Pass IndexThe State of AISign in

Qwen3.5-35B-A3B-Base

A pre-trained Qwen3.5 foundation model with 35B total and 3B activated parameters, combining Gated Delta Networks with sparse mixture-of-experts and early fusion training on multimodal tokens.

text + image → text · made by Alibaba

$0.54$1.33per Mtok in / out
Thinking Machines Lab

Sold by 1 way

SellerLaneRate
Thinking Machines Lab apitraining$0.54per Mtok in$1.33per Mtok out$0.11per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25

About

Qwen3.5-35B-A3B-Base — a text model from Alibaba.

It takes text and images and returns text, with a context window of 262,144 tokens. The catalogue files it under extract.

Every current figure

Maker
Alibaba
Register
model
Takes
text + image
Returns
text
Context
262,144 tokens
Parameters
35 billion · read from its own name, the total of a mixture
Licence
not read

Known as 1 name

Qwen/Qwen3.5-35B-A3B-Base