NousResearch: Hermes 2 Pro - Llama-3 8B API

Access NousResearch: Hermes 2 Pro - Llama-3 8B from Nous Research using Puter.js AI API.

Get Started

Model Card

Hermes 2 Pro Llama 3 8B is an 8B parameter model fine-tuned on Meta's Llama 3, optimized for function calling (90% accuracy) and structured JSON outputs (84% accuracy). It features dedicated tool-call parsing tokens for agentic capabilities and outperforms Llama-3 8B Instruct on AGIEval, TruthfulQA, and BigBench benchmarks.

Context Window

N/A

tokens

Max Output

2,048

tokens

Input Cost

$0.03

per million tokens

Output Cost

$0.08

per million tokens

API Usage Example

Add NousResearch: Hermes 2 Pro - Llama-3 8B to your app with just a few lines of code.
No API keys, no backend, no configuration required.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "nousresearch/hermes-2-pro-llama-3-8b"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add NousResearch: Hermes 2 Pro - Llama-3 8B to your app without worrying about API keys or setup.

Read the Docs View Tutorials