Qwen: Qwen3.5-122B-A10B
Qwen3.5-122B-A10B is a large mixture-of-experts model offering solid reasoning and agentic scores at a modest price, with multimodal input support — a practical choice for businesses needing capable performance at scale.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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 overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.
Capabilities
Architecture
| Modality | Text + Image + Video → Text |
| Tokenizer | Qwen3 |
| Parameters | 122B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.26 | $0.000260 |
| Output | $2.08 | $0.002080 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
