NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano 30B A3B is a cutting-edge small language Mixture-of-Experts (MoE) model designed for developers seeking maximum compute efficiency and accuracy. It's ideal for building specialized agentic AI systems, providing a robust foundation for innovative applications. This model is fully open, featuring open-weights, datasets, and recipes. This transparency allows developers to easily customize, optimize, and deploy the model on their own infrastructure, ensuring maximum privacy and security. With a generous context window of 262K tokens and a max output of 262K tokens, it supports extensive interactions. Pricing is competitive at $0.06/$0.24 per 1M tokens (input/output), available through a FREE access tier. Capabilities include streaming, functions, and long context. Note: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.