GLM 5.2 is now live on CloudBase.
For building AI mini programs on your own, CloudBase is the place.
Why it's convenient
- A Token Plan that comes with cloud resources — ship code right after writing it, no more switching platforms
- HY3, GLM 5.2, DeepSeek, Kimi and Qwen all in one pool — switching models is just one parameter
- Calls within the standard plan: cloud resources + AI for one price
- Even the Personal plan supports models like HY3 and Qwen3.5
Other Token Plans only give you tokens. CloudBase also gives you a place to ship.
Two ways to use AI
1. Plug it into the AI dev tool you already use
CloudBase console → AI → enable the text-generation model.
Copy the Base URL and API Key, and plug the model into WorkBuddy, CodeBuddy, Cursor, or any AI coding tool. Use it like any OpenAI-compatible model — charges go through the CloudBase console's resource-point pool, without touching your existing tool configuration.
2. Call it directly in a full-stack app
If you're building a mini program, web app, official account, or support bot, call AI as a CloudBase capability — a few lines of SDK code give you streaming output, no separate backend needed.
Try it and tell us how it feels in the comments.
