# 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 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.

## Model Information

- **Organization**: [qwen](/llm.txt)
- **Slug**: qwen3-5-122b-a10b
- **Available at Providers**: 13
- **Release Date**: February 25, 2026

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | qwen3.5-122b-a10b | 0.11 | 0.90 |  | [View](https://aihubmix.com/model/qwen3.5-122b-a10b) |
| [ApiYI](/llm/apiyi.txt) | qwen3.5-122b-a10b |  |  |  |  |
| [Arena AI](/llm/arenaai.txt) |  |  |  |  |  |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3.5-122B-A10B | 0.40 | 3.20 |  | [View](https://kilo.ai/models/qwen/qwen3.5-122b-a10b) |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3.5 122B A10B |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3.5 122B A10B Thinking |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen3.5-122B-A10B | 0.40 | 3.20 |  | [View](https://openrouter.ai/qwen/qwen3.5-122b-a10b-20260224) |
| [Routeway](/llm/routeway.txt) | Qwen: Qwen 3.5 122B A10B | 0.37 | 2.94 |  | [View](https://routeway.ai/models) |
| [302.AI](/llm/302ai.txt) | qwen3.5-122b-a10b | 0.12 | 0.92 |  | [View](https://302ai-en.apifox.cn/207705113e0) |
| [Yupp](/llm/yupp.txt) | Qwen3.5 122B A17B |  |  |  |  |
| [Writingmate](/llm/writingmate.txt) | Qwen: Qwen3.5-122B-A10B |  |  |  | [View](https://writingmate.ai/models/qwen/qwen3.5-122b-a10b) |
| [Novita AI](/llm/novita.txt) | qwen3.5-122b-a10b | 0.40 | 3.20 |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3.5 122B A17B (Novita) |  |  |  |  |

---

[← Back to all providers](/llm.txt)