ModelWatch
← Catalog

Qwen3.5-122B-A10B

Alibaba (Qwen)qwenlm.github.io

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

visionopen-weights
Input price
$0.26 / 1M tokens
Output price
$2.08 / 1M tokens
Context window
262K tokens
Max output
66K tokens
Output speed
105 tokens/s
Time to first token
4.5s
Inputs
text, image, video
Open weights
Yes
OpenRouter id
qwen/qwen3.5-122b-a10b
Listed
Feb 25, 2026

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

Speed and benchmarks for “Qwen3.5 122B A10B (Reasoning)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others