{"data":{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","created":1761231332,"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...","architecture":{"tokenizer":"Qwen","instruct_type":null,"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"]},"endpoints":[]}}