minimax logo
minimax

MiniMax: MiniMax M3

Descrizione della fonte (inglese)

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Panoramica

Specifiche del modello

Contesto
1.048.576 tokens
Output massimo
512.000 tokens
Architettura
text+image+video->text
Tokenizer
Other
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.3
per milione di token
Output
$1.2
per milione di token
Lettura cache
$0.06
per milione di token
API

Configurazione del modello

Parametri predefiniti

temperature
1
top_p
0.95

Ragionamento

Ragionamento obbligatorio
No
Parametri predefiniti
No
API

Avvio rapido

Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.

Documentazione 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","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

InputOutput

Input
textimagevideo
Output
text
Ragionamento

No

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provider disponibili

12 provider

Verificato: 7 settembre 2026

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

CoreWeave

fp4
Contesto
262K
Output massimo
236K
Input
$0.23
Output
$0.96
Lettura cache
$0.05
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.24
Output
$0.96
Lettura cache
$0.048
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
524K
Output massimo
512K
Input
$0.28
Output
$1.1
Lettura cache
$0.056
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1M
Output massimo
512K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

Venice

fp8
Contesto
524K
Output massimo
66K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

Together

Non indicato
Contesto
524K
Output massimo
472K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
524K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
524K
Output massimo
524K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

Novita

fp8
Contesto
1M
Output massimo
131K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

Minimax

fp8
Contesto
524K
Output massimo
512K
Input
$0.3
Output
$1.2
Lettura cache
$0.06
Scrittura cache
Non indicato

SambaNova

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.6
Output
$2.4
Lettura cache
Non indicato
Scrittura cache
Non indicato

ModelRun

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.75
Output
$3
Lettura cache
$0.15
Scrittura cache
Non indicato
minimax

4 modelli

Tutti i modelli