qwen

Qwen: Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Context
131k tokens
Input / 1M tokens
$0.45
Output / 1M tokens
$1.82
Benchmark

Pricing

Input tokens$0.45 per 1M tokens
Output tokens$1.82 per 1M tokens

Technical details

Model IDqwen/qwen3-235b-a22b
Context window131k tokens
Input modalitiestext
Output modalitiestext
TokenizerQwen3
Max output tokens8,192

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/qwen3-235b-a22b',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Qwen: Qwen3 235B A22B?

Get an API key and start making requests in minutes.

Get an API key