MLB data for modelers.
Pinnacle full-game, first-5-innings and first-inning odds, pre-game features and line movements. Every figure on these pages is measured on the file you download.
Full-Game Odds
Full-game total and run line, both prices, the exact time of every snapshot, the final score and the settled result. Every price was captured before the actual first pitch. One clean file, ready for pandas.
First 5 Innings
The starting pitchers' market: Pinnacle F5 line, over and under prices, exact snapshot time, score after 5 innings and settled result. Every price was captured before the actual first pitch.
First inning · NRFI
A run in the first inning or not. Pinnacle YRFI and NRFI prices, each team's real first-inning runs, settled result — every price checked, game by game, against the official first-pitch time.
Modeling Features
Pinnacle lines (first and last pre-game snapshot), starting pitchers, bullpen, 7-day form, matchups, park factor, weather — and the real scores to predict. Every column was audited for whether it was known before the game.
Line Movements
Every Pinnacle price snapshot with its exact time and lead before the game, on three markets: full-game total, run line and F5. In 2026 the line is followed through the day; in 2023-2025 totals and run lines were densified (median 5 and 4 snapshots per game).
MLB Complete Pack
The five MLB datasets, each in its own folder with its README: full-game odds, F5, first inning, modeling features and line movements. Everything joins on game_pk.
