TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

GLM-V

By ZhipuAI
New Text Gen 7
Released: July 1, 2025

Overview

GLM-V is ZhipuAI’s open-source multimodal GLM series that adds strong visual reasoning to GLM-4, handling images, video, documents and GUI screens for tasks like VQA, document parsing and agent-style UI control.

Description

GLM-V is an open-source family of vision-language models from ZhipuAI, centered on GLM-4.5V and GLM-4.1V. It extends GLM-4 text models with visual input for image and video understanding, document reading and GUI interaction, and introduces grounding and “thinking” modes so the same model can both reason step by step and act as a practical multimodal agent in real-world workflows.

About ZhipuAI

ZhipuAI is a Chinese AI company specializing in large language models and AI research, aiming to advance artificial general intelligence.

Industry: Artificial Intelligence
Company Size: 501-1000
Location: Beijing, CN
View Company Profile
Last updated: December 9, 2025
0 AIs selected
Clear selection
#
Name
Task