Skip to main content
Z.ai’s GLM models are text-only models with tool use. The GLM-5 generation adds built-in reasoning: GLM-5.3 is the newest, with a 524K-token context window, and GLM 5.3 (evroc) runs the same model in Germany. The GLM-4.7 family brings two complementary models: the 358B flagship GLM-4.7 for deep reasoning, preserved thinking across long agentic workflows, and high-fidelity UI generation; and the lightweight GLM-4.7 Flash for high-volume, real-time automation where hundreds of small decisions are needed per minute. Both models offer strong bilingual (English/Chinese) performance and native support for interleaved thinking.

About

GLM-5.3 is Z.ai’s newest model in DeepMask. Reasoning is always on, and it has a 524K-token context window. Use it for deep analysis, coding, and agentic tasks over long material.

Specifications