{"data":{"id":"xiaomi/mimo-v2-omni","name":"Xiaomi: MiMo-V2-Omni","created":1773863703,"description":"MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"]},"endpoints":[]}}