Scan your repo for retiring models
Paste a public GitHub repo. We look for AI model IDs in your code and flag the ones that are retiring, retired or had price changes.
What this does — and its limits
Public GitHub repos only; we never ask for tokens. We don’t save your code to a database. Files are read in memory; only short matched lines are kept in server memory for about 10 minutes. Detection is plain string-matching against hundreds of known model IDs, so it can miss dynamic names (e.g. built from variables or env vars), aliases we don’t know, and files beyond our size caps (300 files, 300 KB each). Retirement flags come from OpenRouter expiration dates, events ModelCanary has recorded, and a curated list — always confirm on the provider’s deprecation page. No AI is used.
Email digest: coming soon
Sign up and we’ll send a summary of AI API deprecations, price changes and outages once it starts.
We’ll email you a link to confirm your address. Nothing else is sent until you confirm. Email only, no tracking. By subscribing you agree to the Privacy Policy; unsubscribe any time.