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...

• Context window: 262,144 tokens
• Input: text, image, video
• Output: text
• Pricing: $0.26/M input tokens, $2.08/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.