> ## Documentation Index > Fetch the complete documentation index at: https://docs.metar.ws/llms.txt > Use this file to discover all available pages before exploring further. # Model Forecasts > Daily max/min temperature forecasts from global and high-resolution numerical weather models. `metar.forecast..` carries what a numerical weather model expects, as opposed to what a station measured. Each event carries the forecast maximum and minimum for one station over one local calendar day, and is re-sent whenever newly published forecast hours change it. ## Two tiers High-resolution models only cover their own region, so forecasts are split into two tiers. | Channel | Models | Minimum plan | | ----------------------------- | ------------------------------------- | ------------ | | `metar.forecast.basic.` | GFS 0.25°, ICON global, ICON-EU | Sandbox | | `metar.forecast.hires.` | HRRR 3 km, ICON-D2 2 km, JMA MSM 5 km | Starter | Basic forecasts cover all streamed stations, since the underlying global models cover the whole planet. Hires forecasts cover a subset of stations: the US and Toronto under HRRR, several East Asian airports under JMA MSM, and a handful of Central European airports under ICON-D2. Stations outside these regions have no high-resolution model; their `metar.forecast.hires.*` channel exists but stays silent, which is not an error. Temperatures, deltas and coordinates are decimal strings rather than JSON numbers, so no binary float rounding happens in transit. ## Timestamps and status Three timestamps describe the lifecycle of a forecast: `run_utc` is when the model was initialised, `source_available_utc` is when the provider published the file, and `receipt_time` is when metar.ws finished decoding it. The `status` field moves through `detected`, `partial` and `day_complete` as forecast hours arrive; `corrected` means the provider replaced a file that had already been used. `grid_point.distance_km` is the distance from the airport to the model grid cell actually used. A 2 km model typically lands within about 1.5 km of the station; a 25 km global model can be as far as 15 km away. Check this value before treating a forecast as strictly local. Filter on `local_day_complete` before comparing any forecast values. Until a full local day has arrived, `temp_max_c` is only the maximum of the hours received so far, and the missing hours cannot lower it, so an incomplete day systematically under-reports the maximum and over-reports the minimum. This bias does not average out across many days. Treat `local_day_complete: true` (equivalently a `status` of `day_complete` or `run_complete`) as the signal that a measurement is final, and read `available_through_forecast_hour` to see how much of the day an incomplete event actually covers. Compare Sandbox, Starter and Pro, and see how channel limits are counted.