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, none
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 · none

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Provider disponibili

39 provider

Verificato: 19 novembre 2026

Provider live su OpenRouter

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

OpenRouter

Wafer

mxfp4
Contesto
1.0M
Output massimo
944K
Input
$0.051
Output
$0.567
Lettura cache
$0.018
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

Cloudflare

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.1
Output
$0.9
Lettura cache
$0.03
Scrittura cache
Non indicato

InferenceNet

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.103
Output
$0.6
Lettura cache
$0.008
Scrittura cache
Non indicato

InferenceNet

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.103
Output
$0.6
Lettura cache
$0.008
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.112
Output
$0.336
Lettura cache
$0.00336
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

Reka

Non indicato
Contesto
1.0M
Output massimo
393K
Input
$0.12
Output
$0.64
Lettura cache
$0.008
Scrittura cache
Non indicato

CoreWeave

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.13
Output
$0.65
Lettura cache
$0.002
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.135
Output
$0.54
Lettura cache
$0.0135
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.14
Output
$0.42
Lettura cache
$0.0042
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.147
Output
$0.588
Lettura cache
$0.00294
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

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.18
Output
$0.72
Lettura cache
$0.0036
Scrittura cache
Non indicato

Wafer

mxfp4
Contesto
1.0M
Output massimo
944K
Input
$0.19
Output
$0.65
Lettura cache
$0.012
Scrittura cache
Non indicato

Cohere

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.195
Output
$0.66
Lettura cache
$0.003
Scrittura cache
Non indicato

Ionstream

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.2
Output
$0.7
Lettura cache
$0.02
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.21
Output
$0.63
Lettura cache
$0.0063
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

Mancer 2

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.2125
Output
$0.75
Lettura cache
$0.05
Scrittura cache
Non indicato

DigitalOcean

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

Makora

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.26
Output
$1.17
Lettura cache
$0.0058
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

Nebius

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.3
Output
$1.2
Lettura cache
$0.01
Scrittura cache
Non indicato

Google

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

Non indicato
Contesto
1.0M
Output massimo
262K
Input
$0.3
Output
$1.2
Lettura cache
$0.007
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

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

Fireworks

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

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.45
Output
$1.8
Lettura cache
$0.009
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

Venice

fp8
Contesto
1M
Output massimo
131K
Input
$3
Output
$12
Lettura cache
$0.06
Scrittura cache
Non indicato
deepseek

4 modelli

Tutti i modelli
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.15Output: $0.6per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash 1017 (batch)

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.036Output: $0.15per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash (batch)

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...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.112Output: $0.336per milione di token
Vedi i dettagli del modello →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Contesto
1.0M
Input
text · image
Output
text
Input: $0.44Output: $1.32per milione di token
Vedi i dettagli del modello →