Qwen3 Next 80B A3B Thinking
Qwen
qwen/qwen3-next-80b-a3b-thinkingThe extended-reasoning variant of Qwen3-Next 80B-A3B, Alibaba's efficient next-generation MoE model, producing explicit chain-of-thought for harder reasoning and agentic tasks while retaining the architecture's 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
#113 · top 31%
Business, Management, & Finance
#123 · top 32%
Mathematical
#129 · top 35%
Software & IT Services
#130 · top 33%
Performance
Median latency and throughput measured across recent requests.
Throughput183 tok/s
Latency