

SiliconFlow

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.770
Sortie
$3.40
Lecture du cache
$0.140
Écriture du cache
Non indiqué

Novita

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.800
Sortie
$3.40
Lecture du cache
$0.160
Écriture du cache
Non indiqué

GMICloud

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.855
Sortie
$3.60
Lecture du cache
$0.144
Écriture du cache
Non indiqué

DigitalOcean

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.190
Écriture du cache
Non indiqué

Baidu

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué

Cloudflare

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué

Moonshot AI

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué

AtlasCloud

int4
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué

Phala

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$1.09
Sortie
$4.60
Lecture du cache
$0.370
Écriture du cache
Non indiqué

Fireworks

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué

BaseTen

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.950
Sortie
$4.00
Lecture du cache
$0.160
Écriture du cache
Non indiqué
moonshotai

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: $3.00Sortie: $15.00par 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: $3.00Sortie: $15.00par 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: $0.660Sortie: $3.40par 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: $0.450Sortie: $2.25par million de tokens
Voir la fiche du modèle