# Qwen: Qwen3.5-122B-A10B

Provider: qwen  
Category: llm  
Model ID: `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...

## Specs

- Context length: 262144 tokens
- Max output: 65536 tokens
- Modalities: text, image, video
- Released: 2026-02-25

## Pricing

- Input: $0.26 per million tokens
- Output: $2.08 per million tokens

## Providers

- **qwen** — ctx 262144, input $0.26/M, output $2.08/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/qwen3-5-122b-a10b