Alibaba/ Qwen
Qwen3-Next 80B-A3B Instruct
alibaba/qwen3-next-80b-a3b-instruct
Qwen instruction model for multilingual chat, reasoning, and tool use
Released
2025-09
Context window
131K
Max output
33K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-next-80b-a3b-instruct
- Knowledge cutoff
- 2025-04
- Aliases
- Qwen3-Next 80B-A3B Instruct
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| LLM Gateway | qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.15/M output $1.2/M | Yes |
| Helicone | qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.14/M output $1.4/M | Yes |
| Neon | qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.15/M output $1.2/M | Yes |
| Charm Hyper | qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.1175/M output $1.136/M · cache write $0.05875/M | Yes |
| Alibaba | qwen3-next-80b-a3b-instruct | custom | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.5/M output $2/M | Yes |
| Vercel AI Gateway | alibaba/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.15/M output $1.2/M | Yes |
| Alibaba (China) | qwen3-next-80b-a3b-instruct | custom | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.144/M output $0.574/M | Yes |
| Qiniu | qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input ¥0.001/K output ¥0.004/K | Yes |
| OpenRouter | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | Hugging Face: Qwen/Qwen3-Next-80B-A3B-Instruct | input $0.1/M · cache read $0.07/M output $1.1/M | Yes |
| Nvidia | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0/M output $0/M | Yes |
| Kilo Gateway | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.0975/M output $0.78/M | Yes |
| Merge Gateway | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.144/M · cache read $0.0288/M output $0.574/M | Yes |
| NovitaAI | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.15/M output $1.5/M | Yes |
| Jiekou.AI | qwen/qwen3-next-80b-a3b-instruct | openai_chat | 131K | 33K | Text | Text | Tool callTemperatureOpen weightStructured | - | input $0.15/M output $1.5/M | Yes |
Capabilities
Tool callTemperatureOpen weightStructured
Official price
input $0.5/M
output $2/M