---
title: "Find Comparable Sold Properties — AI Analysis API"
description: "Return recent comparable sold properties for a subject address, each with sale price, sale date, distance, and similarity scoring to justify a valuation."
---

# Comparable sold properties (comps) for a subject property

`GET /api/properties/comps/`

5 credits

## What it returns

A ranked list of **comparable sold properties** within a search radius of the subject — each comp scored on similarity (size, beds/baths, year built, distance, condition delta) with the sale price and date. Powers AVM and ARV computations.

## When to use it

- Build a comps table on a property report page.
- Validate AVM against the comparable set it's derived from.
- Power custom value models with raw comp inputs.

## Performance

**This is a slow endpoint — use a 60-second client timeout and cache responses.**

## Pricing

5 credits.

## FAQ

### How are comps ranked?
By a weighted similarity score that favors smaller size/feature deltas and shorter geographic distance. Sold date recency is a strong negative weight on older sales.

### Does it adjust for condition?
Yes — if both the subject and comp have AI-condition scores, prices are adjusted up/down for the condition delta.

## Fallback parameters

You can pass user-supplied values for the attributes the comp model uses, as **fallbacks**: Homesage.ai data is always used when available; your value is used only when our record is missing that field — so verified data is never overridden. Supported fallbacks: `total_size`, `bedrooms`, `bathrooms`, `property_type`. Only `total_size` can unblock an otherwise-empty result; the others just refine comp matching. `year_built` is intentionally **not** a factor in the comp/ARV model.

Every response includes a `field_sources` object telling you where each value came from: `homesage` (our data), `user_provided` (your fallback), or `unavailable`.