Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js
Tutorials

Free, Unlimited Video Analysis API

On this page

This tutorial demonstrates how to perform video analysis using Puter.js. With Puter.js, you get access to powerful AI video analysis capabilities that you can add to your app without API keys or setup.

Puter is the pioneer of the User-Pays model, enabling developers to integrate AI-powered video analysis into their apps while users cover their own usage costs. This approach lets you offer video understanding features without managing API keys or backend infrastructure.

Getting Started

To use Puter.js, import our npm module in your project:

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

Or alternatively, add our script via CDN if you are working directly with HTML, simply add it to the <head> or <body> section of your code:

<script src="https://js.puter.com/v2/"></script>

That's it - you're ready to start analyzing videos.

Example 1: Basic Video Analysis

To analyze a video, pass a video URL as the second argument to puter.ai.chat(). Here's a complete working example:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai
            .chat(`What do you see?`, `https://assets.puter.site/puppy.mp4`, {
                model: "rekaai/reka-edge",
            })
            .then(puter.print);
    </script>
</body>
</html>

This sends the video to the Reka Edge model, which will describe what it sees in the video.

Example 2: Using a Different Model

You can use different models for video analysis. Here's the same example using Google's Gemini 3.5 Flash:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai
            .chat(`What do you see?`, `https://assets.puter.site/puppy.mp4`, {
                model: "google/gemini-3.5-flash",
            })
            .then(puter.print);
    </script>
</body>
</html>

Example 3: Analyze Multiple Media

You can pass multiple inputs - both images and videos - as an array. The model will analyze all of them together:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai
            .chat("Describe these", [
                "https://assets.puter.site/doge.jpeg",
                "https://assets.puter.site/puppy.mp4",
            ], { model: "google/gemini-3.5-flash" })
            .then(puter.print);
    </script>
</body>
</html>

List of Models

You can use the following models for video analysis:

rekaai/reka-edge
google/gemini-3.5-flash
google/gemini-3.1-pro-preview
google/gemini-3-flash-preview
google/gemini-2.5-pro
google/gemini-2.5-flash-lite
google/gemini-2.5-flash
google/gemini-2.0-flash-lite
google/gemini-2.0-flash

Conclusion

That's it! You now have free, unlimited access to video analysis capabilities using Puter.js. Analyze videos, combine them with images, and use different AI models - all without API keys or backend servers.

Ship a Full-Stack App with One Prompt

Give this to your AI Build an AI chat app using Puter.js