AlibabaHosted on Luminet

Qwen3-Next 80B A3B

alibaba/qwen3-next-80b

Try in Playground

3B active / 80B total ultra-sparse MoE. 10× more efficient than dense 8B for the same quality.

Context window

256Ktokens

Input price

$0.14/ 1M tokens

Output price

$0.42/ 1M tokens

P50 latency

78ms

Quick start

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.luminet.ai/v1",
  apiKey: process.env.LUMINET_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "alibaba/qwen3-next-80b",
  messages: [{ role: "user", content: "Hello!" }],
});

Capabilities

textcode

Throughput: 640 tok/s · Released 2025-09