Estimate Property Value
estimate_property_valueGet an automated valuation (AVM) for a property — low / mid / high price range.
Use find_property_comparables instead if you want the raw comparable transactions with similarity scores. estimate_property_value returns only the AVM summary (low/mid/high range).
REQUIRED: latitude, longitude, surface
Optional:
type_local: "Maison" or "Appartement" (default: Appartement)
pieces: Number of rooms
code_postal, commune: Optional administrative fallback when GPS comparables are sparse
radius_m: Search radius (100–2000m, default: 500)
max_age_months: Max transaction age (1–24, default: 18)
Returns:
price_range: { low, mid, high } in euros
price_per_m2: { median, used_surface }
confidence: "high", "medium" or "low": how much the retained comparables agree on price/m² (dispersion (P75-P25)/median: high <15%, medium 15-50%, low >=50%). Measured on 1,957 masked DVF sales: median error 12% / 20% / 30%. It is not a probability of accuracy: even at "high", half of the outcomes fall outside price_range.
confidence_basis: "comparable_agreement" — names what confidence measures.
based_on_count: number of comparables used
interval: { method, coverage_label, basis, cohort, cohort_eligible_n, ratio_low, ratio_high, contract_version, calibration_generated_at } — how price_range was derived.
confidence_factors: { comparable_count, average_similarity, fallback_used, positive_factors[], limiting_factors[] } — what strengthens or limits the estimate.
Returns estimate: null with a message if fewer than 3 comparables are found. Tip: increase radius_m or max_age_months to get more data.
Note: the low/high range is a data-calibrated 50% interquartile interval (P25/P75 of observed-price / published-mid, backtest-measured on 2,000 masked DVF sales), not a fixed percentage. Its width is driven first by how much the retained comparables agree on price/m² — the dispersion cohort, (P75-P25) / median, e.g. interval.cohort = "dispersion=<15%" — then by comparable density, property type and surface band, and it widens to the global cohort when a segment lacks enough measured data (interval.basis). Agreeing or contradicting comparables also surface as confidence_factors comparables_agree / comparables_disagree. The mid value is unaffected by any of this. DVF data covers 2014–2025 (annual cadence). Use max_age_months ≥ 12 for reliable results.
Cost: 10 credits per call
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| pieces | No | Number of rooms (±1 tolerance applied to comparables) | |
| commune | No | Commune fallback when GPS comparables are sparse | |
| surface | Yes | Surface area in m² | |
| latitude | Yes | GPS latitude of the target property | |
| radius_m | No | Search radius in meters (default: 500) | |
| longitude | Yes | GPS longitude of the target property | |
| type_local | No | Property type (default: Appartement) | |
| code_postal | No | Postal code fallback when GPS comparables are sparse | |
| max_age_months | No | Max age of comparable transactions in months (default: 18 — DVF updates semi-annually) |