Qwen3 Next 80B A3B Thinking: pricing, context and benchmarks

What you need to know about Qwen3 Next 80B A3B Thinking

Alibaba (Qwen), based in China, put Qwen3 Next 80B A3B Thinking online on September 11, 2025. It accepts text as input and produces text. Its context window reaches 262,144 tokens, larger than 58 % of the models in the registry, and it can write up to 235,929 tokens in one go.

It has been available for about 13 months, long enough for its prices and scores to have settled.

Qwen3 Next 80B A3B Thinking pricing

On OpenRouter, Qwen3 Next 80B A3B Thinking costs $0.15 per million input tokens and $1.2 per million output tokens. Counting three tokens read for every token written, its average price is $0.413 per million, more expensive than 35 % of paid models (1.8 times cheaper than the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0009. At 1,000 tasks a day, budget $27 a month. The price calculator redoes this with your own volumes.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Qwen3 Next 80B A3B Thinking. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
• Its knowledge stops at September 2025.

Its weights are open and downloadable from Hugging Face (apache-2.0 licence): you can run it on your own machines without sending your data to a third party. With 81,324,862,720 billion parameters, it needs about 45,443,808,317 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 39,598 times on Hugging Face last month.

Other Alibaba (Qwen) models