Qwen3 Next 80B A3B Instruct
Qwen🇨🇳
qwen/qwen3-next-80b-a3b-instructQwen3-Next 80B-A3B Instruct is Alibaba's next-generation efficient mixture-of-experts model (80B total, 3B active), using a highly sparse architecture for strong general-purpose performance at low inference cost.
Cost rate
0.2x
Context
262K
Released
Sep 11, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Medicine & Healthcare
#117 · top 32%
Business, Management, & Finance
#130 · top 33%
Mathematical
#135 · top 36%
Software & IT Services
#139 · top 35%
Performance
Median latency and throughput measured across recent requests.
Throughput181 tok/s
Latency