deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0423

Descrizione della fonte (inglese)

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Panoramica

Specifiche del modello

Contesto
1.048.576 tokens
Output massimo
384.000 tokens
Architettura
text->text
Tokenizer
DeepSeek
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.0886
per milione di token
Output
$0.1772
per milione di token
Lettura cache
$0.0177
per milione di token
API

Configurazione del modello

Ragionamento

Ragionamento obbligatorio
No
Parametri predefiniti
high
Capacità e modalità
xhigh, high
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-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

InputOutput

Input
text
Output
text
Ragionamento

No · xhigh · high

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Provider disponibili

15 provider

Verificato: 22 settembre 2026

Provider live su OpenRouter

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

OpenRouter

OpenInference

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.04
Output
$0.3
Lettura cache
$0.014
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.0886
Output
$0.1772
Lettura cache
$0.0177
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
66K
Input
$0.09
Output
$0.18
Lettura cache
$0.018
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.091
Output
$0.182
Lettura cache
$0.0182
Scrittura cache
Non indicato

Venice

Non indicato
Contesto
1M
Output massimo
33K
Input
$0.0966
Output
$0.1925
Lettura cache
$0.0196
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
384K
Input
$0.098
Output
$0.196
Lettura cache
$0.0196
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.13
Output
$0.28
Lettura cache
$0.028
Scrittura cache
Non indicato

Alibaba

fp8
Contesto
1M
Output massimo
393K
Input
$0.134
Output
$0.268
Lettura cache
$0.0268
Scrittura cache
Non indicato

Baidu

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.14
Output
$0.28
Lettura cache
$0.028
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.14
Output
$0.28
Lettura cache
$0.028
Scrittura cache
Non indicato

AtlasCloud

fp4
Contesto
1.0M
Output massimo
393K
Input
$0.14
Output
$0.28
Lettura cache
$0.028
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.14
Output
$0.28
Lettura cache
$0.07
Scrittura cache
Non indicato

NextBit

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.3
Lettura cache
$0.035
Scrittura cache
Non indicato

Mancer 2

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.19
Output
$0.5
Lettura cache
Non indicato
Scrittura cache
Non indicato

Azure

Non indicato
Contesto
1.0M
Output massimo
384K
Input
$0.21
Output
$0.56
Lettura cache
$0.031
Scrittura cache
Non indicato
deepseek

4 modelli

Tutti i modelli