NYU Langone LLM Inference Service

This service provides free access to LLAMA-3-70b-chat and other state-of-the-art open source language models through a simple OpenAI-style API. Running on H100 hardware, we offer SOTA and specialized models for members of the NYU Langone community. Access is available to approved NYU Langone users on the internal network, with plans to continue expanding model selection.