Qwen

Qwen3.8 2.4T

The largest Qwen of the 3.8 line, with reasoning

Text

Reasoning

Tools

Type: Chat
Context: 1.0M tokens
Russian: medium
Input price: 160 ₽ / 1M tokens
Output price: 480 ₽ / 1M tokens
Release date: August 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: "qwen3.8-2.4t",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Qwen3.8 2.4T is the largest model of the Qwen 3.8 line, built for complex and high-stakes tasks. It lays out step-by-step reasoning, works confidently with code and analytics, follows instructions and calls tools reliably (function-calling). Context is up to a million tokens, input is text. Its size provides a quality margin where smaller models start making mistakes on long chains. Russian at a medium level. A good fit when quality and depth matter more than price and speed.