Qwen3.5-122B-A10B
Qwen3.5-122B-A10B is a large language model made by Qwen, added to the catalog on 25 Feb 2026. It has a context window of 262,144 tokens and costs $0.26 per 1M input tokens and $2.08 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: generate text from images and videos, enhance content creation workflows and facilitate advanced multimodal interactions.
Price checked ยท source: OpenRouter
What Qwen3.5-122B-A10B is
The Qwen3.5-122B-A10B, released on February 25, 2026, is a cutting-edge vision-language model from Qwen. It features a hybrid architecture that combines a linear attention mechanism with a sparse mixture-of-experts model, enhancing inference efficiency. With a context length of 262,144, this model processes text, images, and videos, providing text outputs. Its capabilities in text processing significantly exceed those of its predecessor, Qwen3-235B-2507, while its visual processing is superior to Qwen3-VL-235B. This model is designed for those seeking advanced multimodal interactions.
Key features
- Hybrid architecture for efficiency
- High context length of 262,144
- Processes text, images, and videos
- Superior text and visual capabilities
- Supports various input modalities
Typical uses
- Generate text from images and videos
- Enhance content creation workflows
- Facilitate advanced multimodal interactions
Qwen3.5-122B-A10B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.26 |
| Output, per 1M tokens | $2.08 |
No price change since it was added on 25 Feb 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0008 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0082 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.012 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.042 |
Qwen3.5-122B-A10B specifications
| Model id | qwen/qwen3.5-122b-a10b |
|---|---|
| Version | qwen3.5-122b-a10b-20260224 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 25 Feb 2026 |
| Input types | text, image, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Qwen3.5-122B-A10B yet.