Why I built EcoPrompt: A zero-telemetry Chrome extension to measure LLM compute costs

Description and use

<p>GenAI interfaces like <strong>ChatGPT</strong>, <strong>Google Gemini</strong>, and <strong>Claude</strong> are clean and instant. But behind every prompt lies power-dense GPU clusters drawing electricity and evaporative cooling water.</p> <p>To bring physical transparency to AI interactions without tracking users or slowing down the browser, I built <strong>EcoPrompt</strong> — an open-source, 100% client-side Chrome extension (Manifest V3).</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.

Problem

<p>GenAI interfaces like <strong>ChatGPT</strong>, <strong>Google Gemini</strong>, and <strong>Claude</strong> are clean and instant. But behind every prompt lies power-dense GPU clusters drawing electricity and evaporative cooling water.</p> <p>To bring physical transparency to AI interactions without tracking users or slowing down the browser, I built <strong>EcoPrompt</strong> — an open-source, 100% client-side Chrome extension (Manifest V3).</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.

Outcome

<p>GenAI interfaces like <strong>ChatGPT</strong>, <strong>Google Gemini</strong>, and <strong>Claude</strong> are clean and instant. But behind every prompt lies power-dense GPU clusters drawing electricity and evaporative cooling water.</p> <p>To bring physical transparency to AI interactions without tracking users or slowing down the browser, I built <strong>EcoPrompt</strong> — an open-source, 100% client-side Chrome extension (Manifest V3).</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.

Evidence

Why I built EcoPrompt: A zero-telemetry Chrome extension to measure LLM compute costs

Source