Free, Unlimited Gemini API

Nariman Jelveh

Updated: November 30, 2025

On this page

This tutorial will show you how to use Puter.js to access Gemini's powerful language models for free, without any API keys or usage restrictions. Using Puter.js, you can leverage models like Gemini 2.5 Flash, Gemini 2.0 Flash, Gemini 3 Pro, and Gemini 2.5 Pro for various tasks like text generation, image analysis, and complex reasoning, text and code generation, and more.

Puter is the pioneer of the "User-Pays" model, which allows developers to incorporate AI capabilities into their applications while users cover their own usage costs. This model enables developers to access advanced AI capabilities for free, without any API keys or sign-ups.

Getting Started

Puter.js works without any API keys or sign-ups. To start using Puter.js, include the following script tag in your HTML file, either in the <head> or <body> section:

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

You're now ready to use Puter.js for free access to Gemini capabilities. No API keys or sign-ups are required.

Example 1: Basic Text Generation with Gemini 2.5 Flash

Here's a simple example showing how to generate text using Gemini 2.5 Flash:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain the concept of black holes in simple terms", {
            model: 'gemini-2.5-flash'
        }).then(response => {
            puter.print(response);
        });
    </script>
</body>
</html>

Example 2: Using Gemini 3 Pro

For comparison, here's how to use Gemini 3 Pro:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("What are the major differences between renewable and non-renewable energy sources?", {
            model: 'gemini-3-pro-preview'
        }).then(response => {
            puter.print(response);
        });
    </script>
</body>
</html>

Example 3: Streaming Responses

For longer responses, use streaming to get results in real-time:

<html>
<body>
    <div id="output"></div>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        async function streamResponses() {
            const outputDiv = document.getElementById('output');
            
            // Gemini 2.5 Flash with streaming
            outputDiv.innerHTML += '<h2>Gemini 2.5 Flash Response:</h2>';
            const flashResponse = await puter.ai.chat(
                "Explain the process of photosynthesis in detail", 
                {
                    model: 'gemini-2.5-flash',
                    stream: true
                }
            );
            
            for await (const part of flashResponse) {
                if (part?.text) {
                    outputDiv.innerHTML += part.text.replaceAll('\n', '<br>');
                }
            }            
        }

        streamResponses();
    </script>
</body>
</html>

Example 4: Comparing Models

Here's how to compare responses from both Gemini models:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
    (async () => {
        // Gemini 3 Pro
        const pro3_resp = await puter.ai.chat(
            'Tell me something interesting about quantum mechanics.',
            {model: 'gemini-3-pro-preview', stream: true}
        );
        puter.print('<h2>Gemini 3 Pro Response:</h2>');
        for await (const part of pro3_resp) {
            if (part?.text) {
                puter.print(part.text.replaceAll('\n', '<br>'));
            }
        }

        // Gemini 2.5 Pro
        const pro_resp = await puter.ai.chat(
            'Tell me something interesting about quantum mechanics.',
            {model: 'gemini-2.5-pro', stream: true}
        );
        puter.print('<h2>Gemini 2.5 Pro Response:</h2>');
        for await (const part of pro_resp) {
            if (part?.text) {
                puter.print(part.text.replaceAll('\n', '<br>'));
            }
        }

        // Gemini 2.5 Flash
        const flash_resp = await puter.ai.chat(
            'Tell me something interesting about quantum mechanics.',
            {model: 'gemini-2.5-flash', stream: true}
        );
        puter.print('<h2>Gemini 2.5 Flash Response:</h2>');
        for await (const part of flash_resp) {
            if (part?.text) {
                puter.print(part.text.replaceAll('\n', '<br>'));
            }
        }
    })();
    </script>
</body>
</html>

Example 5: Image Analysis

To analyze images, simply provide an image URL to puter.ai.chat():

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <img src="https://assets.puter.site/doge.jpeg" id="image">
    <script>
        puter.ai.chat(
            "What do you see in this image?",
            "https://assets.puter.site/doge.jpeg",
            { model: 'gemini-2.5-flash' }
        ).then(response => {
            puter.print(response);
        });
    </script>
</body>
</html>

All models

The following Gemini models are available for free use with Puter.js:

gemini-3-pro-preview
gemini-2.5-pro
gemini-2.5-flash-lite
gemini-2.5-flash
gemini-2.0-flash-lite
gemini-2.0-flash
gemini-1.5-flash

Puter.js support for Gemini is not limited to text generation, you can also use it for image generation via Gemini 2.5 Flash/3 Pro Image, also known as Nano Banana! Please refer to the Gemini Image Generation tutorial for more information.

That's it! You now have free access to Gemini's powerful language models using Puter.js. This allows you to add sophisticated AI capabilities to your web applications without worrying about API keys or usage limits.

Free, Serverless AI and Cloud

Start creating powerful web applications with Puter.js in seconds!

Get Started Now

Read the Docs • Try the Playground