Qwen3-Next-80B-A3B-Thinking is a next-generation basic model released by Alibaba Tongyi Qianwen team and specially designed for complex reasoning tasks. It is based on the innovative Qwen3-Next architecture, which combines a hybrid attention mechanism (Gated DeltaNet and Gated Attention) and a high sparsity mixed expert (MoE) structure to achieve ultimate training and inference...
Provider: Qwen
Context window: 256K
Pricing: $0.07 input / $0.55 output per 1M tokens
Capabilities: serverless, json_mode, function_calling, structured_output
