MetricPulse: Token metric normalizer for AI model trackers

Helps developers reconcile token usage across different AI model data sources

Problem

Developers comparing model token usage on OpenRouter and the Ramp AI Index find the two use completely different definitions, making direct comparison impossible. Anyone selecting models or analyzing the market has to manually convert and guess definitions, leaving conclusions on shaky ground.

Solution

A lightweight tool that scrapes multiple public AI usage leaderboards, offers normalized token conversion (by model, vendor, and time), and highlights definitional differences between sources. Users can save their own comparison views and export charts.

Users

AI product managers, indie developers, investment/research analysts tracking model adoption trends

MVP

Integrate OpenRouter and Ramp AI Index as public sources; provide definition notes and normalized conversion; generate comparison charts by model/vendor; export PNG/CSV

Revenue

Free tier for the last 30 days; Pro at $12/mo for historical data, custom sources, and exports; API billing for research institutions

Why now

AI model adoption data is proliferating but definitions are messy, and model selection is frequent; indie developers can ship quickly with scrapers plus a frontend