NVIDIA Nemotron 3 Ultra is now available on Amazon SageMaker JumpStart, the platform ML model hub. The integration allows AWS customers to deploy the large language model with a single click and run inference or fine-tuning jobs on SageMaker managed infrastructure.
Nemotron 3 Ultra is designed for enterprise workloads requiring high-quality text generation, reasoning, and instruction following. By hosting it on SageMaker, organizations can keep data within their AWS environment while accessing the model through standard APIs.
The listing is part of a broader trend of frontier models becoming available on cloud marketplaces, reducing the barrier for enterprises that want to evaluate advanced AI without managing their own GPU clusters. Pricing follows standard SageMaker inference rates based on instance type and duration.