GreenPT / greenpt/glm-5.2-eu

GLM-5.2 - access through LLMTR

GLM-5.2 is a general-purpose reasoning model with a 1,000,000-token context window. Unlike the nine persona variants of it on this provider, this row carries no hidden server-side instruction: an eight-token message was billed as seventeen input tokens in measurement, where the persona rows billed the same message at between 285 and 590. If you do not need an imposed answering style, this row gives you the same model for less. Tool/function calling was verified over a full two-turn loop. Repeated prompt prefixes are served from a cache and those input tokens bill at a quarter of the normal input rate. It does not accept image input; a request containing an image is refused by LLMTR without being charged. The model reasons by default and those tokens bill as output.