deepseek logo
deepseek

DeepSeek: DeepSeek V4.1 Flash

Descrizione della fonte (inglese)

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Panoramica

Specifiche del modello

Contesto
1.048.576 tokens
Output massimo
943.718 tokens
Architettura
text+image->text
Tokenizer
DeepSeek
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
$0.006
per milione di token
API

Configurazione del modello

Ragionamento

Ragionamento obbligatorio
No
Parametri predefiniti
high
Capacità e modalità
max, high, low
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":"deepseek/deepseek-v4.1-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
textimage
Output
text
Ragionamento

Sì · max · high · low

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provider disponibili

31 provider

Verificato: 29 settembre 2026

Provider live su OpenRouter

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

OpenRouter

Relace

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.02
Output
$0.6
Lettura cache
$0.01
Scrittura cache
Non indicato

Wafer

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.0449
Output
$0.7
Lettura cache
$0.0359
Scrittura cache
Non indicato

InferenceNet

Non indicato
Contesto
1.0M
Output massimo
384K
Input
$0.06
Output
$0.39
Lettura cache
$0.02
Scrittura cache
Non indicato

Sail Research

fp4
Contesto
1.0M
Output massimo
384K
Input
$0.08
Output
$0.4
Lettura cache
$0.01
Scrittura cache
Non indicato

Morph

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.0805
Output
$0.51
Lettura cache
$0.0027
Scrittura cache
Non indicato

OpenInference

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.1
Output
$0.5
Lettura cache
$0.01
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.114
Output
$0.456
Lettura cache
$0.0114
Scrittura cache
Non indicato

DekaLLM

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.12
Output
$0.4
Lettura cache
$0.005
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.14
Output
$0.42
Lettura cache
$0.0042
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.1785
Output
$0.714
Lettura cache
$0.00357
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

Novita

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.195
Output
$0.78
Lettura cache
$0.0039
Scrittura cache
Non indicato

CoreWeave

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.2
Output
$0.65
Lettura cache
$0.03
Scrittura cache
Non indicato

NextBit

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.21
Output
$0.84
Lettura cache
$0.004
Scrittura cache
Non indicato

Fireworks

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.22
Output
$0.66
Lettura cache
$0.007
Scrittura cache
Non indicato

Krea

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.225
Output
$0.9
Lettura cache
$0.006
Scrittura cache
Non indicato

Phala

Non indicato
Contesto
1.0M
Output massimo
393K
Input
$0.276
Output
$1.104
Lettura cache
$0.00552
Scrittura cache
Non indicato

Ionstream

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.28
Output
$1.15
Lettura cache
$0.005
Scrittura cache
Non indicato

Baidu

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.3
Output
$1.2
Lettura cache
$0.006
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
33K
Input
$0.3
Output
$1.2
Lettura cache
$0.03
Scrittura cache
Non indicato

Makora

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.3
Output
$1.2
Lettura cache
$0.006
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.3
Output
$1.2
Lettura cache
$0.006
Scrittura cache
Non indicato

Alibaba

Non indicato
Contesto
1M
Output massimo
393K
Input
$0.3
Output
$1.2
Lettura cache
$0.03
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

SiliconFlow

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.3
Output
$1.2
Lettura cache
$0.006
Scrittura cache
Non indicato

Modal

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.3
Output
$1.2
Lettura cache
$0.03
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
33K
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

Venice

fp8
Contesto
1M
Output massimo
131K
Input
$0.375
Output
$1.5
Lettura cache
$0.0075
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
deepseek

4 modelli

Tutti i modelli