The agent storefront at https://agents.homesage.ai/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.
AI property data APIs for proptech teams
One API key gives your app 30+ endpoints on 160M+ US properties. Alongside the records, you get AI fields such as condition from photos and the Seller Motivation Score.
cURLPythonJavaScript
curl -G "https://api.homesage.ai/api/properties/property-condition/" \ -H "Authorization: Bearer $HOMESAGE_API_KEY" \ --data-urlencode "property_address="
import os, requests
r = requests.get(
"https://api.homesage.ai/api/properties/property-condition/",
headers={"Authorization": f"Bearer {os.environ['HOMESAGE_API_KEY']}"},
params={"property_address": ""},
)
print(r.json()["Property Condition"])
const url = new URL("https://api.homesage.ai/api/properties/property-condition/");
url.searchParams.set("property_address", "");
const res = await fetch(url, {
headers: { Authorization: `Bearer ${process.env.HOMESAGE_API_KEY}` },
});
const data = await res.json();
Response
// property-condition, from listing photos
{ "Property Condition": "Good" }
// current-estimate
{ "Estimates": { "current_value": 583410.33 } }
// pfs, the Seller Motivation Score
{ "pfs": 1.43 }
3 sample responses from our public docs pages. Estimated values.
160M+US properties
30+API endpoints
200B+data points
API and MCPone key for both
Each endpoint group below has its own docs page with inputs and a sample response.
| Field | What you get | Made by | Endpoint |
|---|---|---|---|
| Property lookup | Address autocomplete, the full property record and bulk records with estimated returns. | Property records | info |
| Valuation | Current estimated value, 5-year value history, rent projections and renovation returns. | AI model | current-estimate |
| Seller Motivation Score | How much room a seller leaves to negotiate, from days on market, price changes and comps. | AI model | price-flexibility-score |
| Condition from photos | Read from the listing photos as Excellent, Good, Fair or Poor. | AI model | property-condition |
| Room-by-room renovation budget | An LLM prices each room from the photos, with low and high costs. | AI model | renovation-cost-breakdown |
| Comps | Recent sold properties near the subject, each with a confidence score. | AI model | comps |
| Rent estimates | Long-term and short-term rent, net operating income and cap rate. | AI model | rental-long-term |
| Market outlook | A 0 to 100 score per ZIP code, from buyer’s to seller’s market. | AI model | market-outlook |
| Full Property Report | 292 fields from 11 data sources in one response. | AI model | full-report |
| Property search | Search a city, county or ZIP by investment filters, with a match count first. | Property records | run-property-search |
Everything you need before the first call.
| Item | Detail |
|---|---|
| Base URL | https://api.homesage.ai |
| Authentication | Your API key as a Bearer token in the Authorization header. |
| Format | JSON over HTTPS. |
| Spec | OpenAPI 3.0.3, machine-readable. |
| Docs | One page per endpoint, plus the docs as plain text for AI coding tools. |
| AI agents | The MCP server exposes 30+ tools through one connection. |
| Code samples | Quickstart on GitHub. |
Records tell you what a property is. Our models add what it is worth, what it needs and how open a seller is to negotiate.
Property addressMatched to 1 of 160M+ US property records.
Listing photosRead by the vision and renovation models.
Sold and loan recordsRecent sales nearby, mortgages and liens.
Market signalsDays on market, price changes and ZIP activity.
Vision condition modelScores condition from the listing photos.
Renovation budget modelAn LLM prices each room from the photos.
Valuation and comps modelsEstimate value, rents and returns from similar properties.
Seller Motivation Score modelReads days on market, price changes and comps.
Property ConditionExcellent, Good, Fair or Poor.
EstimatesValue, rents and estimated ARV.
pfsThe Seller Motivation Score.
Renovation budgetRoom by room, as JSON.
Every AI field is an estimate. Show it to your users as an estimate, with the date you pulled it.
Each feature maps to the endpoints that power it.
Let your users type an address and open the full record.
Address autocomplete auto-complete
Up to 5 US address suggestions from a partial address.
Property record info
Listing status and price, estimated value and size. It also returns beds, baths, year built and days on market.
Full Property Report full-report
292 fields from 11 data sources in one response.
Show what a property is worth today and how that value moved.
Current estimate current-estimate
Today’s estimated value for the property, as one number.
5-year value history home-value-history
A monthly estimated value for the last 5 years, ready to chart.
Comparable sales comps
Recent sold properties near the subject with sale price, sale date and distance. It also returns an estimated ARV.
Show investors in your app the income side of a deal.
Long-term rental rental-long-term
Estimated monthly rent and net operating income for a 12-month lease. It also returns cap rate, cash-on-cash return and IRR.
Short-term rental rental-short-term
Estimated nightly and monthly gross income, net operating income, cap rate and monthly cash flow.
Investment potential investment-potential
An investment-potential score from 0 to 100.
Add signals our models build from photos and price history.
Property condition property-condition
A condition score from the property photos. Scores run Excellent, Good, Fair or Poor.
Room-by-room renovation budget renovation-cost-breakdown
A room-by-room renovation estimate from the property photos, with a low and high cost per item and major red flags.
Fixer-upper check needs-tlc-check
A yes or no flag for properties likely to need major renovation.
Seller Motivation Score price-flexibility-score
How much room a seller leaves to negotiate, based on days on market, price changes and comps. A higher score means more room.
Create an account and copy your API key from the developer dashboard.
Call address autocomplete, then pass the matched address to any endpoint.
Every endpoint takes the same key and returns JSON.
cURL
curl -G "https://api.homesage.ai/api/properties/current-estimate/" \ -H "Authorization: Bearer $HOMESAGE_API_KEY" \ --data-urlencode "property_address="
Response
{
"address": "",
"Estimates": {
"current_value": 583410.33
}
}
Sample response from the current estimate docs page. Estimated value. Address hidden.
| Option | Best for | Start here |
|---|---|---|
| REST API | Your own software, models and data pipelines | API docs, one page per endpoint |
| MCP server | AI agents and chat features inside your product | Connect the MCP |
| OpenAPI and llms.txt | Generating clients or prompting AI coding tools | OpenAPI spec and docs as plain text |
| GitHub quickstart | Copying working examples | Quickstart repo |
Property records, estimated values and value history come first. Your app can also show rents, comps and the ZIP market outlook, plus AI fields such as condition from photos.
Our models produce condition, renovation budgets and estimated values. They also produce rents, comps scores and the estimated ARV. The Seller Motivation Score, investment potential and market outlook are model scores too.
Send your API key as a Bearer token in the Authorization header. Every endpoint uses the same key.
The OpenAPI 3.0.3 spec lists every parameter, schema and error code.
Connect your agent to the Homesage.ai MCP. It exposes the same data as 30+ tools.
We do not offer an MLS or IDX feed, and we do not supply listing photos for reuse.
The photo models only see what the listing photos show.
Coverage is the United States only.
AI fields are estimates. Label them as estimates in your app.
Usage is credit-based. Plans are on the pricing page.
Screen a city, county or ZIP against your buy box, with AI scores on every match.
Hard money and private lenders
Estimated ARV, renovation budget from photos, comps and liens before you fund a flip loan.
AI-ranked comps, estimated values and ZIP market outlook for every listing.
Our developer page, with platform examples.
Both ways to connect, side by side.
Connect Claude, ChatGPT and other assistants in 3 steps.
Every endpoint group on one page.
MCP vs APIs for real estate apps
When to use each one in your build.
A plain guide for product teams.
Create an account, get your API key and call the address autocomplete endpoint. Or book a demo to talk through your build.
Estimated values. Not investment advice. Sample responses come from our public API docs, read 2026-11-07.