GLM-5

GLM-5 is Zhipu AI's flagship foundation model designed for complex system engineering and long-range Agent tasks, shifting focus from coding to engineering. It features 744B total parameters (40B activated) in a Mixture of Experts architecture, trained on 28.5T tokens. GLM-5 integrates DeepSeek Sparse Attention for higher token efficiency while preserving long-context quality. It supports 200K context length and 128K max output tokens, with capabilities including thinking modes, real-time streaming, function calling, context caching, and structured output. GLM-5 approaches Claude Opus 4.5 in code-logic density and systems-engineering capability.