Hello NVIDIA Team,
I am currently developing and testing a project that involves deep analysis and processing of long-context narratives using the Kimi K2.6 model via NVIDIA NIM.
The current hard limit of 30 requests per hour (RPH) is highly restrictive for my workflow, as generating complex sequential responses and debugging token efficiency requires a much higher frequency of interactions.
Could you please consider increasing the hourly rate limit for the Kimi K2.6 model on my account? Raising it to 60–100 requests per hour would allow me to conduct proper testing and complete my evaluation without constant interruptions.
Thank you for your support and for providing access to these incredible models.