Pass IndexThe State of AISign in

Qwen3-Next-80B-Thinking

Model Studio calls it "a new generation of Qwen3-based open-source thinking mode models" with better instruction adherence and more concise outputs; 80B total parameters, 3B activated, thinking mode only.

text → text · made by Alibaba

$0.15$1.2per Mtok in / out
Google Vertex AI

Sold by 2 ways

SellerLaneRate
Google Vertex AI 0 ways$0.15per Mtok in$1.2per Mtok out
Google Vertex AI cloudnot on the seller's list todaystandard$0.15per Mtok in$1.2per Mtok outcloud.google.com · read 2026-08-24
Venice AI 0 ways$0.35per Mtok in$1.9per Mtok out
Venice AI aggregatornot on the seller's list todaystandard$0.35per Mtok in$1.9per Mtok outmodels.dev · read 2026-08-27

About

Qwen3-Next-80B-Thinking — a text model from Alibaba.

It takes text and returns text, with a context window of 131,072 tokens. The catalogue files it under reasoning.

Every current figure

Maker
Alibaba
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Parameters
80 billion · read from its own name