Teams can efficiently call open-source models through API on Zettabyte’s NVIDIA H100, H200, B200 and B300 GPUs. Model-as-a-Service hosts popular open weight and open-source models, ready to call through an API and run on Zettabyte’s GPUs. NVIDIA H100 is available today, with pricing from US$1.99 per GPU-hour depending on needs and scale. Zettabyte offers three ways to access capacity: Short-Term Capacity, Reserved Clusters, and Private Cloud.
