Hitting rpm limits on certain models

[ytsuprem9]

I’m pretty new to Nvidia NIM, and I noticed there’s a 40 RPM limit. I loaded up GLM and tried it a few times, testing things like 10 burst requests just to see its responses. Then I hit my RPM limit, even though I was under 40 RPM at the time. I waited 5 minutes but was still hitting the limit, and even the next day I kept running into it despite only using it a few times. I’m wondering if this is a bug or if there are certain limits for specific models.