GLM-4.5

GLM-4.5 is an open-source Mixture-of-Experts (MoE) large language model developed by Z.ai, designed to unify reasoning, coding, and agentic capabilities within a single framework. It is available in two versions: the flagship GLM-4.5 with 355 billion total parameters (32 billion active) and the more streamlined GLM-4.5-Air with 106 billion total parameters (12 billion active). Both models support a context length of up to 128,000 tokens and offer a hybrid inference mode with 'thinking' and 'non-thinking' options to balance complex reasoning tasks and instant responses. GLM-4.5 has demonstrated exceptional performance across multiple benchmarks, ranking third globally and first among open-source models. It is released under an open, auditable license, providing options for on-premise deployment and fine-tuning, thereby offering enterprises greater control and transparency.