How much integration work is this, really?

One authenticated GET per route — no request body, no PII, ~50ms from cache. Most teams start by rendering a risk column on the dispatch board, then add the webhook for threshold events. A sandbox key takes minutes; there is no procurement call to book.

What does the API cost?

The sandbox is free on live data, no card. Production runs on request volume: Starter $2,000/month, Pro $5,000/month with SLA and webhooks. The per-FIR detailed endpoint ( /v2/route/risk/detailed ) ships on Enterprise. Full grid on the pricing page .

How fresh are the scores?

Scores recompute every 5–30 minutes across 334 FIRs scored daily. Every response carries scored_at so your board can cache and invalidate correctly, and confidence so you can see how solid the ground is under each number.

Does this replace NOTAMs or our OCC tooling?

No. It is an early-warning input, not a recommendation engine. NOTAMs, SIGMETs, AIPs, and communications from aviation authorities remain the authoritative sources; the feed tells the duty desk where to look first, and the dispatcher decides.

What happens on a route you don’t cover?

The response says so explicitly: coverage.status = "out_of_scope" with score: null — never a guessed number. Branch on the coverage object and the board shows "not monitored" instead of false calm.

What if a score is wrong?

It is a numerical index validated against a documented event ground truth, with a per-score confidence value and a scoring_version on every score. Treat it as one structured input alongside weather, fuel, and permits; the filing decision stays with your dispatcher.

Can ops staff use it without an integration project?

Yes — the same engine runs as the Console, a signed-in workspace: check any leg, keep a dated record of the reroute rationale. Solo $99/month, Team $399/month, 14-day free trial, no card.

For flight dispatchers & OCC

Know a FIR is going hot
before the plan is filed.

Per-FIR numerical risk indices as a data feed into your dispatch systems — one GET per route, a webhook when a threshold is crossed. One more structured input to evaluate alongside weather, active NOTAMs, fuel, and overflight permissions.

An early-warning input, not a recommendation engine. It does not replace NOTAMs, SIGMETs, AIPs, or PIC authority — it tells the duty desk where to look first.

Get a free sandbox key → See the fleet monitor ↓

Sandbox free · production from $2K/mo — no card, no sales call. Full grid on the pricing page.

Proof it's live · fleet route monitor

Live scores for a sample fleet, straight from the engine. Add a route family — it scores instantly and sorts to the top if it's hot.

From

Webhook fires on score change → your dispatch dashboard

Teaser of the same engine the API serves — early-warning input, not a recommendation.

Where dispatcher time goes today.

Manual NOTAM triage

A single long-haul flight plan can include hundreds of NOTAMs. Filtering for operationally relevant items — closures, restrictions, GNSS interference — costs dispatcher time that scales with network size and event intensity.

Fragmented advisories

EASA CZIBs, FAA SFARs, national AIP supplements, and operator bulletins are published independently, with different cadences. Reconciling them into a single view of active FIR status is manual work today.

Short-notice rerouting

Precautionary closures within a single FIR can arrive with no advance warning in the operational feed, forcing in-flight re-filing and hub-level knock-on effects.

UAE, March 2026 — four closures in 24 days

Four precautionary closures inside OMAE in under a month, each arriving with no advance warning in the operational feed — in-flight re-filing and knock-on delays across the DXB hub (case study).

A board that trends per-FIR risk shows the drift while it builds — before the closure NOTAM lands, while rerouting is still a desk decision instead of a scramble.

Into the dispatch workflow in three steps.

One GET per route.

Closes: fragmented advisories. Per-FIR numerical indices as structured JSON, refreshed every 5–30 minutes — one consolidated view of FIR status delivered into pre-filing systems and OCC dashboards, per the methodology.

Regulator flags say where to look.

Closes: manual NOTAM triage. EASA CZIB status, FAA SFAR status, and aggregated NOTAM activity surfaced as fields per FIR. Your dispatcher still reads the official publication — the feed flags which FIRs currently have one, so triage starts at the right place.

Webhook on threshold.

Closes: short-notice rerouting surprises. Configure index thresholds per FIR; when one is crossed, a structured event posts to your dispatch-side webhook. Duty desks are notified without polling — early warning while options are still open.

The response, field by field.

What actually lands in your dispatch system — the sellable unit is this JSON.

GET /route/risk?from=DXB&to=DEL&via=MCT

~50ms · JSON

{
  "from": "DXB", "to": "DEL", "via": ["MCT"],
  "date": "2026-07-14",
  "score": 41, "risk_level": "moderate",
  "confidence": 0.82,
  "legs": [
    { "from": "DXB", "to": "MCT", "score": 31 },
    { "from": "MCT", "to": "DEL", "score": 41 }
  ],
  "coverage": { "status": "covered", … },
  "scored_at": 1783641600
}

legs[]

Multi-leg trips score per segment — the hot leg is isolated, so the reroute discussion starts at which segment, not which trip.

score · risk_level

Two fields drive the board: colour a cell, trend it over the day, alert on threshold. No parsing, no prose.

coverage

Out-of-coverage is explicit — status: "out_of_scope", score null. The board shows "not monitored" instead of false calm.

Illustrative values — the field shape is the exact v2 contract. Scores refresh every 5–30 minutes; always branch on coverage.status, never treat null as 0. Full contract: API docs.

Why the feed holds up next to your official sources.

What's behind a score

→ 334 FIRs scored daily from public regulatory & operational data — EASA · FAA · ICAO · ADS-B · conflict-event signals
→ Regulator source-flags per FIR (CZIB · SFAR · NOTAM activity) for the audit trail
→ Per-score confidence and coverage tier — you see how solid each number is

What we do NOT claim

× A recommendation engine. The index is an input; filing decisions stay with your dispatcher and the PIC.
× A NOTAM replacement. Official publications remain authoritative — the feed tells you where to look first.
× 100% accuracy. Scores are validated against a multi-signal event ground truth; every score carries its scoring version and historical scores are never rewritten — misses stay on the record.

Working references for the desk: Middle East FIR status (live) · Pakistan–India status (live) · NOTAM decoder

Global FIR coverage

Coloured FIRs carry a live ML risk score; blue are GPS-monitored; grey are coverage areas. Watch a route above and it lights up here. Scoring for any FIR is available on request.

Risk scores · 258 drawn / 334 scored daily

Loading airspace map…

How to start.

API pricing — per request volume

Sandbox free · Starter $2K/mo · Pro $5K/mo (SLA + webhooks)

Pilot and production run on API request tiers; free sandbox to evaluate against your current dispatch inputs.

See API plans → Get sandbox key

No integration needed?

The same engine runs as a signed-in workspace — check any leg, keep a dated basis-of-decision record for the reroute rationale. Console from $99/month, 14-day free trial, no card.

See Console plans →

Request a pilot for your fleet — free, no card

Evaluate the early-warning feed against your current dispatch inputs. Per-FIR indices updated every 5–30 minutes, webhook on score change into your OCC dashboard, documented basis per signal for reroute rationale. API + sandbox key in minutes.

Get dev sandbox key →

Dispatch airspace feed — FAQ

Common search queries answered with current status, FIR codes, and source citations.

How much integration work is this, really?: One authenticated GET per route — no request body, no PII, ~50ms from cache. Most teams start by rendering a risk column on the dispatch board, then add the webhook for threshold events. A sandbox key takes minutes; there is no procurement call to book.
What does the API cost?: The sandbox is free on live data, no card. Production runs on request volume: Starter $2,000/month, Pro $5,000/month with SLA and webhooks. The per-FIR detailed endpoint (/v2/route/risk/detailed) ships on Enterprise. Full grid on the pricing page.
How fresh are the scores?: Scores recompute every 5–30 minutes across 334 FIRs scored daily. Every response carries scored_at so your board can cache and invalidate correctly, and confidence so you can see how solid the ground is under each number.
Does this replace NOTAMs or our OCC tooling?: No. It is an early-warning input, not a recommendation engine. NOTAMs, SIGMETs, AIPs, and communications from aviation authorities remain the authoritative sources; the feed tells the duty desk where to look first, and the dispatcher decides.
What happens on a route you don’t cover?: The response says so explicitly: coverage.status = "out_of_scope" with score: null — never a guessed number. Branch on the coverage object and the board shows "not monitored" instead of false calm.
What if a score is wrong?: It is a numerical index validated against a documented event ground truth, with a per-score confidence value and a scoring_version on every score. Treat it as one structured input alongside weather, fuel, and permits; the filing decision stays with your dispatcher.
Can ops staff use it without an integration project?: Yes — the same engine runs as the Console, a signed-in workspace: check any leg, keep a dated record of the reroute rationale. Solo $99/month, Team $399/month, 14-day free trial, no card.

FlySafe provides automated computation of numerical indices from publicly available data. Indices are raw computational output and do not represent opinions, assessments, recommendations, or advice of any kind. They do not replace official NOTAMs, SIGMETs, AIPs, or communications from aviation authorities. See Terms of Service.