{"id":41141,"date":"2025-08-12T10:29:13","date_gmt":"2025-08-12T02:29:13","guid":{"rendered":"https:\/\/www.1ai.net\/?p=41141"},"modified":"2025-08-12T10:29:13","modified_gmt":"2025-08-12T02:29:13","slug":"%e6%99%ba%e8%b0%b1%e8%a7%86%e8%a7%89%e6%8e%a8%e7%90%86%e6%a8%a1%e5%9e%8b-glm-4-5v-%e4%b8%8a%e7%ba%bf%e5%b9%b6%e5%bc%80%e6%ba%90%ef%bc%8c%e5%8f%b7%e7%a7%b0%e5%85%a8%e7%90%83-100b-%e7%ba%a7","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/41141.html","title":{"rendered":"Smart Spectrum Visual Reasoning Model GLM-4.5V is online and open source, claiming to be \"the world's best at 100B\"."},"content":{"rendered":"

August 12 News.Zhipu<\/a> AI today launched the world's most effective 100B-classOpen Source<\/a>visual inference model<\/a> GLM-4.5V (total parameters 106B, activation parameters 12B), and synchronized with Hugging Face open source in the Magic Hitch community. In addition, the API call price is as low as $2\/M tokens for input and $6\/M tokens for output.<\/p>\n

\"21aa5882j00t0v07t006dd000u000a0p\"<\/p>\n

1AI learned from the official introduction that GLM-4.5V is based on GLM-4.5-Air, the flagship text base model of the new generation of Smart Spectrum, and continues the technical route of GLM-4.1V-Thinking, which has reached the performance of the same level of open source model SOTA in the 41 public visual multimodal lists, and covers common tasks such as image, video, document understanding, and GUI Agent. It covers common tasks such as image, video, document understanding, and GUI agent.<\/p>\n

Beyond the multimodal list, it places more emphasis on the model's performance and usability in real-world scenarios.GLM-4.5V By efficiently mixing the trainingAbility to cover a wide range of visual content<\/strong>, which enables full-scene visual reasoning, including:<\/p>\n