minimax logo
minimax

MiniMax: MiniMax M3.1 Flash

Description de la source (anglais)

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...

Présentation

Caractéristiques du modèle

Contexte
1 048 576 tokens
Sortie maximale
524 288 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
$0.075
par million de tokens
Sortie
$0.3
par million de tokens
Lecture du cache
$0.0075
par million de tokens
API

Configuration du modèle

Raisonnement

Raisonnement obligatoire
Oui
Paramètres par défaut
max
Capacités et modalités
max, xhigh, high, medium, low
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":"minimax/minimax-m3.1-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capacités et modalités

Entrée → Sortie

Entrée
textimagevideo
Sortie
text
Raisonnement

Non · max · xhigh · high · medium · low

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Fournisseurs disponibles

15 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

SambaNova

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.06
Sortie
$0.24
Lecture du cache
$0.006
Écriture du cache
Non indiqué

StreamLake

fp8
Contexte
1M
Sortie maximale
512K
Entrée
$0.135
Sortie
$0.54
Lecture du cache
$0.0135
Écriture du cache
Non indiqué

Wafer

nvfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.135
Sortie
$0.54
Lecture du cache
$0.0135
Écriture du cache
Non indiqué

Makora

fp4
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Fireworks

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

InferenceNet

fp4
Contexte
1M
Sortie maximale
524K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

DigitalOcean

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Nebius

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

ModelRun

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Parasail

fp8
Contexte
1.0M
Sortie maximale
524K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

InferenceNet

fp4
Contexte
1M
Sortie maximale
524K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Together

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Inferact vLLM

nvfp4
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

GMICloud

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué

Minimax

Non indiqué
Contexte
1.0M
Sortie maximale
524K
Entrée
$0.15
Sortie
$0.6
Lecture du cache
$0.015
Écriture du cache
Non indiqué
minimax

4 modèles

Tous les modèles
minimax logominimax

MiniMax: MiniMax H3 Image Highspeed

MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 Image model. It takes the same inputs and limits as MiniMax H3 Image: it creates images from text prompts...

Contexte
4K
Entrée
text · image
Sortie
image
Entrée: $2.3 par million de tokensImage en sortie: $7.6 par million de tokens
Voir la fiche du modèle →
minimax logominimax

MiniMax: MiniMax H3 Image

MiniMax H3 Image is MiniMax's image generation and editing model. It creates images from text prompts and edits or composes images from 1 to 16 reference images, with output up...

Contexte
4K
Entrée
text · image
Sortie
image
Entrée: $2.3 par million de tokensImage en sortie: $3.8 par million de tokens
Voir la fiche du modèle →
minimax logominimax

MiniMax: H3 Max

MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...

Contexte
Non indiqué
Entrée
text · image
Sortie
video
Vidéo en sortie: $0.08 par seconde
Voir la fiche du modèle →
minimax logominimax

MiniMax: H3

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...

Contexte
Non indiqué
Entrée
text · image · video · audio
Sortie
video
Vidéo en sortie: $0.13 par secondeReference Image (first 5 free): $0.04 par image
Voir la fiche du modèle →