Model Card
Cogito v2 109B MoE is a sparse mixture-of-experts model built on Llama architecture that uses selective expert activation for efficient complex reasoning tasks. It features hybrid reasoning with both standard and self-reflective modes, achieving strong performance while being cost-effective at $0.18/$0.59 per million input/output tokens.
Context Window N/A
tokens
Max Output N/A
tokens
Input Cost $0.18
per million tokens
Output Cost $0.59
per million tokens
Release Date May 1, 2025
API Usage Example
Add AI to your app with just a few lines of code.
No API keys, no backend, no configuration required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Frequently Asked Questions
The Cogito V2 Preview Llama 109B API gives you access to Deep Cogito's chat model through Puter.js. With just a few lines of JavaScript, you can integrate Cogito V2 Preview Llama 109B into any web app or Node.js project — no API keys, no backend, and no configuration required.
Cogito V2 Preview Llama 109B was created by Deep Cogito and released on May 1, 2025.
| Price per 1M tokens | |
|---|---|
| Input | $0.18 |
| Output | $0.59 |
You can access the Cogito V2 Preview Llama 109B API with just a few lines of JavaScript — no API keys, no backend, and no configuration required. Include the Puter.js library in your project and start making calls right away. For more details, check out our documentation.
Yes — the Cogito V2 Preview Llama 109B 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 AI to your application without worrying about API keys or setup.
Explore Models View Tutorials