All models
Alibaba
Qwen3.8 Flash
A fast, lightweight Qwen
Text
Images
Video
Reasoning
Tools
- Type
- Chat
- Context
- 1M tokens
- Russian
- high
- Input price
- 12 ₽ / 1M tokens
- Output price
- 37,6 ₽ / 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: "qwen-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
Qwen3.8 Flash is the fast, inexpensive member of the Qwen lineup for a high volume of requests where low latency and cost come first. The model answers quickly on standard tasks: auto-replies, classification, short dialogues and bulk request processing. Despite its compact size, it follows instructions and handles Russian and other languages confidently. It fits when speed and price matter more than depth of answer.
Strengths
- Very low response latency
- Very economical at high volume
- Works in Russian and other languages
- Stable under load
- Predictable cost per request
Where to use it
- Auto-replies and standard dialogues
- Classifying and routing inquiries
- Bulk request processing
- Real-time integration into a product
- Extracting simple fields from text
- Quick prototypes and demos