GLM-5.2: 1M-Token Context & Thinking Levels by Z.ai

Z.ai has launched GLM-5.2, their latest large language model, featuring a usable 1-million-token context window. This is a significant jump from GLM-5.1's 200,000-token window. What's interesting is that GLM-5.2 also introduces two new thinking-effort levels: High and Max, with Max recommended for complex coding tasks. However, Z.ai did not release any benchmark scores for GLM-5.2 at launch. This new model allows a coding agent to hold an entire mid-sized repository in its working memory, avoiding constant summarization. The bottom line is that GLM-5.2 could significantly change how coding agents operate in practice.