AI model · Qwen
Qwen3 Next 80B A3B Thinking
Model ID: qwen/qwen3-next-80b-a3b-thinking
- Input
- $0.15 per 1M tokens
- Output
- $1.20 per 1M tokens
- Context
- 262K tokens at once
- Max output
- 236K tokens per reply
- Released
- 11 Sep 2025 Qwen
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- Qwen: Qwen3 Next 80B A3B Thinking on OpenRouter — read 2 Oct 2026