qwen

Qwen: Qwen3 Coder Next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Context
262k tokens
Input / 1M tokens
$0.11
Output / 1M tokens
$0.80
Benchmark

Pricing

Input tokens$0.11 per 1M tokens
Output tokens$0.80 per 1M tokens
Cache read$0.07 per 1M tokens

Technical details

Model IDqwen/qwen3-coder-next
Context window262k tokens
Input modalitiestext
Output modalitiestext
TokenizerQwen
Max output tokens262,144

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-coder-next',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Qwen: Qwen3 Coder Next?

Get an API key and start making requests in minutes.

Get an API key