Specifiche del modello
- Contesto
- 1.048.576 tokens
- Output massimo
- 524.288 tokens
- Architettura
- text+image+video->text
- Tokenizer
- Other
- Limite di conoscenza
- Non indicato
- Moderato
- No
Prezzi completi
Tariffe sincronizzate da OpenRouter, per milione di token.
- Input
- $0.075 per milione di token
- Output
- $0.3 per milione di token
- Lettura cache
- $0.0075 per milione di token
Configurazione del modello
Ragionamento
- Ragionamento obbligatorio
- Sì
- Parametri predefiniti
- max
- Capacità e modalità
- max, xhigh, high, medium, low
Avvio rapido
Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.
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!"}]}'Input → Output
No · max · xhigh · high · medium · low
Parametri API supportati
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p15 provider
Verificato: 19 novembre 2026
Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.
SambaNova
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.06
- Output
- $0.24
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
StreamLake
fp8- Contesto
- 1M
- Output massimo
- 512K
- Input
- $0.135
- Output
- $0.54
- Lettura cache
- $0.0135
- Scrittura cache
- Non indicato
Wafer
nvfp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.135
- Output
- $0.54
- Lettura cache
- $0.0135
- Scrittura cache
- Non indicato
Makora
fp4- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Fireworks
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
InferenceNet
fp4- Contesto
- 1M
- Output massimo
- 524K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
DigitalOcean
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Nebius
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
ModelRun
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Parasail
fp8- Contesto
- 1.0M
- Output massimo
- 524K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
InferenceNet
fp4- Contesto
- 1M
- Output massimo
- 524K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Together
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Inferact vLLM
nvfp4- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
GMICloud
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Minimax
Non indicato- Contesto
- 1.0M
- Output massimo
- 524K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato