Risk Score
API Reference
Risk Score
Calculate the delay risk score for a specific flight.
GET
Risk Score
Overview
The core endpoint. Returns a Risk Score (0–100) for a given route, airline, and date, along with historical statistics, weather data, risk drivers, and an optional news feed.Request
IATA code of the departure airport (e.g.
FCO, LHR, JFK).IATA code of the arrival airport.
IATA airline code (e.g.
AZ for ITA Airways, BA for British Airways).Departure date in
YYYY-MM-DD format.If
true, includes a live news feed of disruption reports for the route in the response.Your API key.
Response
Risk Score from 0 (lowest risk) to 100 (highest risk).
Statistical-only score before ML blending.
ML model prediction (0–100).
null if model unavailable.Whether the ML model contributed to this score.
Human-readable risk label:
Low, Moderate, High, or Very High.One-sentence actionable recommendation based on the risk level and top driver.
Echo of the query parameters:
origin, destination, airline, flight_date.Historical statistics for this route/airline combination.
Sorted list of risk factor contributions (highest first).
Weather risk at the departure airport for the requested date.
Weather risk at the arrival airport. Same structure as
weather_dep.Which data tier was used:
exact (origin+dest+airline match), route_any_airline (fallback — any airline on the route), or no_data.Airline metadata:
name (full name), country.Airport metadata for origin:
name, city, country.Airport metadata for destination:
name, city, country.Present only when
news=true. Array of disruption reports — see Route News for the item schema.Example
Response
Score interpretation
| Score | Label | Recommendation |
|---|---|---|
| 0–30 | Low | Safe to book, low historical delay rate |
| 31–55 | Moderate | Some risk — consider flexible fare and monitor closer to departure |
| 56–74 | High | Elevated risk — check alternatives or add buffer time |
| 75–100 | Very High | High disruption probability — evaluate alternatives |
Scoring formula
confidence_pct < 50), keeping the score grounded in observed outcomes.