# Qwen: Qwen3 Next 80B A3B Thinking

Provider: qwen  
Category: llm  
Model ID: `qwen/qwen3-next-80b-a3b-thinking`

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

## Specs

- Context length: 131072 tokens
- Max output: 32768 tokens
- Modalities: text
- Released: 2025-09-11

## Pricing

- Input: $0.10 per million tokens
- Output: $0.78 per million tokens

## Providers

- **qwen** — ctx 131072, input $0.10/M, output $0.78/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/qwen3-next-80b-a3b-thinking