Qwen3-Next-80B-A3B-Thinking is a reasoning-focused model that generates structured “thinking” traces by default. Suited for complex multi-step tasks like math proofs, code synthesis, logic, and agentic planning. Compared to earlier Qwen3 models, it’s more stable with long reasoning chains and scales efficiently during inference. Designed for agent frameworks, function calling, retrieval-based workflows, and benchmarks needing step-by-step solutions, it supports detailed completions and faster output through multi-token prediction. Runs only in thinking mode.
Retired on Oct 30, 2026: requests to this model ID now return an error. These models are live and work with the same API key.
Qwen3-Next-80B-A3B-Thinking is a reasoning-focused model that generates structured “thinking” traces by default. Suited for complex multi-step tasks like math proofs, code synthesis, logic, and agentic planning.
No. Qwen3 Next 80B A3B Thinking was retired on NagaAI on Oct 30, 2026, and requests to it now return an error. Live models you can use instead with the same API key: Qwen3.8 Max Prime, Qwen3.8 Omni Flash and Qwen3.8 Flash.
It takes text as input and returns text.
