Forecast monitoring
Monitor inference volume and API performance for each deployed forecast model. Usage tracking starts after you generate an API key and call the forecast endpoint.
Per-forecast usage (recommended)
- Open Forecast and click your model.
- Generate API key if needed (deployment guide).
- Scroll to the Usage section on the forecast detail page.
You will see:
- Summary cards — total inferences, requests, average response time, endpoints used
- Charts — daily inference volume and response time, split by Heimdall UI vs API
- Request log — sortable table with endpoint, inference count, response time, channel, and user agent
- Filters — 7 / 30 / 90 day windows and endpoint filter
Account-level monitoring
Open Usage (/usage) → Data Intelligence for workspace-wide forecast traffic alongside ML, Loop, Read, and Vision.
See Production monitoring for daily charts, channel mix, and top assets.
What gets recorded
| Field | Meaning |
|---|---|
| Endpoint | REST path called |
| Inference count | Forecast points returned in the request |
| Response time | Milliseconds to complete |
| Channel | Heimdall UI or API |
| User agent | Client string when present |
Next steps
- API integration guide — integrate forecasts in your app
- Production monitoring — account usage and platform health
- Deploy your forecast — generate keys if not deployed yet