Qwen: Qwen3.5-122B-A10B
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...
Specifications
| Attribute | Value |
|---|---|
| Lab | Qwen |
| Tags | Open Weight |
| Release Date | 2026-02 |
| Context Window | 262,144 tokens |
| Input Price / 1M | $0.26 |
| Output Price / 1M | $2.08 |
| Input Modalities | Text, Image, Video |
| Output Modalities | Text |
Strengths
Weaknesses
Best For
In Depth: Qwen3.5-122B-A10B
Summary
Qwen3.5-122B-A10B is an AI model from Qwen.
Released 2026-02. It currently appears in the Overall category on LMRank. It supports Text, Image, Video input and produces Text output, with a context window of 262,144 tokens. Input pricing is $0.26 per 1M tokens and output is $2.08 per 1M tokens on OpenRouter.