GLM is a family of large language models made by Z.ai (Zhipu.ai). A large language model (LLM) is a neural network trained on large amounts of text that writes text and code in reply to a prompt. Z.ai offers the models through its API platform for developers and through Z.ai, its own chatbot and agent app.
The current models are GLM-5.3, the flagship model for coding and agent tasks; GLM-5.3-Flash, a native multimodal model (it also reads images) at a much lower price; and GLM-5.3-FlashX, tuned for speed. All three read English and Chinese and accept a context of 1 million tokens (the amount of text a model can take in at once). A developer creates an API key on the Z.AI Open Platform and calls the RESTful API, the official Python or Java SDK, or an OpenAI SDK, because the API is compatible with OpenAI's. Features include a thinking mode, function calling, structured output, context caching and a built-in web search tool.
API use is billed per million input and output tokens. The GLM Coding Plan is a monthly subscription for use in coding tools.