Alibaba Qwen 3.5 MoE (397B total, 17B active). Excellent Chinese reasoning and generation, with strong multilingual and coding capabilities. Accessed via OpenRouter. Particularly useful for classical Chinese work, mainland marketing copy, and cross-border e-commerce localization. Maximum context window (input and output combined): about 262,144 tokens. Maximum output per reply: about 65,500 tokens (model reasoning, if any, counts toward this limit). Maximum total upload size per request: 256MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: bmp, gif, jpeg, jpg, png, webp. Maximum size per image: 10MB. Image dimensions: at least 11 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Image aspect ratio: 1/200 to 200. Output content formats: Text This module does not support continuous conversations. AI can make mistakes. Please verify important information.