Skip to main content
POST
Submit Forecast From Storage Object

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request body for submitting a forecast job from a stored object.

object_id
string
required
Required string length: 1 - 128
prediction_length
integer
default:24
Required range: x >= 1
presets
string
default:eomer_pulse_l
Required string length: 1 - 128
item_id_column
string
default:item_id
Required string length: 1 - 200
timestamp_column
string
default:timestamp
Required string length: 1 - 200
target_column
string
default:target
Required string length: 1 - 200
freq
string | null
Maximum string length: 20
quantile_levels
string | null
Maximum string length: 200
covariates
string | null
Maximum string length: 500
latitude
number | null
longitude
number | null
feature_engineering
FeatureEngineeringConfig · object | null

Internal covariate generation from the dataset itself. When enabled, deterministic features (calendar, cyclical encodings, lag, rolling statistics, growth metrics, and event flags) are generated and injected as covariates before model fitting.

external_covariates
ExternalCovariatesConfig · object | null

External covariate source settings.

explainability
ExplainabilityConfig · object | null

Optional post-forecast explainability analyses and artifacts.

reconciliation
ReconciliationConfig · object | null

Reconcile forecasts across a summation hierarchy. When enabled, the pipeline derives every hierarchy level from hierarchy_columns (aggregate series are forecast alongside the bottom ones) and post-adjusts all forecasts to coherence: each parent equals the sum of its children.

callback_url
string | null
Maximum string length: 2048

Response

Successful Response

Response model for job status queries.

job_id
string
required
status
enum<string>
required

Status values for async forecast jobs.

Available options:
pending,
running,
completed,
failed
created_at
string<date-time>
required
completed_at
string<date-time> | null
elapsed_seconds
number | null
num_items
integer | null
prediction_length
integer | null
error
string | null
error_code
enum<string> | null

Machine-readable error codes for agent-friendly error handling.

Available options:
validation_error,
invalid_preset,
file_too_large,
rate_limited,
server_overloaded,
job_not_found,
job_not_completed,
auth_failed,
internal_error,
timeout,
pipeline_failed,
storage_error,
gpu_offload_unavailable,
connection_not_found,
connector_error,
sandbox_domain_used,
sandbox_captcha_failed,
sandbox_dataset_too_large,
sandbox_corporate_email_required
download_url
string | null
report_url
string | null
external_covariate_metadata
External Covariate Metadata · object | null
explainability
ExplainabilitySummaryResponse · object | null

Explainability execution status for a forecast job.

explainability_url
string | null
forecast_plot_url
string | null
reconciliation
Reconciliation · object | null
explanation
ExplanationResponse · object | null

Post-forecast business explanation surfaced on a completed job. Written by the explanation agent (the second LLM in the agentic "sandwich"). Always vendor-neutral — the backend sanitizes every field before persisting, so no underlying model/vendor name appears here.

request_id
string | null
config_hash
string | null
dataset_hash
string | null
model_version
string | null
delivery_status
string | null
delivery_connection_id
string | null
delivery_uri
string | null
delivery_error
string | null