NVIDIA: Nemotron 3 Nano 30B A3B API

Access NVIDIA: Nemotron 3 Nano 30B A3B from NVIDIA using Puter.js AI API.

Get Started

Model Card

Nemotron 3 Nano 30B A3B is a 31.6B total parameter (3.2B active) hybrid Mamba-Transformer MoE model trained from scratch by NVIDIA with a 1M token context window. It offers up to 3.3x higher throughput than comparable models and supports configurable reasoning traces for both agentic and conversational tasks.

Context Window

N/A

tokens

Max Output

262,144

tokens

Input Cost

$0.06

per million tokens

Output Cost

$0.24

per million tokens

API Usage Example

Add NVIDIA: Nemotron 3 Nano 30B A3B 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: "nvidia/nemotron-3-nano-30b-a3b"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add NVIDIA: Nemotron 3 Nano 30B A3B to your app without worrying about API keys or setup.

Read the Docs View Tutorials