Llama 3.1 Nemotron Ultra 253B v1

by NVIDIA

Released · 20 days after Llama 3.3 Nemotron Super 49B v1

Key info

Context window
Max output
Input price
$0.60 /1M
Output price
$1.80 /1M

Prices are the median across providers tracked by Artificial Analysis, not Opper billing.

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#412 of 597 LLMs
TierEfficient
Output speed52 tok/s
First token0.69s
Intelligence Index8.9
Math Index63.7
Reasoning & knowledge
MMLU-Pro
83%
GPQA Diamond
73%
Humanity's Last Exam
7%
Long-context reasoning
8%
Coding
LiveCodeBench
64%
SciCode
35%
Agentic & tool use
Terminal-Bench Hard
2%
τ²-Bench Telecom
11%
Math & instruction following
AIME 2025
64%
IFBench
38%

Available routes

No routes currently available — Llama 3.1 Nemotron Ultra 253B v1 isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Available models from NVIDIA

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Llama 3.1 Nemotron Ultra 253B v1 — release date & benchmarks | Opper AI