API Rate Limit Increase Request

Hello NVIDIA Support Team,

I am writing to request a rate limit increase for my NVIDIA NIM API account.

- Current Limit: 40 RPM
- Requested Limit: 200 RPM (or the next available tier for individual developer use)

Project Details:
I'm developing a review aggregation website for nursing homes, which is used for website content and architecture building and requires concurrent calls to multiple models. Currently, even with exponential backoff, I frequently encounter 429 Too Many Requests errors, impacting development efficiency.

Account Information:
- NVIDIA Developer Account Email: clockworkboxl@gmail.com
- Primary Models Used: [例如 GLM, Kimi K2, Nemotron, Llama......]

This is for development/prototyping purposes only.

Thank you for your assistance!

i think that you don’t understud that is free test plan …. it’s not fair use to request 200 rpm … if you planed to used it in concurent workflow you should think about purchase some cloud hardware like nvidia allready purpose or maybe stop conccurency

in fact current 40 rpm is allready enougth to test model and they don’t need to upgrade that because api is allready dying every day because too much people are on it, so if you need more power you have to take a look at Brev.dev Console that allready exist and will help you and nvidia

hope that you understud FREE TESTING is not made for hardcore usage.

please allways remember the TOS of nvidia nim api

OK IC

Hi there,

Thanks for the detailed request.

I can elevate this internally to the team, as many others have had similar requests, but we cannot approve rate-limit increases directly from the forum.

I know that’s not the answer you are looking for, but I will do my best to ensure forum posters are heard in the decision-making process.

Thanks,

Aharpster