AI Hub
All models
LLMOpen weights

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Access
Open weights
Released
April 7, 2025
License
LLAMA 3 1 community license
Parameters
253000000000
Knowledge cutoff
December 1, 2023
Output speed
42 tok/s
Latency (TTFT)
0.72s
API pricing
$0.60 in · $1.80 out / 1M tokens

Benchmarks

Compare Llama 3.1 Nemotron Ultra 253B v1 with

See all Llama 3.1 Nemotron Ultra 253B v1 alternatives →