Predict where used-car prices are heading

Hey hunters 👋

Quick context on why I built this:

Every used-car pricing tool a dealer uses today (Manheim Market Report, KBB, Black Book, vAuto) answers one question — "what did this vehicle sell for last week?" That's a backward-looking average. In a stable market it's fine. In 2024–2026 it has been anything but.

I watched dealers buy used trucks at peak in Q1 2025 because last week's data still looked great. Three months later prices corrected 12% and they were stuck on inventory.

CarCast answers a different question: where are prices heading?

We forecast 30 and 60 days out across 300+ used-vehicle segments — pickup trucks, SUVs, sedans, EVs, even classic cars — and each forecast comes with P10/P50/P90 confidence bands and a Rising / Stable / Softening trend classification. Powered by a 200M-parameter foundation model for time-series forecasting, retrained weekly against live dealer-listing data plus the Manheim Used Vehicle Value Index and the BLS used-car CPI.

Free plan covers 5 segments; Pro at $149/mo unlocks all 300+. The product is live at carcast.ai today, happy for early hunters to kick the tires and tell me what's wrong.

A few things I'd genuinely love feedback on before we go live:

1. Which vehicle segments do you wish we covered that we don't?

2. What's broken in your current pricing tool that you'd love a forecaster to fix?

3. Is the 60-day horizon the right length, or do you need 90 / 120?

Drop a comment below or DM me.

Roast me. I can take it.

— Rick