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...
The figures
- Made by
- Qwen
- Model ID
- qwen/qwen3.5-122b-a10b
- Input
- $0.26 per million tokens
- Output
- $2.08 per million tokens
- Context window
- 262K tokens
- Longest answer
- 66K tokens
- Takes in
- text, image, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 25 Feb 2026
Read on 3 Oct 2026.