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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibaba | $0.098 | $0.780 | 131K | — |
| Nebiusfp8 | $0.150 | $1.20 | 128K | — |
| $0.150 | $1.20 | 262K | — | |
| Novitabf16 | $0.150 | $1.50 | 131K | — |
| AtlasCloudfp8 | $0.150 | $1.50 | 262K | — |
Qwen3 Next 80B A3B Thinking costs $0.098 per million input tokens and $0.780 per million output tokens via OpenRouter, making it 46th cheapest of 298 paid models.
Qwen3 Next 80B A3B Thinking scores 26.7 on the Artificial Analysis Intelligence Index, ranking 87th of 180 benchmarked models, with a GPQA Diamond score of 76%.
Qwen3 Next 80B A3B Thinking generates around 168 tokens per second with 352ms time-to-first-token (p50), the 23rd fastest tracked model.
Qwen3 Next 80B A3B Thinking supports a 262K-token context window and can output up to 33K tokens. It accepts text input.