TIME-SERIES FORECASTING API

One call ahead.

POST your history. The forecast returns in 287 ms — confidence intervals included, best model auto-selected.

567,676,646 FORECASTS SERVED

OBSERVED FORECAST · 95% CI TODAY 177.1 MEDIAN
FIG. 01 — DEMAND, MONTHLY · 18 MO → 8 MO MODEL AUTOETS · SMAPE 4.2 · RESPONSE 287 MS
MEDIAN RESPONSE 287 MS
MODELS, AUTO-SELECTED 30+
UPTIME SLA 99.99%
CONFIDENCE INTERVALS 95%
TYPE II SOC 2

History in.
Future out.

No training runs. No tuning. No ML team.

01 Send

POST any series as JSON — sales, inventory, traffic, demand. No schema, no setup, no training.

02 Selected

Thirty-plus models compete on your data — ARIMA to Prophet to ETS. The most accurate wins, every call.

03 Served

The forecast comes back with confidence intervals and the winning model's name. Median 287 ms.

REQUEST
curl -X POST https://forecastapi.com/v2/forecast \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "data": [
      {"date": "2024-01-01", "value": 152},
      {"date": "2024-02-01", "value": 149},
      {"date": "2024-03-01", "value": 164}
    ],
    "periods": 6,
    "frequency": "M"
  }'
200 · RESPONSE
{
  "forecasts": [
    { "period": 1, "date": "2024-04-01",
      "forecast": 177.1, "lower": 162.9, "upper": 191.4 },
    { "period": 2, "date": "2024-05-01",
      "forecast": 179.4, "lower": 163.2, "upper": 195.6 }
  ],
  "model_info": {
    "method": "AutoETS",
    "smape": 4.2,
    "confidence": 0.95
  }
}

No training.
No waiting.

There is no model to build. The first call is the deployment.

TRADITIONAL ML 6–12 WEEKS
TRAIN & RETRAIN
FORECASTAPI 287 MS
FIG. 02 — TIME TO FIRST FORECAST, SAME DATA
NO TRAINING PHASE · NO ENDPOINTS · NO MLOPS

Every model competes.

Each call runs your series against thirty-plus methods and scores them out-of-sample. You get the winner — and the scoreboard that proves it.

MODELSMAPE ↓
AUTOETS ● SELECTED 4.21
PROPHET5.08
ARIMA5.83
CROSTON9.42

Uncertainty, quantified.

Every forecast ships with calibrated intervals, not a single guess. Plan on the median. Set safety stock on the upper bound. Sleep on the lower.

UPPER 191.4
MEDIAN 177.1
LOWER 162.9

Sub-second, end to end.

The race runs in parallel on warm infrastructure — fast enough to sit inside a checkout, a dashboard, a replenishment loop. The timing breakdown ships in every response.

VALIDATE 11 MS
MODEL RACE 96 MS
FORECAST 141 MS
TOTAL 287 MS

Different shapes.
Different models.

The API reads the shape of your series and picks accordingly.

Sales forecasting
E-COMMERCE

Seasonal peaks, promotions, slow SKUs. Stock to the upper bound, not the guess.

TYPICAL MAPE 14–25%
Revenue projection
SAAS

MRR compounds; churn dampens. Project both, with intervals your CFO can plan on.

TYPICAL MAPE 5–20%
Traffic & load
INFRASTRUCTURE

Hourly spikes on a weekly rhythm. Scale the fleet before the surge, not during it.

TYPICAL MAPE 6–18%
Demand planning
SUPPLY CHAIN

Intermittent, lumpy, zero-heavy series. Croston was built for exactly this.

TYPICAL MAPE 10–28%
"We deleted our forecasting pipeline and kept one API call."
Head of Data
FORTUNE 500 RETAILER
500M+
FORECASTS SERVED
99.99%
UPTIME, TRAILING 12 MO
$0
TO GET STARTED

One price.
Every model.

No tiers. No per-datapoint billing.
Volume pricing kicks in as you grow.

VOLUME PRICING$ PER CALL
$0.0025 $0.0020 $0.0010 FIRST 50K TO 1M BEYOND 1M
PAY PER CALL
$0.0025 / FORECAST, LIST
1,000 free calls, every month
Volume pricing down to $0.001/call
Save 50% with batching
All 30+ models, auto-selected
Confidence intervals included
99.99% SLA · SOC 2 Type II
Start free
VS AWS FORECAST
93% cheaper
No training costs, simpler pricing.
VS CUSTOM ML TEAM
$100K+ saved
No hiring, training, or maintenance.
VS BUILDING IN-HOUSE
6 months saved
Integrate in minutes, not months.

Stop guessing.

Your first 1,000 forecasts are free.
The first one is 287 ms away.