Authentication

Learn how to authenticate your API requests with tokens.

Get Started

Endpoints

Complete reference for all available API endpoints.

Explore

AI Models

Access our predictive analytics and AI capabilities.

Learn More

Integrations

Connect with MRO systems like AMOS, TRAX, and SAP.

View APIs

System Architecture

Understanding how Trakt's AI-powered predictive maintenance works

TRAKT SYSTEM AI-POWERED PREDICTIVE MAINTENANCE 95% ACCURACY 2-13 WKS ADVANCE ~22% COST SAVED DATA SOURCES ACARS / ADS-B Real-time flight telemetry Sensor Telemetry Temp, vibration, pressure MRO Systems Maintenance records Pilot Reports Crew observations Weather APIs Environmental factors Tech Bulletins OEM recommendations DATA PROCESSING Ingestion Engine Feature Engineering Data Validation Normalization 99.7% Success AI CORE PREDICTION ENGINE Failure Prevention 95% Accuracy Component Life RUL Analysis Smart Scheduling Optimization Fleet Optimization Max Availability Parts Forecasting Supply Chain Early Warning Pattern Analysis ACTIONABLE OUTPUTS Predictive Alerts 2-13 weeks advance warning on failures RUL Estimates Remaining useful life for all components Maintenance Schedules Optimized timing for minimal disruption Parts Procurement Predictive inventory management Fleet Dashboard Real-time health visualization Cost Analytics ROI tracking and optimization insights SMART COMPONENT HEALTH MONITORING CRITICAL Immediate action needed Schedule maintenance now WARNING Wear accelerating Plan maintenance within 2 weeks MONITOR Normal wear detected Schedule at next convenient check HEALTHY Operating normally No action required FEDERATED LEARNING Privacy-preserving cross-fleet intelligence Zero proprietary data sharing between operators SECURITY TLS 1.3 + AES-256 encryption AWS GovCloud | GDPR Compliant DEPLOYMENT 4-12 weeks to production No infrastructure changes required COMPATIBILITY Boeing | Airbus | Bombardier | Embraer Universal fleet support

Data Ingestion

ACARS, ADS-B, sensor telemetry, MRO systems, pilot reports, weather data, and technical bulletins.

AI Core Processing

AI prediction engine with six specialized models for comprehensive predictive analytics.

Actionable Outputs

Predictive alerts, component life estimates, optimized maintenance schedules, and fleet dashboards.

Authentication

Secure your API requests with bearer token authentication

API Key Authentication

All API requests require authentication using your company API key in the Authorization header.

HTTP Header 
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
Replace YOUR_API_KEY with your actual API key from the dashboard.

Base URL & Rate Limits

All API endpoints are accessed via the base URL:

https://trakt.tech

Rate Limits by Plan

Read Only 1,000 requests/month
Read/Write 5,000 requests/month
Full Access 20,000 requests/month

AI Prediction Models

Six specialized AI models working together for comprehensive predictive maintenance

Early Warning System

Pattern Analysis

Spots unusual patterns in your aircraft data and alerts you before small issues become big problems.

Pattern Detection Pattern Recognition Statistical Analysis
Detection Rate: 97%

Failure Prevention

95% Accuracy

Predicts which parts are at risk and when they might fail, giving you 2-13 weeks advance warning.

Multi-Model Analysis Risk Assessment Trend Analysis
Advance Warning: 2-13 Weeks

Component Life Tracking

RUL Estimates

Estimates how much useful life remains in each part, so you replace things at the right time.

Usage-Based Analysis Lifecycle Modeling Physics-Based
Estimation Accuracy: ±8%

Smart Scheduling

Cost Optimization

Recommends the best times for maintenance to minimize downtime and reduce costs.

Adaptive Optimization Schedule Optimization Resource Planning
Cost Savings: 22%

Fleet Optimization

Max Availability

Balances maintenance needs across your entire fleet to maximize aircraft availability.

Cross-Fleet Intelligence Fleet Balancing Availability Optimization
Availability Increase: +15%

Parts Forecasting

Inventory Management

Predicts what parts you'll need and when, helping you manage inventory and avoid AOG situations.

Demand Forecasting Lead Time Prediction Stock Optimization
AOG Reduction: 40%

Degradation Analysis Models

Physics-based models that understand how aircraft components wear over time

Critical Wear Model

For components showing critical health levels (≤15%). Requires immediate attention and accelerated monitoring.

Health Threshold: ≤ 15%

Accelerated Degradation

For components with accelerating wear patterns. Uses advanced degradation modeling for accurate remaining life prediction.

Condition Factor: > 0.7

Linear Wear Model

For components with steady, predictable wear patterns. Standard degradation rate based on usage and age.

Condition Factor: 0.3 - 0.7

Statistical Life Model

For components operating normally. Uses statistical reliability modeling for lifecycle planning.

Condition Factor: ≤ 0.3

API Endpoints

Complete reference for all available endpoints - click to expand

Check API service status and your authentication.

Response 
{
  "status": "healthy",
  "timestamp": "2025-01-01T12:00:00Z",
  "version": "1.0.0",
  "authenticated": true,
  "company": "Demo Airlines",
  "rate_limit": {
    "remaining": 4950,
    "total": 5000,
    "reset_time": "2025-01-01T13:00:00Z"
  }
}

Get current AI model training status and performance metrics.

Response 
{
  "model_info": {
    "model_trained": true,
    "last_training_date": "2025-01-01T08:00:00Z",
    "training_data_count": 15420,
    "auto_training_enabled": true
  },
  "degradation_models": {
    "available_models": [
      "Statistical Life Model",
      "Linear Wear Model",
      "Accelerated Degradation",
      "Critical Wear Model"
    ],
    "calibrated_components": 156
  },
  "ai_models_status": {
    "early_warning_system": "ready",
    "failure_prevention": "ready",
    "component_life_tracking": "ready",
    "smart_scheduling": "ready",
    "fleet_optimization": "ready",
    "parts_forecasting": "ready"
  }
}

Retrieve all aircraft in your fleet with basic information.

Query Parameters

limit (optional) Maximum number of results (default: 50)
offset (optional) Pagination offset (default: 0)
active_only (optional) Filter for active aircraft only (default: true)
Response 
{
  "aircraft": [
    {
      "id": 1,
      "tail_number": "N123DA",
      "aircraft_type": "Boeing 737-800",
      "manufacturer": "Boeing",
      "model": "737-800",
      "year_manufactured": 2015,
      "total_flight_hours": 25000,
      "total_flight_cycles": 15000,
      "is_active": true,
      "component_count": 6,
      "average_health_score": 78.5
    }
  ],
  "total": 1,
  "limit": 50,
  "offset": 0
}

Retrieve available predictions for components with full AI analysis.

Response 
{
  "success": true,
  "predictions": [
    {
      "component_id": 1,
      "component_name": "Engine 1",
      "aircraft_tail": "N123DA",
      "health_score": 85.2,
      "remaining_useful_life_hours": 2500,
      "failure_probability_30_days": 0.08,
      "degradation_model": "Linear Wear Model",
      "ai_models_applied": [
        "Early Warning System",
        "Failure Prevention",
        "Component Life Tracking"
      ],
      "recommended_action": "Monitor",
      "confidence_score": 0.92
    }
  ]
}

Submit sensor readings for real-time analysis and prediction updates.

Request Body 
{
  "component_id": 1,
  "timestamp": "2025-01-01T12:00:00Z",
  "readings": {
    "temperature": 95.5,
    "vibration": 1.8,
    "pressure": 42.0,
    "rpm": 8500
  },
  "flight_phase": "cruise"
}
Response 
{
  "success": true,
  "data_id": 12345,
  "analysis": {
    "health_impact": "nominal",
    "anomalies_detected": false,
    "prediction_updated": true
  }
}

Export complete fleet data with all predictions for integration with external systems.

Requires Read/Write or Full Access level
Response 
{
  "success": true,
  "data": {
    "export_timestamp": "2025-01-01T12:00:00Z",
    "fleet_overview": {
      "total_aircraft": 25,
      "active_aircraft": 23,
      "total_components": 156,
      "average_health_score": 82.5
    },
    "aircraft": [...],
    "components": [...],
    "predictions_summary": {
      "total": 156,
      "critical": 3,
      "warning": 12,
      "monitor": 28,
      "healthy": 113
    }
  }
}

Returns all configuration options: regions, currencies, week-end settings, and maintenance interval types.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/config

Response Fields

regions (array) Available regions with codes, names, and defaults
currencies (array) Supported currencies with symbols
week_end_options (array) Week-end day options (Friday / Saturday / Sunday)
interval_types (array) Maintenance interval types
supported_currencies (array) List of currency codes

Returns planning scenarios with duration, SLA targets, currency, region, and predictions summary.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/scenarios

Response Fields

id (integer) Unique scenario identifier
name (string) Scenario name
start_date (datetime) Scenario start date (ISO 8601)
end_date (datetime) Scenario end date (ISO 8601)
duration_days (integer) Duration in days
duration_weeks (integer) Duration in weeks
duration_years (float) Duration in years
currency (string) Currency code (USD, EUR, SAR, etc.)
end_of_week (string) Week end day (Friday / Saturday / Sunday)
region (string) Region code
sla_targets (object) aircraft_availability, dispatch_reliability, on_time_performance
predictions_summary (object) Summary: critical, high, medium, low, total counts

Create a new planning scenario. Body fields are optional; sensible defaults are applied when omitted (one-year window, USD, Sunday week-end).

cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name":"Q3 Fleet Plan","start_date":"2026-07-01","end_date":"2026-09-30","currency":"USD","end_of_week":"Sunday","region":"north_america"}' \
  https://trakt.tech/api/integrations/scenarios
Request Body 
{
  "name": "Q3 Fleet Plan",
  "description": "Summer schedule",
  "start_date": "2026-07-01",
  "end_date": "2026-09-30",
  "currency": "USD",
  "end_of_week": "Sunday",
  "region": "north_america",
  "sla_targets": {
    "aircraft_availability": 98.5,
    "dispatch_reliability": 99.2,
    "on_time_performance": 90.0
  }
}
Response 
{
  "success": true,
  "scenario": {
    "id": 14,
    "name": "Q3 Fleet Plan",
    "start_date": "2026-07-01T00:00:00",
    "end_date": "2026-09-30T00:00:00",
    "currency": "USD",
    "end_of_week": "Sunday"
  }
}

Retrieve a single planning scenario by its numeric ID, including SLA targets and predictions summary.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/scenarios/14

Response Fields

id (integer) Unique scenario identifier
name (string) Scenario name
start_date (datetime) Scenario start date (ISO 8601)
end_date (datetime) Scenario end date (ISO 8601)
duration_days (integer) Duration in days
duration_weeks (integer) Duration in weeks
duration_years (float) Duration in years
currency (string) Currency code (USD, EUR, SAR, etc.)
end_of_week (string) Week end day (Friday / Saturday / Sunday)
region (string) Region code
sla_targets (object) aircraft_availability, dispatch_reliability, on_time_performance
predictions_summary (object) Summary: critical, high, medium, low, total counts

Returns asset configurations (aircraft types) with maintenance programs, specifications, and typical utilization.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/asset-configurations

Response Fields

id (integer) Asset configuration ID
name (string) Configuration name
code (string) Short code (e.g. NB-COMM)
description (string) Full description
category (string) commercial / regional / business / military
mtow_kg (integer) Max takeoff weight in kg
max_range_nm (integer) Maximum range in nautical miles
typical_seats (string) Typical seating capacity
engines (object) Engine count and type
typical_utilization (object) Hours per day, days per year
maintenance_programs (array) Array of maintenance task definitions

Create an asset configuration (aircraft type) and optionally attach maintenance programs in the same request.

cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name":"Narrowbody Commercial","code":"NB-COMM","category":"commercial"}' \
  https://trakt.tech/api/integrations/asset-configurations
Request Body 
{
  "name": "Narrowbody Commercial",
  "code": "NB-COMM",
  "description": "Single-aisle commercial type",
  "manufacturer": "Boeing",
  "model_series": "737",
  "category": "commercial",
  "is_global": false,
  "maintenance_programs": [
    {
      "name": "A-Check",
      "task_code": "A-CHECK",
      "interval_type": "flight_hours",
      "interval_value": 750,
      "interval_unit": "hours",
      "duration_hours": 10,
      "estimated_cost": 12000,
      "is_mandatory": true,
      "required_certifications": ["A&P"]
    }
  ]
}
Response 
{
  "success": true,
  "asset_configuration": {
    "id": 8,
    "name": "Narrowbody Commercial",
    "code": "NB-COMM",
    "maintenance_programs_created": 1
  }
}

Returns maintenance programs supporting calendar, flight-hour, flight-cycle, and combined intervals. Filter by interval_type.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/maintenance-programs?interval_type=flight_hours

Response Fields

id (integer) Program ID
task_code (string) Task code (A-CHECK, C-CHECK, ENG-HSI, etc.)
name (string) Task name
description (string) Task description
interval_type (string) calendar / flight_hours / flight_cycles / combined / condition
interval_value (integer) Interval value
interval_unit (string) days / hours / cycles
duration_hours (float) Expected task duration in hours
estimated_cost (float) Estimated cost in USD
is_mandatory (boolean) Whether task is mandatory
required_certifications (array) Required technician certifications

Returns aircraft with fields: start_of_operations, YTD hours/cycles, health status, and component prediction breakdown.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/aircraft/extended?region=middle_east

Response Fields

id (integer) Aircraft ID
tail_number (string) Aircraft tail number
aircraft_type (string) Aircraft type
asset_configuration_id (integer) Linked asset configuration ID
asset_configuration_name (string) Asset configuration name
start_of_operations (datetime) Date aircraft entered service (ISO 8601)
current_flight_hours (float) Total accumulated flight hours
total_flight_cycles (integer) Total flight cycles
ytd_flight_hours (float) Year-to-date flight hours
ytd_flight_cycles (integer) Year-to-date flight cycles
yearly_hour_limit (float) Annual flight hour limit
daily_utilization_hours (float) Average daily utilization
region (string) Operating region
health_status (string) critical / attention_required / monitor / healthy
lowest_component_health (float) Lowest component health score
component_predictions (object) Breakdown: critical, high, medium, low counts

Returns components with full model outputs: cost, lead time, predictions, anomaly detection, survival analysis, and maintenance recommendations.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/components/extended?component_type=Engine

Response Fields

id (integer) Component ID
name (string) Component name
component_type (string) Component type
unit_cost (float) Component unit cost
cost_range (object) {min, max}
currency (string) Cost currency
lead_time_days (integer) Order-to-receipt lead time
lead_time_range (object) {min, max}
predictions.current_health_score (float) AI-predicted health (0-100)
predictions.predicted_rul_hours (float) Remaining useful life in hours
predictions.failure_probability (float) Failure probability (0-1)
predictions.prediction_confidence (float) Model confidence (0-1)
anomaly_detection.anomaly_detected (boolean) Anomaly flag
anomaly_detection.anomaly_score (float) Anomaly score (0-1)
survival_analysis.hazard_rate (float) Instantaneous failure rate
survival_analysis.survival_function (object) Survival probabilities at intervals
survival_analysis.rul_distribution (object) RUL distribution: median, p10, p90
maintenance.priority (string) critical / high / medium / low
maintenance.optimal_action (string) monitor / inspect / repair / replace
maintenance.action_deadline (string) Action deadline

Planner board grid: aircraft rows by day columns. Each cell summarizes scheduled work orders and predicted failures. Same shape that powers the web UI planner board.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  "https://trakt.tech/api/integrations/planner/grid?days=7&fp_threshold=0.5"

Response Fields

window (object) start, end, days
columns (array) Day column headers: date, label (e.g. "Sun 05/17")
rows (array) One row per aircraft with cells[] for each day
rows[].aircraft_id (integer) Aircraft identifier
rows[].tail_number (string) Aircraft tail number
rows[].aircraft_type (string) Aircraft type (e.g. B737)
rows[].cells (array) Per-day cells with predictions and work_orders
rows[].cells[].badge (string) PREDICTED / DUE / SCHEDULED / NON MX
rows[].cells[].urgency (string) critical / high / medium / normal
rows[].cells[].predictions (array) Forecast components for this cell
rows[].cells[].work_orders (array) Scheduled work orders for this cell
rows[].cells[].total_hours (float) Sum of estimated/suggested hours
total_aircraft (integer) Number of aircraft rows returned
total_items (integer) Total predictions + work orders in window
filters_applied (object) Echo of fleet_type, station, fp_threshold, company_id

Flat sorted feed of upcoming maintenance items (predictions and work orders) in one window. Best for automation, dashboards, and alerting. Sorted by urgency desc, then date asc. Filter by kind (predictions / work_orders / all) and min_urgency.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  "https://trakt.tech/api/integrations/planner/forecast?days=30&min_urgency=high&kind=predictions"

Response Fields

window (object) start, end, days of the forecast window
items (array) Flat sorted list of forecast items
items[].kind (string) prediction or work_order
items[].urgency (string) critical / high / medium / normal
items[].urgency_rank (integer) 1-4 (higher = more urgent)
items[].aircraft_id (integer) Aircraft identifier
items[].tail_number (string) Aircraft tail number
items[].component_id (integer) Component identifier (predictions and component-scoped WOs)
items[].component_name (string) Component name (predictions only)
items[].failure_probability (float) 0-1 failure probability (predictions only)
items[].current_health_score (float) Current health score 0-100 (predictions only)
items[].predicted_rul_hours (float) Predicted remaining useful life (predictions only)
items[].maintenance_due_date (datetime) Predicted due date (predictions only)
items[].suggested_action_date (datetime) Recommended date to schedule maintenance
items[].suggested_duration_hours (float) Suggested work duration
items[].work_order_id (integer) Work order ID (work_orders only)
items[].work_order_number (string) WO number (work_orders only)
items[].scheduled_start (datetime) Scheduled start (work_orders only)
counts (object) predictions and work_orders count rollup
filters_applied (object) Echo of all filters used

Programmatically turn a predicted failure into a real work order. Requires READ_WRITE or FULL token. Auto-infers work_type, priority, and duration from component signals if not provided. Returns the new work order details. (Preview shows a sample response; the real endpoint creates a WO each call.)

Requires Read/Write or Full Access level
cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"component_id": 12345, "target_date": "2026-05-25T08:00:00", "priority": "high"}' \
  https://trakt.tech/api/integrations/planner/convert-prediction

Response Fields

work_order_id (integer) ID of the newly-created work order
work_order_number (string) Generated WO number (format: WO-PRED-XXXXXX-TIMESTAMP)
component_id (integer) Source component identifier
aircraft_id (integer) Associated aircraft ID
scheduled_start (datetime) Scheduled work start (ISO 8601)
scheduled_end (datetime) Scheduled work end (ISO 8601)
priority (string) Auto-inferred or supplied priority (critical/high/medium/low)
work_type (string) Auto-inferred or supplied work_type (inspection/replacement/maintenance)
estimated_hours (float) Suggested work duration in hours

Time-bucketed failure probability distributions per component across the planning horizon. Includes rectangular and triangular failure window objects for optimizer coverage scoring. Spread is confidence-adjusted.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/predictions/failure-windows?horizon_days=730&bucket_days=30

Response Fields

component_id (integer) Component identifier
component_name (string) Component name
current_health_score (float) Health score (0-100)
predicted_rul_hours (float) Remaining useful life in hours
prediction_confidence (float) Model confidence (0-1)
horizon_days (integer) Planning horizon in days
bucket_days (integer) Width of each time bucket in days
failure_probability_buckets (array) Per-bucket: start_date, end_date, failure_probability, cumulative_probability, severity_coefficient, risk_level
peak_risk_bucket (integer) Index of the highest-probability bucket
failure_window.rectangular (object) start_date, end_date (p10-p90) for binary coverage
failure_window.triangular (object) left_date, center_date, right_date (p25/median/p75) for graded coverage
failure_window.rul_distribution (object) p10, p25, median, p75, p90 in hours and calendar dates
failure_window.confidence_adjusted (boolean) Whether window spread was adjusted for prediction confidence

Ingests optimizer scheduling outputs as reinforcement training signals. Each slot is scored against the Trakt failure window that was sent. Coverage results are persisted and a model retraining job is queued automatically when batch size is large enough.

Requires Read/Write or Full Access level
cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"optimizer_result_id":"result_13","optimizer_scenario_id":"KquiAC-15","optimizer_generation":32,"result_availability":93.33,"result_fh_per_month":10.44,"sla_compliant":true,"slots":[{"component_id":42,"aircraft_tail_number":"A6-TRK01","scheduled_date":"2026-04-15","task_type":"scheduled_maintenance","bundled_with":[43,44]}]}' \
  https://trakt.tech/api/integrations/optimizer/feedback

Response Fields

optimizer_result_id (string) Request: Optimizer result identifier (required)
optimizer_scenario_id (string) Request: Scenario name
optimizer_generation (integer) Request: Generation number at termination
result_availability (float) Request: Fleet availability % achieved
result_fh_per_month (float) Request: Flight hours per month
sla_compliant (boolean) Request: Whether all SLA conditions were met
slots (array) Request: Per-component slot assignments (component_id, scheduled_date, task_type, bundled_with)
ingested_count (integer) Response: Slots successfully ingested
skipped_count (integer) Response: Slots skipped due to missing data
coverage_summary.rectangular_coverage_rate (float) Response: Fraction of slots within p10-p90 window
coverage_summary.mean_triangular_score (float) Response: Mean proximity score (0-1)
coverage_summary.not_covered (integer) Response: Slots outside the rectangular window
training_job_id (string) Response: Async retraining job ID
retraining_queued (boolean) Response: Whether a retraining job was queued

Legacy endpoint: select specific components and prediction types. Returns failure window objects alongside each prediction.

Requires Read/Write or Full Access level
cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"component_ids":[1,2,3]}' \
  https://trakt.tech/api/integrations/predictions/select

Response Fields

component_ids (array) Request: Component IDs to select
prediction_types (array) Request: Types to include
selected_predictions (array) Response: Selected predictions with failure_window

Legacy endpoint: export predictions in JSON or CSV format. Each record includes failure window objects.

Requires Read/Write or Full Access level
cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"component_ids":[1,2,3],"format":"json"}' \
  https://trakt.tech/api/integrations/predictions/export

Response Fields

component_ids (array) Request: Component IDs to export
format (string) Request: json or csv
data (array) Response: Exported predictions with failure_window objects

Returns information about the current token: usage, limits, expiry, and access level.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/token/info

Response Fields

name (string) Token holder name
email (string) Token holder email
organization (string) Organization name
access_level (string) Access level
company_id (integer) Scoped company ID (null = all)
requires_login (boolean) Whether login is required
expires_at (datetime) Token expiration date
days_remaining (integer) Days until expiry
daily_limit (integer) Daily request limit
daily_usage (integer) Requests made today
monthly_limit (integer) Monthly request limit
monthly_usage (integer) Requests this month

Machine-to-machine batch ingestion for sensor telemetry. Each reading is verified against the token company, so cross-tenant rows are rejected per row while the rest of the batch lands. Supply external_id for idempotent retries.

Sends up to 1,000 readings per request. Rate limited to 60 requests per minute.
cURL 
curl -X POST -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d @batch.json \
  https://trakt.tech/api/v1/sensor-data/batch
Request Body 
{
  "readings": [
    {
      "component_id": 1234,
      "timestamp": "2026-05-18T14:32:00Z",
      "external_id": "fdr-abc-001",
      "external_system": "aviatar",
      "temperature": 85.2,
      "vibration": 2.1,
      "pressure": 42.0,
      "rpm": 12450,
      "oil_temperature": 78,
      "fuel_flow": 48,
      "voltage": 27.8,
      "current": 15.2,
      "raw_data": {"any": "additional", "fields": "here"}
    }
  ]
}
Response 
{
  "success": true,
  "received": 1000,
  "stored": 985,
  "duplicates": 12,
  "rejected": 3,
  "errors": [
    {"row": 47,  "reason": "component_not_found", "component_id": 9999},
    {"row": 105, "reason": "cross_tenant", "component_id": 12},
    {"row": 832, "reason": "out_of_range:temperature", "value": 50000.0}
  ]
}

Check connection health and last sync time for your configured MRO and data integrations. Scoped to your company: a token only ever sees its own company's integrations.

cURL 
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
  https://trakt.tech/api/integrations/status

Response Fields

configured_systems (array) Connected systems with system, name, status, and last_sync
integration_health (object) Overall health, for example available or not_configured
data_flow_status (object) Most recent sync timestamp across all systems
Response 
{
  "configured_systems": [
    {
      "system": "amos",
      "name": "AMOS",
      "status": "active",
      "last_sync": "2026-06-15T09:30:00Z"
    }
  ],
  "integration_health": {
    "status": "available"
  },
  "data_flow_status": {
    "last_sync": "2026-06-15T09:30:00Z"
  }
}

Why Choose Trakt?

The intelligent layer that makes your existing systems smarter

AI-First Architecture

While legacy MRO systems focus on record-keeping, Trakt was built from the ground up for predictive intelligence. Our AI models analyze patterns across your entire operation to predict failures before they happen.

Universal Connectivity

Your existing systems store valuable data but can't predict the future. Trakt connects to 50+ MRO platforms, enriches your data with AI predictions, and sends actionable insights back - no system replacement required.

Privacy-Preserving Intelligence

Benefit from industry-wide learning through our federated AI without ever sharing your proprietary data. Your maintenance patterns stay private while you gain insights from aggregate fleet intelligence.

2-13 Week Advance Warning

Traditional systems tell you what happened. Trakt tells you what's about to happen - with 95% accuracy and weeks of advance notice, giving you time to plan maintenance on your terms.

Measurable ROI

Our clients see ~22% reduction in maintenance costs, ~40% fewer AOG events, and ~15% improvement in fleet availability. Trakt pays for itself within months, not years.

Rapid Deployment

Go live in 4-12 weeks with zero infrastructure changes. Trakt works alongside your existing systems, enhancing them with predictive capabilities without disrupting your operations.

Connect Your Existing Systems to Trakt

Trakt enhances your current MRO platforms with AI-powered predictive maintenance - no system replacement needed

Your Data + Trakt's AI = Predictive Intelligence

Legacy MRO systems excel at tracking maintenance history and managing work orders, but they weren't built to predict the future. Trakt connects to your existing platforms, ingests your historical data, applies advanced AI models, and delivers actionable predictions - transforming reactive maintenance into proactive fleet management.

MRO & Maintenance Systems

Trakt pulls your maintenance records, analyzes patterns, and pushes AI-generated work order recommendations back to your system of record.

AMOS TRAX Ramco IFS Maximo OASES Ultramain Veryon EmpowerMX

Enterprise & ERP

Sync inventory levels, procurement data, and financial metrics with Trakt's parts forecasting to optimize your supply chain.

SAP S/4HANA SAP ECC Oracle

OEM Data Sources

Trakt aggregates OEM sensor data and technical bulletins to enhance prediction accuracy across all aircraft types.

Airbus Skywise Boeing AnalytX Aviatar EngineWise PWC FAST

Parts & Supply Chain

Connect your parts suppliers to Trakt's demand forecasting for automated procurement and reduced AOG risk.

Satair SmartParts AFI KLM E&M Custom API

Universal Integration API

All integrations use Trakt's standardized API endpoints. Configure your connection once, and Trakt handles the complexity of each external system.

GET /api/integrations/status

Check connection health and sync status

Don't see your system? Trakt's Custom API connector supports any REST or SFTP-based integration. Contact us to add your MRO platform.

Error Codes

Standard HTTP status codes and error responses

Status Code Name Description
200 OK Request successful
201 Created Resource created successfully
400 Bad Request Invalid request parameters or body
401 Unauthorized Missing or invalid API key
403 Forbidden Insufficient permissions for this endpoint
404 Not Found Resource not found
429 Too Many Requests Rate limit exceeded
500 Server Error Internal server error

Ready to Get Started?

Generate your API key and start integrating Trakt's predictive maintenance capabilities today.

Login to Get Started Visit Help Center