# 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 planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.

The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.

## Model Information

- **Organization**: [qwen](/llm.txt)
- **Slug**: qwen3-next-80b-a3b-thinking
- **Available at Providers**: 33
- **Release Date**: September 10, 2025

### Benchmark Scores
- AIME 2025: 0.878
- GPQA: 0.772

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | qwen3-next-80b-a3b-thinking | 0.14 | 1.38 |  | [View](https://aihubmix.com/model/qwen3-next-80b-a3b-thinking) |
| [AIMLAPI](/llm/aimlapi.txt) | Qwen 3 Next 80B A3B Thinking |  |  |  |  |
| [Alibaba](/llm/alibaba.txt) | Qwen3-Next 80B-A3B (Thinking) | 0.50 | 6.00 |  |  |
| [Nvidia](/llm/nvidia.txt) | qwen3-next-80b-a3b-thinking | 0.00 | 0.00 | Yes | [View](https://build.nvidia.com/qwen/qwen3-next-80b-a3b-thinking) |
| [Alibaba (China)](/llm/alibabacn.txt) | Qwen3-Next 80B-A3B (Thinking) | 0.14 | 1.43 |  |  |
| [Novita AI](/llm/novita.txt) | qwen3-next-80b-a3b-thinking | 0.15 | 1.50 |  |  |
| [SiliconFlow (China)](/llm/siliconflowcn.txt) | Qwen/Qwen3-Next-80B-A3B-Thinking | 0.14 | 0.57 |  |  |
| [Cortecs](/llm/cortecs.txt) | Qwen3 Next 80B A3B Thinking | 0.16 | 1.31 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | Qwen3-Next-80B-A3B-Thinking | 0.14 | 0.57 |  | [View](https://www.siliconflow.com./models/qwen3-next-80b-a3b-thinking) |
| [Hugging Face](/llm/huggingface.txt) | Qwen3-Next-80B-A3B-Thinking | 0.30 | 2.00 |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 Next 80B A3B Thinking | 0.15 | 1.20 |  | [View](https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking-2509) |
| [Together AI](/llm/togetherai.txt) | Qwen3 Next 80B A3b Thinking | 0.15 | 1.50 |  |  |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 Next 80B A3B Thinking |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen3-next-80b-a3b-thinking) |
| [Vercel AI Gateway](/llm/vercel.txt) | Qwen3 Next 80B A3B Thinking | 0.15 | 1.50 |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3 Next 80B A3B Thinking (OpenRouter) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3 Next 80B A3B Thinking (Together AI) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3-Next-80B-A3B-Thinking |  |  |  |  |
| [Atlas Cloud](/llm/atlascloud.txt) | Qwen3 Next 80B A3B Thinking | 0.15 | 1.50 |  | [View](https://www.atlascloud.ai/models/Qwen/Qwen3-Next-80B-A3B-Thinking) |
| [LangDB](/llm/langdb.txt) | qwen3-next-80b-a3b-thinking |  |  |  | [View](https://langdb.ai/app/models) |
| [Nebius Token Factory](/llm/nebius.txt) | Qwen3-Next-80B-A3B-Thinking | 0.15 | 1.20 |  | [View](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking) |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 Next 80B A3B Thinking | 0.15 | 1.20 |  |  |
| [GMI Cloud](/llm/gmi.txt) | Qwen3 Next 80B A3B Thinking | 0.15 | 1.50 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3 Next 80B A3B (Thinking) |  |  |  |  |
| [302.AI](/llm/302ai.txt) | sophnet/Qwen3-Next-80B-A3B-Thinking | 0.14 | 1.43 |  | [View](https://302ai-en.apifox.cn/319727732e0) |
| [302.AI](/llm/302ai.txt) | Qwen/Qwen3-Next-80B-A3B-Thinking | 0.14 | 0.57 |  | [View](https://302ai-en.apifox.cn/api-252564719) |
| [Arena AI](/llm/arenaai.txt) |  |  |  |  |  |
| [Jiekou.AI](/llm/jiekou.txt) | Qwen3 Next 80B A3B Thinking | 0.15 | 1.50 |  |  |
| [RouterLink](/llm/routerlink.txt) | Qwen3-Next-80B-A3B-Thinking |  |  |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/qwen/qwen3-next-80b-a3b-thinking |  |  |  |  |
| [Qiniu](/llm/qiniuai.txt) | Qwen3 Next 80B A3B Thinking |  |  |  |  |
| [ApiYI](/llm/apiyi.txt) | qwen3-next-80b-a3b-thinking |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | qwen3-next-80b-a3b-thinking | 0.17 | 1.32 |  |  |
| [Writingmate](/llm/writingmate.txt) | Qwen: Qwen3 Next 80B A3B Thinking |  |  |  | [View](https://writingmate.ai/models/qwen/qwen3-next-80b-a3b-thinking) |

---

[← Back to all providers](/llm.txt)