qwen

Qwen: Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Context
262k tokens
Input / 1M tokens
$2
Output / 1M tokens
$6
Benchmark

Pricing

Input tokens$2 per 1M tokens
Output tokens$6 per 1M tokens
Cache read$0.20 per 1M tokens

Technical details

Model IDqwen/qwen3.8-2.4t-a95b
Context window262k tokens
Input modalitiestext
Output modalitiestext
TokenizerQwen
Max output tokens52,429

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'qwen/qwen3.8-2.4t-a95b',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Qwen: Qwen3.8 2.4T A95B?

Get an API key and start making requests in minutes.

Get an API key