Specifiche del modello
- Contesto
- 1.048.576 tokens
- Output massimo
- 393.216 tokens
- Architettura
- text+image->text
- Tokenizer
- DeepSeek
- Limite di conoscenza
- Non indicato
- Moderato
- No
Prezzi completi
Tariffe sincronizzate da OpenRouter, per milione di token.
- Input
- $0.15 per milione di token
- Output
- $0.6 per milione di token
- Lettura cache
- $0.003 per milione di token
Configurazione del modello
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-v4.1-flash-1017","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Sì · max · high · low · none
Parametri API supportati
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p50 provider
Verificato: 19 novembre 2026
Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.
Particle AI
Non indicato- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.03
- Output
- $0.25
- Lettura cache
- $0.01
- Scrittura cache
- Non indicato
Ambient
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.035
- Output
- $0.15
- Lettura cache
- $0.0015
- Scrittura cache
- Non indicato
Wafer
mxfp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.036
- Output
- $0.5
- Lettura cache
- $0.01
- Scrittura cache
- Non indicato
PrimeIntellect
Non indicato- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.0437
- Output
- $0.7
- Lettura cache
- $0.0024
- Scrittura cache
- Non indicato
Pearl Research
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.05
- Output
- $0.3
- Lettura cache
- $0.003
- Scrittura cache
- Non indicato
Morph
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.059
- Output
- $0.52
- Lettura cache
- $0.005
- Scrittura cache
- Non indicato
Particle AI
Non indicato- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.06
- Output
- $0.5
- Lettura cache
- $0.02
- Scrittura cache
- Non indicato
Wafer
mxfp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.066
- Output
- $0.5
- Lettura cache
- $0.0065
- Scrittura cache
- Non indicato
DeepInfra
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.0784
- Output
- $0.2352
- Lettura cache
- $0.002352
- Scrittura cache
- Non indicato
InferenceNet
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.08
- Output
- $0.635
- Lettura cache
- $0.008
- Scrittura cache
- Non indicato
InferenceNet
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.08
- Output
- $0.635
- Lettura cache
- $0.008
- Scrittura cache
- Non indicato
OpenInference
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.09
- Output
- $1.2
- Lettura cache
- $0.005
- Scrittura cache
- Non indicato
DeepInfra
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.098
- Output
- $0.294
- Lettura cache
- $0.00294
- Scrittura cache
- Non indicato
Cloudflare
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.1
- Output
- $0.6
- Lettura cache
- $0.003
- Scrittura cache
- Non indicato
StepFun
fp8- Contesto
- 1M
- Output massimo
- 384K
- Input
- $0.105
- Output
- $0.42
- Lettura cache
- $0.0021
- Scrittura cache
- Non indicato
StreamLake
fp8- Contesto
- 1.0M
- Output massimo
- 384K
- Input
- $0.111
- Output
- $0.444
- Lettura cache
- $0.00222
- Scrittura cache
- Non indicato
Ant Digital
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.12
- Output
- $0.48
- Lettura cache
- $0.0024
- Scrittura cache
- Non indicato
River
Non indicato- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.12
- Output
- $0.48
- Lettura cache
- $0.0024
- Scrittura cache
- Non indicato
Novita
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.12
- Output
- $0.48
- Lettura cache
- $0.0024
- Scrittura cache
- Non indicato
Relace
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.12
- Output
- $0.5
- Lettura cache
- $0.003
- Scrittura cache
- Non indicato
DeepInfra
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.147
- Output
- $0.441
- Lettura cache
- $0.00441
- Scrittura cache
- Non indicato
Cohere
fp8- Contesto
- 1.0M
- Output massimo
- 384K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.003
- Scrittura cache
- Non indicato
SiliconFlow
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.15
- Output
- $0.6
- Lettura cache
- $0.003
- Scrittura cache
- Non indicato
Makora
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.8
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
ModelRun
fp4- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.17
- Output
- $0.67
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
DekaLLM
Non indicato- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.18
- Output
- $0.68
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Nebius
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.18
- Output
- $0.72
- Lettura cache
- $0.0036
- Scrittura cache
- Non indicato
DigitalOcean
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.18
- Output
- $0.72
- Lettura cache
- $0.0036
- Scrittura cache
- Non indicato
GMICloud
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.18
- Output
- $0.72
- Lettura cache
- $0.0036
- Scrittura cache
- Non indicato
Alibaba
Non indicato- Contesto
- 1M
- Output massimo
- 393K
- Input
- $0.18
- Output
- $0.72
- Lettura cache
- $0.0036
- Scrittura cache
- Non indicato
AtlasCloud
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.195
- Output
- $0.78
- Lettura cache
- $0.0039
- Scrittura cache
- Non indicato
Ionstream
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.21
- Output
- $0.62
- Lettura cache
- $0.0105
- Scrittura cache
- Non indicato
Fireworks
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.21
- Output
- $0.84
- Lettura cache
- $0.0042
- Scrittura cache
- Non indicato
Mistral
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.24
- Output
- $0.96
- Lettura cache
- $0.0056
- Scrittura cache
- Non indicato
PrimaLabs
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.24
- Output
- $0.96
- Lettura cache
- $0.0048
- Scrittura cache
- Non indicato
Modal
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.25
- Output
- $1
- Lettura cache
- $0.005
- Scrittura cache
- Non indicato
Baidu
fp8- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.28
- Output
- $1.13
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Crusoe
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.29
- Output
- $1.2
- Lettura cache
- $0.007
- Scrittura cache
- Non indicato
Inceptron
fp4- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
CoreWeave
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Near AI
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Venice
fp8- Contesto
- 1M
- Output massimo
- 262K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.0075
- Scrittura cache
- Non indicato
Together
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Fireworks
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
BaseTen
Non indicato- Contesto
- 1.0M
- Output massimo
- 262K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.007
- Scrittura cache
- Non indicato
Parasail
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
DeepSeek
Non indicato- Contesto
- 1.0M
- Output massimo
- 393K
- Input
- $0.3
- Output
- $1.2
- Lettura cache
- $0.006
- Scrittura cache
- Non indicato
Fireworks
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.45
- Output
- $1.8
- Lettura cache
- $0.009
- Scrittura cache
- Non indicato
Morph
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.6
- Output
- $2.4
- Lettura cache
- $0.014
- Scrittura cache
- Non indicato
BaseTen
Non indicato- Contesto
- 1.0M
- Output massimo
- 262K
- Input
- $0.6
- Output
- $2.4
- Lettura cache
- $0.014
- Scrittura cache
- Non indicato