/ Models

Language models

Qwen: Qwen3.5 Plus 2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

Maker
Qwen
Context window
1M
Max output
66K
Input / 1M
$0.26
Output / 1M
$1.56
1M in + 1M out
$1.82

Everything else

Max output66K
Input / 1M$0.26
Output / 1M$1.56
Cache read / 1M
Cache write / 1M
1M in + 1M out$1.82
Takestext, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-02-16
Knowledge cutoff
Retires
Catalog idqwen/qwen3.5-plus-02-15

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models