Qwen: Qwen3 Next 80B A3B Thinking
qwen
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...
- Context window
- 131,072 tokens
- Input cost
- $0.10 / 1M
- Output cost
- $0.78 / 1M
- Latency (p50)
- —