Add money Find jobsWatch videosDocsBuild with AIExamplesUse casesFor agentsDaily storm leadsML Storm ForecastDataCompareStorm mapAPI AccessStorm Mailers Legacy log in Get an API key
ML Storm Forecast by Address · AtlasCast, an Atlas United product

Know a storm is coming
before it hits.

Address-level ML forecasts, 24 hours to 10 days ahead, with the structure value and the people at each address. Call first, while the sky is still clear.

Powered by atlasunited.io

Get an API keyAsk your AI
Calm blue sky after the storm, with a repair crew at work Dark storm clouds over a suburban street at night Before Storm could hit After You are first in line ↔ Neighborhood map with an address pin, a 5-mile ring and colored points on houses where storms were reported

Drag the line. Before the storm, you get the forecast. After it, you are first in line.

24 hours to 10 daysForecast, address by address
Value and peopleat every address
10 perilsCould happen, not will
5 centsper address. Free previews.
Refreshed 4 times a day. No contract.

The forecast suite

Forecasts and weather,
by address.

Atlas United risk models for every U.S. address: address-level storm forecasts for the next 24 hours to 10 days, plus every reported storm near that address back to 2003. Pay per address, no contract.

AtlasCast, an Atlas United product

ML Storm Forecast by Address

Probabilistic, address-level storm forecasts, 24 hours to 10 days ahead, for 10 perils: tornado, hail, wind, flash flood, heavy rain, winter, ice, coastal surge, hurricane and wildfire. A separate machine-learning model runs for each peril. Models are trained and validated chronologically on held-out reported events, and use only information available at forecast issue time. Forecasts refresh 4 times a day.

You get
Per address: structure replacement value in USD (replacement cost, not market value) and the estimated people there, plus the full address, forecast time, storm type, risk label and past storm reports. Every paid response carries a reference_id receipt.
Price
$0.05 per address. limit= caps the rows; limit=10 is a 50 cent sample.
Free preview
Free. County, window, counts per storm type and the exact cost, with the county A to F grade shown as a teaser only.
What it is not
Forecasts describe what could happen, not what will happen. Not a prediction of damage to any structure. The county grade is a whole-county label, not a property score.
dataset=risk&addresses=true

Atlas United

Model-Based Weather by Address

Point weather for any U.S. address or coordinate: current conditions, active severe weather alerts and a short-term rain outlook.

You get
The free lean answer: temperature, dewpoint, humidity, wind speed, gust and direction, precipitation and type, pressure, visibility and alerts. With details=true, over 170 variables, including hail size, storm rotation, lightning, reflectivity, instability, cloud layers, winds by level, soil, snow and vegetation.
Price
Free lean response. $0.0002 per call with details=true, or $0.0002 per location in a batch of up to 500.
Free preview
The lean response is the free preview. No account.
What it is not
Weather conditions, not a hazard or damage assessment.
dataset=weather&details=true

Atlas United

Model-Based Hourly Forecast by Address

Hour-by-hour forecast weather for any U.S. address or coordinate, 0 to 48 hours ahead. The answer says which forecast hour it used.

You get
Temperature, dewpoint, humidity, wind, gust, precipitation, visibility, pressure, hail size, lightning rate and a tornado rotation score for the hour you ask about, about 40 core fields with details=true, plus forecast_hour_used and a forecast note.
Price
$0.0002 per call with details=true. The lean answer is free.
Free preview
The lean response is free, no account.
What it is not
Forecast hours carry fewer fields than current conditions. Weather, not a hazard or damage assessment.
dataset=weather&hours_ahead=0-48

Free previews on every product. Forecasts describe what could happen, not what will happen. Not affiliated with NOAA or the NWS.

The free teaser: the county grade

Watch the county grade
as the storm gets close.

Press a day, or just watch. The county A to F grade climbs as the storm gets closer. It is a free teaser, a whole-county label. The product is the address records underneath it.

Example, not live dataExample county, Dallas TX
A
No current risk

Clear skies in the forecast. Nothing to do yet.

Day 0: forecast issuedDay 10: storm arrives
STORM LEADS BEFORE THE STORM

Reach out before the storm

See which addresses are in the forecast, with the structure value and people at each one. Call, text or email them while there is still time. Send your own message to them.

STORM TRACKING FOR YOUR LIST

Watch a whole list at once

Send up to 500 locations in one call. Get each one's county forecast status. County-level, not an address forecast. For address records use the forecast itself.

A real answer from the live API

Here is what
you get back.

Real free preview from today. No key needed. It is a county preview: counts and the exact cost before you buy any address.

curl, free preview
curl "https://data.truefixr.com/v1/data?dataset=risk&county=Dallas&state=TX"
JSON response (trimmed)
{
  "dataset": "risk",
  "county": "Dallas", "state": "TX",
  "window": "24h",
  "grade": "C",
  "grade_label": "Elevated risk",
  "total_leads": 725,
  "storm_types": { "HEAVY_RAIN": 642, "FLASH_FLOOD": 239 },
  "generated": "2026-10-03T03:29:41Z",
  "estimated_cost_usd": 36.25
}

Free. Nothing was charged.

Read it like this

  • "grade": "C" The county grade, a free teaser only. Not a property score.
  • "window": "24h" The next 24 hours.
  • "total_leads": 725 725 storm leads: addresses in the storm's path.
  • "storm_types" What is forecast: heavy rain and flash flood. One address can be in both.
  • "estimated_cost_usd" What the paid address list would cost. 725 x $0.05.

The free preview takes a county name so you can see the size and the price first. The paid pull gives you the address-level records. Forecast risk, could happen.

One address, one call

curl, free preview
curl "https://data.truefixr.com/v1/data?dataset=address&lat=32.78&lon=-96.80"
JSON response (trimmed)
{
  "dataset": "address",
  "storm_event_count": 297,
  "storm_types": { "HEAVY_RAIN": 297 },
  "current_forecast_risk": { "grade": "C", "grade_label": "Elevated risk" }
}

storm_event_count is how many reported and radar-detected storms were found near the point in the past year. current_forecast_risk is the county grade, context only. For address-level forecasts use dataset=risk.

One paid record

What you get
for each address.

A real, trimmed response from the live API. Lead with the value and the people. The A to F county grade appears only in free previews, as a teaser.

dataset=risk, addresses=true, limit=1
{"county":"Dallas","state":"TX","window":"24h","total_leads":809,"returned":1,
 "exposure_value_usd":204622180150,"exposure_people":1550820,
 "value_basis":"Replacement cost of structure (not market value)",
 "leads":[{"full_address":"405 Evergreen Trail, Cedar Hill, TX 75104","city":"Cedar Hill","state":"TX",
  "zip":"75104","county":"Dallas","lat":32.5599,"lon":-96.9493,"storm_type":"HEAVY_RAIN",
  "forecast_time":"2026-10-04T12:27:00Z","risk_label":"Extreme",
  "structure_value":300882,"people":3.5,"storm_hits":2}],
 "reference_id":"TFX-202610-6A3B8262"}
  • structure_value is the replacement cost of the structure in dollars, never market value.
  • people is the estimated number of occupants at that address.
  • risk_label is a word tier. Records carry no probability or severity number.
  • reference_id is your receipt. Forecasts describe what could happen, not what will happen.
Ten perils

Ten kinds of storm.
Every address.

A separate machine-learning model for each peril: hail, wind, tornado, flood and more. Models are trained and validated chronologically on held-out reported events, and use only information available at forecast issue time.

Tornado

Rotating storms that can touch down.

Hail

Ice that falls with a storm. Hail forecast by size.

Wind

Damaging straight-line wind gusts.

Flash Flood

Water rising fast after intense rain.

Heavy Rain

Rain heavy enough to cause trouble.

Winter

Snow and winter storms.

Ice

Freezing rain and ice build-up.

Coastal Surge

Ocean water pushed onto land.

Hurricane

Named tropical storms, wind and rain.

Wildfire

Fire risk in the coming days.

Just ask your AI

Copy. Paste.
Get told when risk rises.

No coding needed. Copy a box, paste it into Claude or ChatGPT, and it walks you through it step by step.

Check one address

Copy, paste into ChatGPT or Claude
Using the TrueFixR storm API (https://data.truefixr.com/llms.txt), what is the storm forecast for 2100 Ross Ave, Dallas this week? Use ML Storm Forecast by Address and tell me the structure value and people. My key: YOUR_KEY
Find leads before the storm
Using the TrueFixR storm API (https://data.truefixr.com/llms.txt), which addresses in Dallas County, TX have a high hail forecast risk in the next few days? Show the price first. My key: YOUR_KEY

Paste it into ChatGPT or Claude, swap in your address and your key.

More detail for your AI
Paste into Claude or ChatGPT
I want to know what storms are forecast near one address. Use ML Storm Forecast by Address from the TrueFixR API. Base URL: https://data.truefixr.com
Docs: https://truefixr.com/docs.html . Plain list of everything the API can do (free): https://data.truefixr.com/v1/data . Technical spec: https://data.truefixr.com/openapi.json .
Call GET /v1/data?dataset=address&lat=<lat>&lon=<lon>. This is a free preview and needs no key. It returns the property's past-year storm events and the county forecast grade as context (A is lowest, F is highest, a whole-county label). Explain the result in plain English like I am not technical. Say clearly this is forecast risk, something that could happen, not a promise and not an inspection. Do not make any paid call.
Address coordinates: 32.78, -96.80 (downtown Dallas)

What you get: A plain-English summary for that address, with the county grade as context only.

Watch my list of addresses

Copy, paste into ChatGPT or Claude
Using the TrueFixR storm API (https://data.truefixr.com/llms.txt), check every address in my spreadsheet and tell me which counties just got a worse forecast status. Show me the price first. My key: YOUR_KEY

Paste it into ChatGPT or Claude, swap in your address and your key.

More detail for your AI
Paste into Claude or ChatGPT
I have a list of customer addresses in a spreadsheet (a CSV file with columns name, address, lat, lon). Using the TrueFixR API, write me a script I can run every morning that tells me which of my locations just got a worse county forecast status.
Docs: https://truefixr.com/docs.html . Plain list of everything the API can do (free): https://data.truefixr.com/v1/data .
Use POST https://data.truefixr.com/v1/portfolio/risk with header Authorization: Bearer YOUR_KEY and body {"locations":[{"lat":..,"lon":..,"label":""}],"window":"24h"}. Up to 500 locations per call, $0.05 per location. My key is YOUR_KEY (I will replace it myself; keep it in an environment variable, never in the code). Save each day's grades to a file, compare with yesterday, and print only the locations whose county grade went up (for example B to C). Show me the cost before any paid call. Explain how to set it up and run it step by step like I am not technical.

What you get: A daily script that tells you only which locations sit in a county whose forecast status got worse.

See the ML storm forecast addresses in my counties

Copy, paste into ChatGPT or Claude
Using the TrueFixR storm API (https://data.truefixr.com/llms.txt), which storms are headed to Dallas and Harris counties in Texas? Start with the free daily list. My key: YOUR_KEY

Paste it into ChatGPT or Claude, swap in your address and your key.

More detail for your AI
Paste into Claude or ChatGPT
I want to see which addresses a storm is forecast to hit before it arrives. Set up a simple daily check for me using the TrueFixR AtlasCast API. TrueFixR does not send alerts; if I want a text or email, show me how to send my own. Base URL: https://data.truefixr.com . Docs: https://truefixr.com/docs.html .
Each morning, for each county on my list (Dallas TX, Harris TX), call GET /v1/data?dataset=risk&county=<county>&state=<state>. The free preview shows the county grade (A to F, a teaser), which storm types are forecast, and how many addresses are in the window. If the grade is C, D or F, send me an email or text saying which county and which storm types. Use the free preview only, no key needed. If I later want the address list, the paid pull is $0.05 per address with my key YOUR_KEY (I will replace it myself); ask me before any paid call. Explain how to set it up and run it step by step like I am not technical. Remind me this is forecast risk, could happen.

What you get: An email or text when a county you follow reaches county grade C or worse.

An API key is a password that lets your tool ask us for data. Free previews need no key. Paid pulls do: get one on Get started, then put it where the prompt says YOUR_KEY.

For developerscurl, Python and Node, all run for real
curl
curl "https://data.truefixr.com/v1/data?dataset=risk&county=Dallas&state=TX"

Routes: dataset=risk, dataset=address, dataset=at_risk (schools and businesses at risk, by peril and window), POST /v1/portfolio/risk. Full list at docs.

Pricing

Pay for what
you use.

Prepaid balance. No contract. Every route has a free preview that shows the real price first.

ML Storm Forecast by Address

$0.05 per address

Address-level records for a place and window, with structure value and people.

County forecast status

$0.05 per location

The county status for each of up to 500 locations in one call. County-level, not address-level.

Schools and businesses in the forecast

$0.05 per record

Sites in the forecast footprint, by storm type and window.

Forecast risk, could happen. Not a property inspection or a damage assessment. Not affiliated with NOAA or the National Weather Service.

Get startedSee all pricing

Your data. Your template. Your brand. Everything comes back as JSON you can save (lists also as CSV with format=csv).

Start free in 2 minutes.

No contract. Pay only for what you use.

Powered by atlasunited.io