Specifiche del modello
- Contesto
- 1.048.576 tokens
- Output massimo
- 943.718 tokens
- Architettura
- text->text
- Tokenizer
- DeepSeek
- Limite di conoscenza
- Non indicato
- Moderato
- No
Prezzi completi
Tariffe sincronizzate da OpenRouter, per milione di token.
- Input
- $0.111 per milione di token
- Output
- $4.44 per milione di token
- Lettura cache
- $0.097 per milione di token
Configurazione del modello
Parametri predefiniti
temperature- 1
top_p- 1
Ragionamento
- Ragionamento obbligatorio
- No
- Parametri predefiniti
- high
- Capacità e modalità
- max, high, low, none
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":"deepseek/deepseek-v4-pro-0813","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
No · max · high · low · none
Parametri API supportati
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p25 provider
Verificato: 8 novembre 2026
Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.
Relace
fp4- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.0999
- Output
- $8
- Lettura cache
- $0.0999
- Scrittura cache
- Non indicato
Wafer
mxfp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.111
- Output
- $4.44
- Lettura cache
- $0.097
- Scrittura cache
- Non indicato
Wafer
mxfp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.285
- Output
- $4.3
- Lettura cache
- $0.284
- Scrittura cache
- Non indicato
Alibaba
Non indicato- Contesto
- 1M
- Output massimo
- 393K
- Input
- $0.5808
- Output
- $1.7424
- Lettura cache
- $0.0581
- Scrittura cache
- Non indicato
Baidu
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.6587
- Output
- $1.976
- Lettura cache
- $0.021
- Scrittura cache
- Non indicato
Alibaba
Non indicato- Contesto
- 1M
- Output massimo
- 393K
- Input
- $0.66
- Output
- $1.98
- Lettura cache
- $0.066
- Scrittura cache
- Non indicato
StreamLake
Non indicato- Contesto
- 1.0M
- Output massimo
- 384K
- Input
- $0.66
- Output
- $1.98
- Lettura cache
- $0.022
- Scrittura cache
- Non indicato
DeepSeek
Non indicato- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.66
- Output
- $1.98
- Lettura cache
- $0.022
- Scrittura cache
- Non indicato
Phala
Non indicato- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.957
- Output
- $2.8776
- Lettura cache
- $0.099
- Scrittura cache
- Non indicato
Novita
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.99
- Output
- $2.97
- Lettura cache
- $0.033
- Scrittura cache
- Non indicato
GMICloud
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.056
- Output
- $3.168
- Lettura cache
- $0.0352
- Scrittura cache
- Non indicato
DeepInfra
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $1.3
- Output
- $2.6
- Lettura cache
- $0.1
- Scrittura cache
- Non indicato
CoreWeave
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.31
- Output
- $3.96
- Lettura cache
- $0.044
- Scrittura cache
- Non indicato
BaseTen
fp4- Contesto
- 1.0M
- Output massimo
- 262K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.132
- Scrittura cache
- Non indicato
AtlasCloud
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.132
- Scrittura cache
- Non indicato
Nebius
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.04
- Scrittura cache
- Non indicato
Parasail
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.044
- Scrittura cache
- Non indicato
Together
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.13
- Scrittura cache
- Non indicato
DigitalOcean
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.044
- Scrittura cache
- Non indicato
SiliconFlow
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.044
- Scrittura cache
- Non indicato
Cloudflare
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.32
- Output
- $3.96
- Lettura cache
- $0.044
- Scrittura cache
- Non indicato
Sail Research
fp4- Contesto
- 1.0M
- Output massimo
- 384K
- Input
- $1.35
- Output
- $2.4
- Lettura cache
- $0.195
- Scrittura cache
- Non indicato
Sail Research
fp4- Contesto
- 1.0M
- Output massimo
- 384K
- Input
- $1.35
- Output
- $2.4
- Lettura cache
- $0.195
- Scrittura cache
- Non indicato
Venice
Non indicato- Contesto
- 1M
- Output massimo
- 262K
- Input
- $1.65
- Output
- $4.95
- Lettura cache
- $0.165
- Scrittura cache
- Non indicato
Parasail
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $1.98
- Output
- $5.94
- Lettura cache
- $0.066
- Scrittura cache
- Non indicato