deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0423

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. $0.0679 per million input tokens, $0.168 per million output tokens. 1,048,576 token context window. Higher uptime with 17 providers. Includes independent benchmarks from Artificial Analysis.

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
$0.0679
/M tokens
Output
$0.168
/M tokens
Lettura cache
$0.0168
/M tokens
API

Configurazione del modello

Ragionamento

Moderato
No
Parametri predefiniti
high
Capacità e modalità
xhigh, high
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl 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

17 provider

Provider live su OpenRouter

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

OpenRouter

DigitalOcean

unknown
Contesto
1.0M
Output massimo
944K
Input
$0.068
Output
$0.168
Lettura cache
$0.017
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
384K
Input
$0.089
Output
$0.177
Lettura cache
$0.018
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
1.0M
Output massimo
66K
Input
$0.090
Output
$0.180
Lettura cache
$0.018
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.112
Output
$0.224
Lettura cache
$0.022
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.130
Output
$0.280
Lettura cache
$0.028
Scrittura cache
Non indicato

Alibaba

fp8
Contesto
1M
Output massimo
393K
Input
$0.134
Output
$0.268
Lettura cache
$0.027
Scrittura cache
Non indicato

Venice

unknown
Contesto
1M
Output massimo
33K
Input
$0.138
Output
$0.275
Lettura cache
$0.028
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
393K
Input
$0.140
Output
$0.280
Lettura cache
$0.028
Scrittura cache
Non indicato

NextBit

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.140
Output
$0.280
Lettura cache
$0.028
Scrittura cache
Non indicato

AtlasCloud

fp4
Contesto
1.0M
Output massimo
393K
Input
$0.140
Output
$0.280
Lettura cache
$0.028
Scrittura cache
Non indicato

Baidu

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.140
Output
$0.280
Lettura cache
$0.028
Scrittura cache
Non indicato

CoreWeave

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.140
Output
$0.280
Lettura cache
$0.070
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.140
Output
$0.280
Lettura cache
$0.070
Scrittura cache
Non indicato

Mancer 2

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.180
Output
$0.500
Lettura cache
Non indicato
Scrittura cache
Non indicato

Phala

unknown
Contesto
1.0M
Output massimo
393K
Input
$0.200
Output
$0.400
Lettura cache
$0.070
Scrittura cache
Non indicato

Azure

unknown
Contesto
1.0M
Output massimo
384K
Input
$0.210
Output
$0.560
Lettura cache
$0.031
Scrittura cache
Non indicato

Cloudflare

unknown
Contesto
384K
Output massimo
346K
Input
$0.440
Output
$1.32
Lettura cache
$0.014
Scrittura cache
Non indicato
deepseek

modelli

Tutti i modelli