Pass IndexThe State of AISign in

Llama-3.1-Nemotron-Ultra-253B-v1

NVIDIA-tuned Llama variant built for high-efficiency reasoning, safety, and enterprise-grade performance.

text → text · made by NVIDIA

$0.6$1.8per Mtok in / out
Nebius Token Factory

Sold by 2 ways

SellerLaneRate
Nebius Token Factory 0 ways$0.6per Mtok in$1.8per Mtok out
Nebius Token Factory aggregatornot on the seller's list todaystandard$0.6per Mtok in$1.8per Mtok outtokenfactory.nebius.com · read 2026-08-25
ElectronHub 0 ways$1.75per Mtok in$3.5per Mtok out
ElectronHub aggregatornot on the seller's list todaystandard$1.75per Mtok in$3.5per Mtok outapi.electronhub.ai · read 2026-08-29

About

Llama-3.1-Nemotron-Ultra-253B-v1 — a text model from NVIDIA.

It takes text and returns text, with a context window of 131,072 tokens. It was published in January 2025, trained on material up to December 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat.

Every current figure

Maker
NVIDIA
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Longest answer
128,000 tokens
Published
January 2025
Knowledge to
December 2024
Parameters
253 billion · read from its own name
Licence
not read

Known as 1 name

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1