GLM 5.2 API returns HTTP 429 for every request while other models work

AI & Data Science NVIDIA NIM Models
1

Hello,

I am experiencing an issue with the GLM 5.2 model on NVIDIA Build.

Every request to GLM 5.2 returns HTTP 429 Too Many Requests, even when I send only a single request. I have also tested with tools disabled, and the issue still occurs.

Other models (such as MiniMax M3 and Qwen) work normally using the same API key and the same client.

Could you please check if there is an issue with the GLM 5.2 endpoint or my account?

Thank you.

2

true , and even if it work sometimes its very dam slow like i am running it on my local gpu