Deep Cogito: Cogito V2 Preview Llama 405B API

Access Deep Cogito: Cogito V2 Preview Llama 405B from Deep Cogito using Puter.js AI API.

Get Started

Model Card

Cogito v2 405B is a dense large-scale model built on Llama architecture, optimized for high performance across varied hardware setups. It offers hybrid reasoning capabilities and is designed to approach frontier-level intelligence within its size class through improved non-reasoning mode intuition.

Context Window

N/A

tokens

Max Output

N/A

tokens

Input Cost

$3.5

per million tokens

Output Cost

$3.5

per million tokens

API Usage Example

Add Deep Cogito: Cogito V2 Preview Llama 405B 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: "deepcogito/cogito-v2-preview-llama-405b"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add Deep Cogito: Cogito V2 Preview Llama 405B to your app without worrying about API keys or setup.

Read the Docs View Tutorials