NVIDIA

NVIDIA: Llama 3.1 Nemotron 70B Instruct

nvidia/llama-3.1-nemotron-70b-instruct

Access Llama 3.1 Nemotron 70B Instruct from NVIDIA using Puter.js AI API.

Get Started
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "nvidia/llama-3.1-nemotron-70b-instruct"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "nvidia/llama-3.1-nemotron-70b-instruct"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="nvidia/llama-3.1-nemotron-70b-instruct",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "nvidia/llama-3.1-nemotron-70b-instruct",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Llama 3.1 Nemotron 70B Instruct is a 70B parameter LLM customized by NVIDIA using RLHF to improve response helpfulness, achieving top rankings on alignment benchmarks like Arena Hard and AlpacaEval 2 LC. It supports a 128K token context and is optimized for conversational AI and instruction-following tasks.

Context Window 131K

tokens

Max Output 16K

tokens

Input Cost $1.2

per million tokens

Output Cost $1.2

per million tokens

Release Date Oct 1, 2024

 

Output Speed 47

tokens / sec

Latency 0.34s

time to first token

Model Playground

Try Llama 3.1 Nemotron 70B Instruct instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat nvidia/llama-3.1-nemotron-70b-instruct
NVIDIA
Chat with Llama 3.1 Nemotron 70B Instruct
Powered by Puter.js

Benchmarks

How Llama 3.1 Nemotron 70B Instruct performs on standard evaluations.

Artificial Analysis
Intelligence Index
13.4
Better than 30% of tracked models
Artificial Analysis
Coding Index
10.8
Better than 26% of tracked models
Artificial Analysis
Math Index
11.0
Better than 14% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
46.5%
Humanity's Last Exam Cross-domain reasoning
4.6%
LiveCodeBench Recent coding problems
16.9%
SciCode Scientific programming
23.3%
MATH-500 Competition math
73.3%
AIME 2024 Advanced math exam
24.7%
AIME 2025 Advanced math exam
11.0%
IFBench Instruction following
30.7%
LCR Long-context reasoning
7.0%
Terminal-Bench Hard Agentic terminal tasks
4.5%
τ²-Bench Tool use / agents
23.1%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Llama 3.1 Nemotron 70B Instruct?

You can access Llama 3.1 Nemotron 70B Instruct by NVIDIA through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Llama 3.1 Nemotron 70B Instruct free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Llama 3.1 Nemotron 70B Instruct to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Llama 3.1 Nemotron 70B Instruct?
Pricing for Llama 3.1 Nemotron 70B Instruct is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$1.2
Output$1.2
Who created Llama 3.1 Nemotron 70B Instruct?

Llama 3.1 Nemotron 70B Instruct was created by NVIDIA and released on Oct 1, 2024.

What is the context window of Llama 3.1 Nemotron 70B Instruct?

Llama 3.1 Nemotron 70B Instruct supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Llama 3.1 Nemotron 70B Instruct?

Llama 3.1 Nemotron 70B Instruct can generate up to 16K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Llama 3.1 Nemotron 70B Instruct API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Llama 3.1 Nemotron 70B Instruct to your app without worrying about API keys or setup.

Read the Docs View Tutorials