DeepSeek

DeepSeek V4 Flash

Chat
deepseek/deepseek-v4-flash

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 high-throughput workloads, while maintaining strong reasoning and coding performance.

1M ventana de contexto
384K tokens de salida máximos
Lanzamiento: 2026-04-24
Protocolos Soportados:OpenAIopenaiAnthropicanthropic
Proveedores Disponibles:AzureAzureDeepSeekDeepSeekBaiLianAliyun
Capacidades:Function CallingPrompt Caching

Providers

BaiLianAliyun
Tokens de Entrada
$0.14/M
Tokens de Salida
$0.28/M
Lectura de Caché
$0.028/M
Búsqueda Web
$0.01/R
Protocols
Anthropicanthropic
AzureAzure
Tokens de Entrada
$0.14/M
Tokens de Salida
$0.28/M
Lectura de Caché
$0.028/M
Protocols
OpenAIopenai/v1/chat/completions/v1/responses
DeepSeekDeepSeek
Tokens de Entrada
$0.14/M
Tokens de Salida
$0.28/M
Lectura de Caché
$0.028/M
Protocols
OpenAIopenai/v1/chat/completions
Anthropicanthropic

Ejemplos de Código

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.ai/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Preguntas Frecuentes

DeepSeek V4 Flash en Ofox.ai cuesta $0.14/M por millón de tokens de entrada y $0.28/M por millón de tokens de salida. Pago por uso, sin cuotas mensuales.