DeepSeek

DeepSeek V4 Flash Vision

Fast DeepSeek that sees images

Text

Images

Reasoning

Tools

Type: Chat
Context: 1.0M tokens
Russian: medium
Input price: 17,6 ₽ / 1M tokens
Output price: 52,8 ₽ / 1M tokens
Release date: August 21, 2026

Start for free Try in the Playground

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-vision",
  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 Vision is the fast variant of the DeepSeek line: image understanding is added to the capabilities of Flash. The model analyzes screenshots, diagrams and documents with visual elements, supports reasoning for complex tasks and calls tools (function-calling). Context is up to a million tokens, so a large material together with its illustrations fits into a single request. It answers quickly and costs little. Russian at a medium level.