Llama 3.1 Nemotron Instruct 70B

by NVIDIA

Released

Key info

Context window
Max output
Input price
$1.20 /1M
Output price
$1.20 /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#451 of 597 LLMs
TierEfficient
Output speed88 tok/s
First token6.44s
Intelligence Index7.4
Math Index11.0
Reasoning & knowledge
MMLU-Pro
69%
GPQA Diamond
47%
Humanity's Last Exam
4%
Long-context reasoning
7%
Coding
LiveCodeBench
17%
SciCode
23%
Agentic & tool use
Terminal-Bench Hard
5%
τ²-Bench Telecom
23%
Math & instruction following
AIME 2025
11%
IFBench
31%

Available routes

No routes currently available — Llama 3.1 Nemotron Instruct 70B 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 Instruct 70B — release date & benchmarks | Opper AI