Forecast Sandbox

predict a versioned per-series daily-state forecast model

Sandbox only. History/calendar training uses relationship_state_correction_v2; extended features use relationship_state_context_guard_v4 with a protected automatic reference. Both combine: automatic calendar/recency reference plus historically validated state correction. Existing v1/v2/v3 artifacts remain readable. Historical labels and transition models use D-2 availability. Immutable tenant-scoped artifacts. Train requires at least 14 complete days; activating state features requires historical validation. Predict reloads frozen parameters and can persist recent complete-day context without retraining. Live dates beyond 2025 supported; no future knowledge origins.

post/api/forecast-sandbox/consumption/state-model/predict

Request

  • Base URL: https://api.cernion.de
  • URL: https://api.cernion.de/api/forecast-sandbox/consumption/state-model/predict
  • Auth: none declared

Query parameters

tokenstring

Optional Cernion MCP token as URL query parameter. If provided, it overrides CERNION_TOKEN for this request. Prefer Authorization Bearer header in production to reduce token exposure in URLs/logs.

Request body

series_idstring required
artifact_versionstring required
forecast_forstring date required
configurationobject

Refresh weather/context or immutable dataset IDs only. Model parameters and issue_time remain frozen.

tokenstring

Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.

Response

Version metadata, validation or PT15M forecasts; inspect warnings and state_features_enabled.

series_idstring
artifact_versionstring
model_versionstring
forecast_valuesobject[]
validationobject
warningsstring[]

Changes

No recorded changes to this operation across all 2 revisions of this API.