GLM-4.6V

GLM-4.6V is a next-generation multimodal large language model series from Z.ai (Zhipu AI), designed for high-fidelity visual understanding and long-context reasoning across images, video, documents, and text. It comes in two main variants: the 106B-parameter GLM-4.6V foundation model for cloud and cluster deployment, and the lightweight GLM-4.6V-Flash (9B) optimized for local and low-latency applications. With a 128k token context window, GLM-4.6V can read large PDFs, slide decks, and multi-page mixed-media documents in a single pass. Native multimodal function calling lets it use tools directly from visual inputs, closing the loop from perception to executable actions and enabling powerful agent-style workflows. Typical use cases include visual document QA, chart and layout understanding, multimodal search and analysis, converting UI screenshots into production-ready code, and generating image-rich content. The models are released with open weights under a permissive open-source license, making them suitable for research, self-hosted deployments, and integration into production systems.