Volver a modelos
DeepSeek·Familia DeepSeek V
DeepSeek V4 Flash Vision Exp
proprietaryPublicado el 21 ago 2026
DeepSeek's experimental multimodal V4 Flash model that adds image input while matching DeepSeek V4 Flash text capabilities for agents, reasoning, world knowledge, tool use, and Responses API workflows. It supports mixed text and image requests, one million tokens of context, and the same token-based pricing as DeepSeek V4 Flash.
ChatCompletar textoLlamada a funcionesVisiónGeneración de códigoRazonamientotext · image · code
Proveedores (1)
Ordenados por coste total (entrada y salida por 1 millón de tokens). Selecciona una fila para ver los detalles del proveedor.
| Proveedor | Precio (por 1 M) | Límites | Regiones | Estado | Latencia |
|---|---|---|---|---|---|
| Entrada: $0.44Salida: $1.32 | 3K RPM / 1.0M TPM | us-east-1global | Operativo | 0ms |
Inicio rápido
Usa este modelo mediante DeepSeek con un SDK compatible con OpenAI.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.deepseek.com/v1",
apiKey: process.env.DEEPSEEK_API_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-v4-flash-vision-exp",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);API de DeepSeek · SDK compatible con OpenAI