nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
Nvidia · → text
Llama-3.1-Nemotron-Ultra-253B is a 253 billion parameter reasoning-focused language model optimized for efficiency that excels at math, coding, and general instruction-following tasks while running on a single 8xH100 node.
Input$0.50 /M
Output$0.50 /M