DeepSeek

DeepSeek V4 Flash

Fast DeepSeek V4 for high-volume tasks

Text

Reasoning

Tools

Type: Chat
Context: 1.0M tokens
Russian: high
Input price: 7,09 ₽ / 1M tokens
Output price: 14,18 ₽ / 1M tokens
Release date: April 2026

chat/completions

import OpenAI from "openai"
const client = new OpenAI({
  baseURL: "https://api.yenisei.ru/v1",
  apiKey: process.env.YENISEI_API_KEY,
})
const stream = await client.chat.completions.create({
  model: "deepseek-flash",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

DeepSeek V4 Flash is the fast, economical member of the V4 lineup with low time to first token. It is designed for chats, assistants and a high volume of requests, where response speed and predictable cost matter. For complex requests the model switches on reasoning; in normal mode it answers quickly. It follows instructions and system prompts well, speaks Russian confidently and keeps a coherent conversation.