As of mid-2026, large language models are increasingly accessed via hosted APIs rather than local deployments, and GLM-5.2 stands out for its OpenAI-compatible interface, offering advanced capabilities like configurable reasoning effort, robust function calling, and extended context retrieval. In this hands-on tutorial, we work with GLM-5.2 via its hosted, OpenAI-compatible API—a practical choice for developers who want to avoid the overhead of running the full model locally. Below, we walk through the core steps: configuring multiple provider options, securely loading API keys, and building a reusable chat wrapper that supports normal chat, thinking mode, streaming, tool calling, and token tracking. We then move beyond a simple chatbot example and test the model in real-world scenarios, demonstrating how to leverage reasoning effort, function calling, and long-context retrieval for more sophisticated AI workflows.