Multimodal model

SenseNova 6.7 Flash-Lite

SenseNova 6.7 Flash-Lite is a lightweight multimodal agent model from SenseTime built for long horizon office workflows. It uses a native multimodal architecture that reads images and documents directly, skipping a vision to text intermediate step, cutting token consumption by up to 60 percent versus text only agents in search heavy tasks while supporting a 262144 token context window.