{ "status": "completed", "model": "chronos-2", "series": [ [ { "prediction": { "0.1": [ 124.2, 125, 123.8, 126.5, 128, 129.3 ], "0.5": [ 127.4, 128.9, 127.2, 130.1, 131.8, 133.2 ], "0.9": [ 130.6, 132.8, 130.6, 133.7, 135.6, 137.1 ], "mean": [ 127.4, 128.9, 127.2, 130.1, 131.8, 133.2 ] }, "index": [ "2023-06-01", "2023-07-01", "2023-08-01", "2023-09-01", "2023-10-01", "2023-11-01" ] } ] ] }

import requests resp = requests.post( "https://oab-forecasting.com/forecast", headers={ "Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json", }, json={ "series": [ {"index": ["2023-01-01","2023-02-01","2023-03-01","2023-04-01","2023-05-01"], "target": [120.5, 122.3, 119.8, 124.1, 126.7]} ], "model": "chronos-2", "model_size": "base", "horizon": 6, "freq": "MS", "quantiles": [0.1, 0.5, 0.9], }, ) print(resp.json())

POSToab-forecasting.com/forecast

Run a Forecast

Perform synchronous model inference. Send one or more time-series inline and receive forecasts directly in the response.

Request Schema

seriesarray[object]requiredOne or more time-series objects.

[item]object

targetarray[number]requiredThe time-series values to forecast from.

indexarray[string]requiredISO date strings matching target length.

hist_variablesobjectoptionalHistorical covariate columns. Keys are variable names, values are arrays same length as target.

future_variablesobjectoptionalFuture covariate columns. Keys are variable names, values are arrays of length horizon.

future_variables_indexarray[string]optionalISO date strings for future_variables, length = horizon.

static_variablesobjectoptionalStatic scalar covariates. Each key maps to a single value.

horizonintegerrequiredNumber of steps to forecast. Range: 1–10000.

freqstring (enum)required5min · 15min · 30min · H · D · W · M · MS · Q · Y

contextintegeroptionalHistory steps to use. Default: min(model_max, series_length).

quantilesarray[number]optionalQuantiles to return. Default: [0.1, 0.5, 0.9].

model_sizestringoptionalSize variant for multi-size models (chronos, chronos-2). e.g. "base".

Response Schema

statusstring (enum)completed · failed · in_progress

modelstringModel ID used for inference.

seriesarray[array[object]]Outer array = series, inner array = items per series.

[i][j]object

predictionobject

meanarray[number]Point forecast.

"0.1"array[number]10th percentile.

"0.5"array[number]Median.

"0.9"array[number]90th percentile.

indexarray[string]ISO date strings for forecast horizon.

metricsobject | nullOptional evaluation metrics.

Response Example

{
  "status": "completed",
  "model": "chronos-2",
  "series": [
    [
      {
        "prediction": {
          "0.1": [
            124.2,
            125,
            123.8,
            126.5,
            128,
            129.3
          ],
          "0.5": [
            127.4,
            128.9,
            127.2,
            130.1,
            131.8,
            133.2
          ],
          "0.9": [
            130.6,
            132.8,
            130.6,
            133.7,
            135.6,
            137.1
          ],
          "mean": [
            127.4,
            128.9,
            127.2,
            130.1,
            131.8,
            133.2
          ]
        },
        "index": [
          "2023-06-01",
          "2023-07-01",
          "2023-08-01",
          "2023-09-01",
          "2023-10-01",
          "2023-11-01"
        ]
      }
    ]
  ]
}

Possible Errors

401UnauthorizedMissing or invalid Authorization header

422UnprocessableUnknown model ID · index/target length mismatch · invalid freq

429Too Many RequestsRate limit exceeded. Check X-RateLimit-Reset header.

500Server ErrorModel inference failure. See the detail field.