Prime Intellect: INTELLECT-3 API

Access Prime Intellect: INTELLECT-3 from Prime Intellect using Puter.js AI API.

Get Started

Model Card

INTELLECT-3 is a 106B parameter open-source Mixture-of-Experts reasoning model (12B active parameters) from Prime Intellect, trained using large-scale reinforcement learning on top of GLM-4.5-Air-Base. It achieves state-of-the-art performance for its size across math, code, science, and reasoning benchmarks, scoring 90.8% on AIME 2024 and outperforming many larger frontier models.

Context Window

N/A

tokens

Max Output

131,072

tokens

Input Cost

$0.2

per million tokens

Output Cost

$1.1

per million tokens

API Usage Example

Add Prime Intellect: INTELLECT-3 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: "prime-intellect/intellect-3"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add Prime Intellect: INTELLECT-3 to your app without worrying about API keys or setup.

Read the Docs View Tutorials