NFL playoff odds API: division, wild card and No. 1 seed probabilities

A Monte Carlo simulator for the NFL. It plays the rest of the season on the real schedule, 20,000 times by default, and returns playoff, division, wild card and No. 1 seed probabilities for all 32 teams, with projected win totals.

Open on Apify API reference Input schema

What it returns

How the model works

A 17-game season is a small sample, so the model leans on point differential rather than the raw record: by default 65% of the strength estimate comes from points scored and allowed. The estimate is then regressed towards .500 as if each team had six extra games at a .500 record.

Every simulated season redraws each team's strength around that estimate, because 17 games say little about true talent and a model without that step is far too confident. Each game adds a home-field term worth roughly a 55% win rate between evenly matched teams, and a small tie probability, with a tie counted as half a win.

Before a single game is played the model is a pure prior: last season's point differential, shrunk towards average, run through this year's schedule. Its preseason numbers are deliberately timid, and they sharpen as real results replace the prior.

Default settings

All of them are inputs you can change, and two of the ready-made examples show what happens when you switch parts of the model off.

10 ready-made examples

Each one is a saved configuration with its input filled in. Open it on Apify and run it in one click.

Common questions

Why are the preseason probabilities so close together?

Because at that point the model only knows last season's scoring margin and this season's schedule. It does not use camp reports, depth charts or injury news, so it does not claim more conviction than that information supports.

Why point differential instead of wins?

Over a short season, point differential predicts future wins better than the win-loss record, which is heavily affected by close games.

How do I track how the odds move through the season?

Set a dataset name in the archive option and run the model on a schedule. Every run appends to that dataset, and Apify keeps named datasets instead of deleting them after a few days.

Can I compare it with sportsbook futures?

Yes. Pass implied probabilities for playoff or division markets and each team comes back with the model probability, the market probability, the edge and a capped stake suggestion.

Other models