Sold by: Atlas United
Probabilistic address-level storm forecasts from per-peril machine-learning models, 24 hours to 10 days ahead, refreshed 4 times a day. Each address carries its structure replacement value and people. $0.05 per address.
Overview
Image
Product overview
Image
Sample response
Image
County map
ML Storm Forecast by Address
Address-level storm forecasts for the next 24 hours to 10 days. A separate machine-learning model runs for each of 10 perils: tornado, hail, wind, flash flood, heavy rain, winter, ice, coastal surge, hurricane and wildfire. 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 and every response is timestamped and versioned.
What each record contains
- Address, city, state, ZIP, county and coordinates
- Storm type, forecast time and a risk label
- Structure replacement value (not market value) and estimated people at the address
- Past-hit count, and a reference_id receipt on every paid response
Filter by county, peril and window (24h, 48h, 3d, 5d, 7d, 10d).
Who it is for
- Insurance carriers and reinsurers: pre-event exposure reports by county and peril.
- Emergency management: pre-position resources using people and value counts per address.
- Utilities, property managers and restoration teams: stage crews and equipment ahead of wind, hail, ice or flood.
- Lenders and municipalities: monitor portfolios and service areas.
- AI agents and data teams: one JSON endpoint, free previews, pay per returned address.
Getting started
- Subscribe through AWS Marketplace and complete the registration page to receive your API key.
- Call https://data.truefixr.com/v1/data with no parameters to see the machine-readable menu of datasets, prices and parameters.
- Add dataset=risk and your filters. The default response is a free preview with counts and the exact price.
- Add addresses=true to pull the paid records. JSON responses, with CSV available on selected datasets. Documentation, free previews and pricing: https://atlasunited.io/api
Forecasts describe what could happen, not what will happen, and are not a prediction of damage to any structure. Built by Atlas United. Not affiliated with NOAA or the NWS.ML Storm Forecast by Address returns the addresses inside the forecast footprint for the coming 24 hours to 10 days. A separate machine-learning model runs for each of 10 perils: tornado, hail, wind, flash flood, heavy rain, winter, ice, coastal surge, hurricane and wildfire. 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 and every response is timestamped and versioned. Each address record leads with the structure replacement value (not market value) and the estimated people at that address, plus storm type, forecast time, a risk label and a past-hit count. Filter by county, peril and window (24h, 48h, 3d, 5d, 7d, 10d).
Pricing is per returned address. A free preview shows counts, per-peril totals and the exact cost before you pay, and every paid response carries a reference_id receipt. Forecasts describe what could happen, not what will happen, and are not a prediction of damage to any structure.
Built by Atlas United. Not affiliated with NOAA or the NWS.
Highlights
- Address-level forecasts for 10 perils, 24 hours to 10 days ahead, refreshed 4 times a day, timestamped and versioned.
- Each address record includes structure replacement value and estimated people, so you can size exposure before a storm arrives.
- Pay per returned address with a free preview of counts and exact cost first. No contract. API key or pay-per-call.
Details
Sold by
Categories
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit |
|---|---|---|
Forecast addresses returned | One returned address record in a forecast pull, priced per address | $0.05 |
Dimensions summary
This listing uses one usage-based dimension. You pay per forecast address record returned in a pull. Pricing scales directly with how many address-level records you request. There are no tiers, seats, or fixed plans. You preview counts for free, then pay only for the real address records you pull. Your cost rises in step with the number of addresses returned. The forecast refreshes four times a day, so pulling again after a refresh counts as new addresses returned and bills accordingly.
Top-of-mind questions for buyers
One address record is a single property returned in a real pull. Each record leads with structure replacement value and estimated people, plus full address, storm type, forecast time, and a risk label. You preview counts for free, then pay only for the address records returned when you add addresses=true.
Yes. Adding a peril filter narrows results to one storm type, so fewer addresses return on the real pull. Since you pay per address returned, filtering lowers the count billed. The free preview shows exact counts and cost before you pull.
No. Preview calls return counts, per-peril totals, and the exact price with no token and no charge. You pay only when you add addresses=true with your API key, which triggers the real pull of address records and bills per address returned.
atlasunited.io+1
Helpful?
Vendor refund policy
Usage is billed only for records returned to you. If a response was billed in error, such as a failed pull or a duplicate charge, contact us within 30 days with the reference_id from the response and we will review it and refund or credit the billed usage. Records already delivered and correctly billed are not refundable. Contact: https://atlasunited.io/api
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
API
To get started with ML Storm Forecast by Address, follow the instructions below.
Prerequisites An active subscription to this listing on AWS Marketplace and any HTTP client or AI agent with HTTP access.
Authentication
- After you subscribe, choose "Set up your account" and finish the short form. Your API key is shown once on that page. If you lose it, choose "Set up your account" again in AWS Marketplace to get a new key; the old key stops working.
- Send the key on every paid request in this HTTP header: Authorization: Bearer YOUR_API_KEY Replace YOUR_API_KEY with your actual key. Free previews need no key.
Endpoint: GET <https://data.truefixr.com/v1/data> with dataset=risk POST <https://data.truefixr.com/v1/data> accepts the same parameters as a JSON body (keeps addresses out of URLs and logs). Lists the addresses inside the forecast footprint for the next 24 hours to 10 days, for 10 perils: tornado, hail, wind, flash flood, heavy rain, winter, ice, coastal surge, hurricane and wildfire. Forecasts describe what could happen, not what will happen.
Query Parameters:
| Param | Type | Description |
|---|---|---|
| dataset | string | risk (required) |
| county + state | string | County name and 2-letter state, for example Dallas and TX. Or use lat + lon. |
| window | string | 24h, 48h, 3d, 5d, 7d or 10d |
| peril | string | Optional. Narrow to one peril, for example HAIL |
| addresses | boolean | true returns the paid address records. Omit for the free preview. |
| limit | int | Maximum addresses to return and bill (default 2000, max 5000) |
Example Request (free preview, shows count and exact cost):
curl "https://data.truefixr.com/v1/data?dataset=risk&county=Dallas&state=TX&window=24h"Example Request (paid pull):
curl "https://data.truefixr.com/v1/data?dataset=risk&county=Dallas&state=TX&window=24h&addresses=true&limit=10" \ -H "Authorization: Bearer YOUR_API_KEY"Response Schema (free preview):
{"dataset":"risk","county":"string","state":"string","window":"string","total_leads":number, "storm_types":{"HAIL":number},"estimated_cost_usd":number,"generated":"UTC timestamp","dataset_version":"string"}Response Schema (paid):
{"reference_id":"string","county":"string","state":"string","window":"string","total_leads":number,"returned":number, "lead_cap":number,"exposure_value_usd":number,"exposure_people":number,"generated":"UTC timestamp", "leads":[{"full_address":"string","city":"string","state":"string","zip":"string","county":"string", "lat":number,"lon":number,"storm_type":"string","forecast_time":"UTC timestamp","risk_label":"string", "structure_value":number,"people":number,"storm_hits":number}]}structure_value is replacement cost in US dollars, not market value. Pricing: $0.05 per address returned. Billing unit: forecast_addresses.
Error Codes
| Status | Code | Meaning |
|---|---|---|
| 400 | bad_request | A required parameter is missing or invalid. The detail field says which. |
| 401 | unauthorized | The key is not valid. |
| 402 | payment_required | A paid pull was requested without a valid key or enough prepaid balance. |
| 404 | not_found | No data for that location or filter. |
| 422 | invalid_parameter | A parameter value is not accepted. The response names the field and accepted values. |
| 429 | rate_limited | Too many requests. Wait and retry with exponential backoff. |
| 500, 502, 503 | server_error | Temporary server problem. Retry later. |
Error responses follow this structure: {"detail": "dataset=risk needs county+state, or lat+lon", "code": "bad_request", "request_id": "f38f7e69f7fb4ad4"} Quote the request_id (or the reference_id on a paid response) in a support request.
Learn More Docs: https://atlasunited.io/api Menu of every dataset, parameter and price: GET https://data.truefixr.com/v1/data MCP server for AI agents: https://mcp.atlasunited.io/mcp
Resources
Vendor resources
Support
Vendor support
Support: https://atlasunited.io/api for documentation, pricing and free previews. Email admin@truefixr.com , answered by the Atlas United team on business days. Include the reference_id from any paid response. We help with integration, response fields and billing questions. If a charge looks wrong, send the reference_id and we will review it.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Predictive storm planning reduces crew costs while improving safety and customer satisfaction
The solution provides 30 days forecast of web traffic using historical web traffic data.
With TensorIoT, get expert guidance and development for enhanced forecasting with machine learning.
The Accenture Multimedia Advertising Platform is a comprehensive and customizable platform that integrates artificial intelligence to accurately predict customer advertising preferences. It leverages process automation and advanced analytics to forecast highly qualified audience impressions over any digital platform resulting in increased monetization of ad inventories across all digital sales channels, while prioritizing privacy compliance.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.