Experience top-notch Football predictions with our Football Prediction API. Developed and continually improving since 2017, our state-of-the-art model offers accurate predictions for 1350+ leagues and 20+ prediction markets. Available as a supplement to our Football API.
In the realm of football predictions, precision and reliability are paramount. Our Football Prediction Service stands as a pinnacle of excellence, meticulously crafted and continuously refined since its inception in 2017. Here’s why it should be your go-to choice:
Our Prediction Service isn’t just a tool; it’s a gateway to unparalleled football insights and informed betting decision-making. Whether you’re a seasoned bettor or a passionate football fan, elevate your football experience with accurate, data-driven match predictions.
Start your free trial now
Our Predictions API offers extensive coverage across 1,350+ football leagues worldwide. Including major competitions like the UEFA Champions League, Premier League and La Liga. Whether you’re building a global betting platform, a fantasy app, or a data-driven football site, our Football API ensures you never miss a match.
Ready to see what’s possible?
Explore how you can integrate predictions with real impact.
Need practical examples? Check out our How-to use our Prediciton API guide for more information.
Check our league coverageOur Football Predictions API is sold as an exclusive add-on for our football plans.
Just like our football plans, we offer a 14-day free trial with every option.
Prediction API add-on for our Euro Plan
Prediction API add-on for our World Plan
Prediction API add-on for our Enterprise Plan
We also offer our Football Prediction API as an add-on for custom plans.
Request quote
{
"data": {
"id": 18535329,
"sport_id": 1,
"league_id": 8,
"season_id": 19734,
"stage_id": 77457864,
"group_id": null,
"aggregate_id": null,
"round_id": 274692,
"state_id": 5,
"venue_id": 281313,
"name": "Tottenham Hotspur vs Chelsea",
"starting_at": "2023-02-26 13:30:00",
"result_info": "Tottenham Hotspur won after full-time.",
"leg": "1/1",
"details": null,
"length": 90,
"placeholder": false,
"has_odds": true,
"starting_at_timestamp": 1677418200,
"predictions": [
{
"id": 4557974,
"fixture_id": 18535329,
"predictions": {
"yes": 55.6,
"no": 44.4
},
"type_id": 235,
"type": {
"id": 235,
"name": "Over/Under 2.5 Probability",
"code": "over-under-2_5-probability",
"developer_name": "OVER_UNDER_2_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557980,
"fixture_id": 18535329,
"predictions": {
"yes": 47.78,
"no": 52.22
},
"type_id": 331,
"type": {
"id": 331,
"name": "Home Over/Under 1.5 Probability",
"code": "home-over-under-1_5_probability",
"developer_name": "HOME_OVER_UNDER_1_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557976,
"fixture_id": 18535329,
"predictions": {
"scores": {
"0-0": 5.91,
"0-1": 6.9,
"0-2": 4.14,
"0-3": 1.62,
"1-0": 9.54,
"1-1": 11.15,
"1-2": 6.8,
"1-3": 2.63,
"2-0": 7.07,
"2-1": 9.14,
"2-2": 5.53,
"2-3": 2.4,
"3-0": 4.12,
"3-1": 4.91,
"3-2": 3.24,
"3-3": 1.38,
"Other_1": 9.75,
"Other_2": 3.51,
"Other_X": 0.23
}
},
"type_id": 240,
"type": {
"id": 240,
"name": "Correct Score Probability",
"code": "correct-score-probability",
"developer_name": "CORRECT_SCORE_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557968,
"fixture_id": 18535329,
"predictions": {
"yes": 57.7,
"no": 42.3
},
"type_id": 231,
"type": {
"id": 231,
"name": "Both Teams To Score Probability",
"code": "both-teams-to-score-probability",
"developer_name": "BTTS_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557972,
"fixture_id": 18535329,
"predictions": {
"home": 32.41,
"away": 25.21,
"draw": 42.38
},
"type_id": 233,
"type": {
"id": 233,
"name": "First Half Winner Probability",
"code": "first-half-winner",
"developer_name": "FIRST_HALF_WINNER_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557978,
"fixture_id": 18535329,
"predictions": {
"yes": 77.9,
"no": 22.1
},
"type_id": 334,
"type": {
"id": 334,
"name": "Home Over/Under 0.5 Probability",
"code": "home-over-under-0_5_probability",
"developer_name": "HOME_OVER_UNDER_0_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557969,
"fixture_id": 18535329,
"predictions": {
"home_home": 25.07,
"home_away": 3.01,
"home_draw": 4.93,
"away_home": 3,
"away_away": 16.66,
"away_draw": 5.85,
"draw_draw": 14.85,
"draw_home": 15.26,
"draw_away": 11.36
},
"type_id": 232,
"type": {
"id": 232,
"name": "Half Time/Full Time Probability",
"code": "half-time-full-time-probability",
"developer_name": "HTFT_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557982,
"fixture_id": 18535329,
"predictions": {
"yes": 36.84,
"no": 63.16
},
"type_id": 1585,
"type": {
"id": 1585,
"name": "Corners Over/Under 10.5 Probability",
"code": "corners-over-under-10_5-probability",
"developer_name": "CORNERS_OVER_UNDER_10_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557973,
"fixture_id": 18535329,
"predictions": {
"yes": 77.63,
"no": 22.37
},
"type_id": 234,
"type": {
"id": 234,
"name": "Over/Under 1.5 Probability",
"code": "over-under-1_5-probability",
"developer_name": "OVER_UNDER_1_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557975,
"fixture_id": 18535329,
"predictions": {
"yes": 33.79,
"no": 66.21
},
"type_id": 236,
"type": {
"id": 236,
"name": "Over/Under 3.5 Probability",
"code": "over-under-3_5_probability",
"developer_name": "OVER_UNDER_3_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557970,
"fixture_id": 18535329,
"predictions": {
"draw_home": 72.22,
"draw_away": 51.480000000000004,
"home_away": 76.30000000000001
},
"type_id": 239,
"type": {
"id": 239,
"name": "Double Chance Probability",
"code": "double_chance-probability",
"developer_name": "DOUBLE_CHANCE_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557967,
"fixture_id": 18535329,
"predictions": {
"home": 48.52,
"away": 27.78,
"draw": 23.7
},
"type_id": 237,
"type": {
"id": 237,
"name": "Fulltime Result Probability",
"code": "fulltime-result-probability",
"developer_name": "FULLTIME_RESULT_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557979,
"fixture_id": 18535329,
"predictions": {
"yes": 63.6,
"no": 36.4
},
"type_id": 333,
"type": {
"id": 333,
"name": "Away Over/Under 0.5 Probability",
"code": "away-over-under-0_5_probability",
"developer_name": "AWAY_OVER_UNDER_0_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557981,
"fixture_id": 18535329,
"predictions": {
"yes": 31.49,
"no": 68.51
},
"type_id": 328,
"type": {
"id": 328,
"name": "Away Over/Under 2.5 Probability",
"code": "away-over-under-2_5_probability",
"developer_name": "AWAY_OVER_UNDER_2_5_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4557971,
"fixture_id": 18535329,
"predictions": {
"home": 53.65,
"away": 40.44,
"draw": 5.91
},
"type_id": 238,
"type": {
"id": 238,
"name": "Team To Score First Probability",
"code": "team_to_score_first-probability",
"developer_name": "TEAM_TO_SCORE_FIRST_PROBABILITY",
"model_type": "prediction",
"stat_group": null
}
}
]
},
Using advanced machine learning techniques and historical data, our model accurately predicts the outcomes of future football matches, considering various factors such as team form, player injuries, head-to-head records, and more.
Predictions are available 21 days before the match starts. Daily updated based on the mentioned models
In addition to that, we also incorporate the player contribution model, which further enhances the accuracy of the Football predictions API. By analysing the performance of individual players and their impact on the team, we can better understand how they’ll contribute to the match’s final outcome. This model takes into account various metrics, such as the player’s recent form, their position, and their contribution to the team’s overall performance.
With our Football Predictions API, you’ll have access to a vast range of markets, including match-winner, double chance, total goals, and more. We’re constantly improving our model, adding new features to ensure you have access to the most accurate and up-to-date predictions possible.
More info about the model{
"data": [
{
"id": 1,
"fixture_id": 18054408,
"predictions": {
"bet": "1",
"fair_odd": 1.11,
"odd": 1.12,
"stake": 3.21,
"is_value": false
},
"type_id": 33
},
{
"id": 2,
"fixture_id": 18208090,
"predictions": {
"bet": "1",
"fair_odd": 3.64,
"odd": 3.9,
"stake": 0.52,
"is_value": false
},
"type_id": 33
},
{
"id": 3,
"fixture_id": 18211778,
"predictions": {
"bet": "1",
"fair_odd": 1.87,
"odd": 1.93,
"stake": 0.96,
"is_value": false
},
"type_id": 33
},
The Value Bet model processes thousands of historical odds data and market trends to find the best value opportunities. In other words: it compares bookmakers’ odds with each other and then gives you the best value bookmaker.
Our value bet models uses bookmakers odds to find the best betting option.
Using our value bet model, you can access valuable insights into the best bets, which can help you make better decisions. We continuously improve our model and test it by analysing past odds and value bets to make sure it works correctly
It’s important to note that we only use machine learning for both models to ensure the most accurate and reliable Football predictions.
How to beat the bookies?{
"data": [
{
"id": 1,
"league_id": 8,
"type_id": 241,
"data": {
"fulltime_result": -1.0275,
"away_over_under_0_5": null,
"away_over_under_1_5": -0.6777,
"both_teams_to_score": -0.7212,
"team_to_score_first": -0.8167,
"home_over_under_0_5": null,
"home_over_under_1_5": -0.6913,
"over_under_1_5": -0.5341,
"over_under_2_5": -0.7213,
"over_under_3_5": -0.7169,
"correct_score": -3.4172,
"ht_ft": -1.9327,
"fulltime_result_1st_half": -1.1103
},
"type": {
"id": 241,
"name": "Historical Log Loss",
"code": "historical-log-loss",
"developer_name": "HISTORICAL_LOG_LOSS",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 2,
"league_id": 8,
"type_id": 242,
"data": {
"fulltime_result": 0.59,
"away_over_under_0_5": null,
"away_over_under_1_5": null,
"both_teams_to_score": 0.52,
"team_to_score_first": 0.6,
"home_over_under_0_5": null,
"home_over_under_1_5": null,
"over_under_1_5": 0.43,
"over_under_2_5": 0.53,
"over_under_3_5": 0.59,
"correct_score": 0.16,
"ht_ft": 0.37,
"fulltime_result_1st_half": 0.44
},
"type": {
"id": 242,
"name": "Model Hit Ratio",
"code": "model-hit-ratio",
"developer_name": "MODEL_HIT_RATIO",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 3,
"league_id": 8,
"type_id": 243,
"data": {
"fulltime_result": "high",
"away_over_under_0_5": null,
"away_over_under_1_5": null,
"both_teams_to_score": "medium",
"team_to_score_first": "good",
"home_over_under_0_5": null,
"home_over_under_1_5": null,
"over_under_1_5": "poor",
"over_under_2_5": "good",
"over_under_3_5": "medium",
"correct_score": "high",
"ht_ft": "good",
"fulltime_result_1st_half": "medium"
},
"type": {
"id": 243,
"name": "Model Predictability",
"code": "model-predictability",
"developer_name": "MODEL_PREDICTABILITY",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 4,
"league_id": 8,
"type_id": 244,
"data": {
"fulltime_result": "unchanged",
"away_over_under_0_5": null,
"away_over_under_1_5": null,
"both_teams_to_score": "unchanged",
"team_to_score_first": "up",
"home_over_under_0_5": null,
"home_over_under_1_5": null,
"over_under_1_5": "down",
"over_under_2_5": "unchanged",
"over_under_3_5": "down",
"correct_score": "down",
"ht_ft": "unchanged",
"fulltime_result_1st_half": "down"
},
"type": {
"id": 244,
"name": "Model Predictive Power",
"code": "model-predictive-power",
"developer_name": "MODEL_PREDICTIVE_POWER",
"model_type": "prediction",
"stat_group": null
}
},
{
"id": 5,
"league_id": 8,
"type_id": 245,
"data": {
"fulltime_result": -0.9202,
"away_over_under_0_5": null,
"away_over_under_1_5": null,
"both_teams_to_score": -0.6907,
"team_to_score_first": -0.7641,
"home_over_under_0_5": null,
"home_over_under_1_5": null,
"over_under_1_5": -1.2013,
"over_under_2_5": -0.6718,
"over_under_3_5": -0.6886,
"correct_score": -2.7148,
"ht_ft": -1.8096,
"fulltime_result_1st_half": -1.0663
},
"type": {
"id": 245,
"name": "Models Log Loss",
"code": "models-log-loss",
"developer_name": "MODELS_LOG_LOSS",
"model_type": "prediction",
"stat_group": null
}
}
],
By providing full transparency into the accuracy of our model, users can have complete trust in the predictions they receive via the Football Predictions API.
You will have access to our prediction history and performance metrics to see our model’s accuracy over time. We continually monitor and refine our model to stay accurate and current.
Let’s look at the English Premier League to showcase the accuracy of our prediction model.
Predictability explained