A
Qwen3 Next 80B A3B ThinkingOPEN
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default.
Prices update automatically — checked daily against provider list prices.
- $0.41 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 46% of the 191 open-weight models tracked here
- 24 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 Next 80B A3B Thinking, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Qwen3 Next 80B A3B Thinking delivers 6.5 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.48 per 1M tokens (median of 12) — this one costs $0.41.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna (batch) and 28 more
About this model
Qwen3 Next 80B A3B Thinking is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3 Next 80B A3B Thinking?
Qwen3 Next 80B A3B Thinking is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 16.9 on the Artificial Analysis intelligence index.
Is Qwen3 Next 80B A3B Thinking free?
The weights are free and open — you can self-host Qwen3 Next 80B A3B Thinking and pay nothing per token. If you prefer a hosted API, list prices are $0.15 per million input tokens and $1.2 per million output tokens.
What is Qwen3 Next 80B A3B Thinking good at?
Independent benchmarks from Artificial Analysis give it GPQA 75.9%, MMLU-Pro 82.4%, Humanity's Last Exam 12.6%, Long Context Reasoning 62%, LiveCodeBench 78.4%, SciCode 38.8%, AIME 2025 84.3%, IFBench 60.7%, τ²-Bench 41.5%, τ-Bench Banking 6.2%, Terminal-Bench 6.7%, Terminal-Bench Hard 9.8%. It is particularly used for code generation.
How fast is Qwen3 Next 80B A3B Thinking?
It generates about 180.7 tokens per second, with a median 1.09s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Qwen3 Next 80B A3B Thinking?
Yes. Qwen3 Next 80B A3B Thinking has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.