moonshotai logo
moonshotai

MoonshotAI: Kimi K3.1 Pro

Description de la source (anglais)

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

Présentation

Caractéristiques du modèle

Contexte
1 048 576 tokens
Sortie maximale
943 718 tokens
Architecture
text+image+video->text
Tokenizer
Other
Limite des connaissances
Non indiqué
Modéré
Non
OPENROUTER

Tarification complète

Tarifs synchronisés depuis OpenRouter, par million de tokens.

Entrée
$0.253
par million de tokens
Sortie
$8.8
par million de tokens
Lecture du cache
$0.18
par million de tokens
API

Configuration du modèle

Paramètres par défaut

top_p
0.95

Raisonnement

Raisonnement obligatoire
Non
Paramètres par défaut
max
Capacités et modalités
max, high, low, none
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-k3.1-pro","messages":[{"role":"user","content":"Hello!"}]}'
Capacités et modalités

Entrée → Sortie

Entrée
textimagevideo
Sortie
text
Raisonnement

Oui · max · high · low · none

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Fournisseurs disponibles

27 fournisseurs

Vérifié: 19 novembre 2026

Fournisseurs en direct sur OpenRouter

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

OpenRouter

Relace

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.2403
Sortie
$8.4023
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Wafer

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.253
Sortie
$8.8
Lecture du cache
$0.18
Écriture du cache
Non indiqué

Morph

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.901
Sortie
$13.513
Lecture du cache
$0.286
Écriture du cache
Non indiqué

Sail Research

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.0425
Sortie
$9.35
Lecture du cache
$0.187
Écriture du cache
Non indiqué

Decart

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.2
Sortie
$6
Lecture du cache
$0.12
Écriture du cache
Non indiqué

Sail Research

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.4025
Sortie
$9.35
Lecture du cache
$0.187
Écriture du cache
Non indiqué

AkashML

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.75
Sortie
$10
Lecture du cache
$0.18
Écriture du cache
Non indiqué

Wafer

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.8
Sortie
$9
Lecture du cache
$0.18
Écriture du cache
Non indiqué

InferenceNet

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.8
Sortie
$9
Lecture du cache
$0.189
Écriture du cache
Non indiqué

InferenceNet

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.8
Sortie
$9
Lecture du cache
$0.189
Écriture du cache
Non indiqué

DeepInfra

bf16
Contexte
1.0M
Sortie maximale
944K
Entrée
$1.9
Sortie
$9.5
Lecture du cache
$0.19
Écriture du cache
Non indiqué

Makora

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$9.49
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Nebius

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

River

Non indiqué
Contexte
1.0M
Sortie maximale
1.0M
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Fireworks

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

PrimaLabs

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

DigitalOcean

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Parasail

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Alibaba

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Modal

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Together

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Moonshot AI

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2
Sortie
$10
Lecture du cache
$0.2
Écriture du cache
Non indiqué

InferenceNet

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2.7
Sortie
$13.5
Lecture du cache
$0.27
Écriture du cache
Non indiqué

InferenceNet

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$2.7
Sortie
$13.5
Lecture du cache
$0.27
Écriture du cache
Non indiqué

Amazon Bedrock

Non indiqué
Contexte
1.0M
Sortie maximale
128K
Entrée
$4
Sortie
$20
Lecture du cache
$0.2
Écriture du cache
$5

Moonshot AI

mxfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$4
Sortie
$20
Lecture du cache
$0.2
Écriture du cache
Non indiqué

Amazon Bedrock

Non indiqué
Contexte
1.0M
Sortie maximale
128K
Entrée
$4.4
Sortie
$22
Lecture du cache
$0.22
Écriture du cache
$5.5
moonshotai

4 modèles

Tous les modèles
moonshotai logomoonshotai

MoonshotAI: Kimi K3.1 Pro (batch)

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

Contexte
1.0M
Entrée
text · image · video
Sortie
text
Entrée: $0.372Sortie: $5.583par million de tokens
Voir la fiche du modèle →
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: $0.192Sortie: $16par 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: $0.6Sortie: $3.5par million de tokens
Voir la fiche du modèle →