Qwen

Qwen3 Coder Next

Next-generation Qwen code model, low cost

Text

Tools

Type: Chat
Context: 262K tokens
Russian: medium
Input price: 9,6 ₽ / 1M tokens
Output price: 64 ₽ / 1M tokens
Release date: February 4, 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-coder-next",
  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 Coder Next is a next-generation code model in the Qwen line. It writes and edits code, completes existing files and explains someone else's code, answering quickly and to the point without thinking aloud step by step. The context of 262 thousand tokens holds several project files, and tool calling (function-calling) is supported for agents in the editor and the build pipeline. Input is text. Russian at a medium level. It is the choice when you need a low-cost coding assistant for every day.