Home/Offers/Real Estate & Property/Construction Cost Estimation API

Real Estate & Property

Construction Cost Estimation API

Early-stage cost estimates decide whether a scheme goes ahead. They are usually produced from a rate per square metre that was true two years ago.

Developers
Contractors
Quantity surveying software
Lenders
Insurers

Discuss This Build See What It Returns

What your customers would see

example interface

MockupIllustrative mockup of the interface we would build. Figures shown are examples, not results from a live deployment.

The problem this solves

Feasibility costing happens before there is enough design to cost properly, which is precisely why it matters. A developer deciding whether to pursue a site needs a number within days, and the number they get is usually a benchmark rate per square metre, adjusted by judgement, with no indication of how wide the plausible range is.

Material prices have made this harder. Steel, timber, cement and insulation have all moved sharply enough in recent years that a rate derived from projects completed eighteen months ago can be badly stale, and the direction is not uniform — some inputs fell while others kept rising. Labour has its own regional dynamics, with availability in some trades constraining price independently of material cost.

The honest version of this product does two things conventional benchmarks do not. It separates the estimate into material and labour components that can be re-priced as inputs move, and it attaches a range that reflects how little is known at this design stage. A feasibility estimate presented as a single figure invites a decision the data cannot support.

Who buys this

Developers, Contractors, Quantity surveying software, Lenders, Insurers

Category: Real Estate & Property

What the API returns

What comes back

Whole-project cost estimate with a stated uncertainty range tied to design stage
Breakdown by element: substructure, frame, envelope, services, fit-out, external works
Material and labour split per element, so each can be re-priced independently
Regional cost adjustment factors with the basis disclosed
Material price index series and the exposure of the project to each input
Programme duration estimate and the cost consequence of extension
Contingency recommendation derived from design stage and project characteristics
Comparable completed projects, where you hold or license the cost data

Endpoints

Method	Path	Returns
POST	/v1/estimate	Estimate project cost from scheme parameters
POST	/v1/estimate/elemental	Elemental breakdown with material and labour split
GET	/v1/indices/materials	Material price index series and recent movement
GET	/v1/regions/{id}/factors	Regional labour and material adjustment factors
POST	/v1/estimate/reprice	Re-price a stored estimate against current indices
POST	/v1/comparables	Comparable completed projects from your own cost history

Request and response

illustrative

Request

{
  "project": {
    "type": "residential_apartments",
    "storeys": 6,
    "units": 48,
    "gia_sqm": 4320,
    "structure": "rc_frame",
    "cladding": "brick_slip_rainscreen",
    "basement": false,
    "region": "GB-NW",
    "site_constraints": ["tight_urban", "no_crane_oversail"]
  },
  "design_stage": "concept",
  "start_on_site": "2027-04-01",
  "include": ["elemental", "contingency", "programme"]
}

Response

{
  "estimate": {
    "total": 9460000,
    "currency": "GBP",
    "per_sqm": 2190,
    "range_80": [8520000, 10690000],
    "design_stage": "concept",
    "range_basis": "concept_stage_dispersion_from_completed_projects"
  },
  "elements": [
    { "element": "substructure", "cost": 760000, "material_pct": 54, "labour_pct": 46 },
    { "element": "frame_and_upper_floors", "cost": 1890000, "material_pct": 61, "labour_pct": 39 },
    { "element": "envelope", "cost": 1620000, "material_pct": 58, "labour_pct": 42 },
    { "element": "services", "cost": 2070000, "material_pct": 49, "labour_pct": 51 },
    { "element": "fit_out", "cost": 2210000, "material_pct": 52, "labour_pct": 48 },
    { "element": "external_works", "cost": 910000, "material_pct": 47, "labour_pct": 53 }
  ],
  "regional_factor": 0.94,
  "material_exposure": [
    { "input": "reinforcement_steel", "share_of_cost": 0.09, "index_12m_pct": 7.4 },
    { "input": "cement_and_concrete", "share_of_cost": 0.11, "index_12m_pct": 3.1 },
    { "input": "insulation", "share_of_cost": 0.05, "index_12m_pct": 11.2 }
  ],
  "programme": { "months": 26, "cost_per_month_extension": 88000 },
  "contingency": { "recommended_pct": 12, "basis": "concept stage, constrained urban site" },
  "caveats": [
    "No ground investigation supplied; substructure carries the widest uncertainty",
    "Excludes land, finance, professional fees and VAT unless specified"
  ]
}

Where the data comes from

Published construction cost indices	Official and licensed index series for materials, labour and tender prices, which is how estimates stay current between projects
Material price data	Input prices for the major commodities, from licensed market data and published producer indices
Your own completed project costs	Final accounts from your past projects — the single most valuable input, and the only one calibrated to how you actually build
Labour rate and availability data	Regional wage and trade-availability statistics from official labour market sources
Benchmark cost datasets	Licensed elemental cost libraries, where your use case is covered by the licence terms
Regulatory and standards changes	Building regulation and compliance changes that move cost, such as fire safety and energy standards

On data licensing. Being allowed to read a dataset does not automatically mean you may redistribute it, resell it through an API, or train a model on it. Before any build starts we check the licence, terms and derived-data rules of every source, and we design around the ones that do not permit your intended use. Where a commercial licence is required, that cost is identified during discovery rather than discovered later.

The intelligence layer

The difference between a demo and a service is mostly in this section. These are the parts that keep the answer trustworthy once real traffic is hitting it.

Elemental estimation with material and labour decomposed per element, so each component can be re-priced against its own index rather than inflated uniformly
Uncertainty ranges derived from observed dispersion of completed projects at each design stage, not from a chosen percentage
Regional adjustment factors estimated from completed project data where available, falling back to published factors with the basis stated
Site-constraint adjustments for access, oversail, phasing and working restrictions, which are frequently the difference between a good and a bad estimate
Index-linked re-pricing so a stored estimate can be brought current without re-running the whole exercise
Programme modelling with an explicit monthly extension cost, because time is a cost line most feasibility estimates omit
Validation against held-out completed projects, reported by project type and design stage so the concept-stage error is visible separately
Monitoring on index freshness and on systematic bias against outturn costs as projects complete

What it changes for the business

Faster feasibility

A credible range within hours lets a developer decide whether a site is worth pursuing at all.

Honest ranges in appraisals

A stated uncertainty band changes how a board or a lender reads a feasibility number.

Current pricing

Index-linked re-pricing stops appraisals quietly resting on rates from two years ago.

Reusable cost knowledge

Your own completed project costs become a calibrated asset rather than a folder of final accounts.

How it fits into your product

How it embeds

Synchronous estimation for use inside a feasibility or appraisal tool
Stored estimates with a re-pricing endpoint, so an appraisal can be refreshed against current indices on demand
Elemental output in a structure your existing cost planning templates can consume
Ingestion of your own final accounts, which is what moves accuracy from benchmark level to your level
Export to the spreadsheet formats quantity surveyors actually work in
Deployment inside your environment where project cost data is commercially sensitive

Included in every build

Authentication, scoped API keys and per-customer rate limiting
Input validation with predictable, documented error responses
Versioned endpoints so your integration never breaks without notice
Request and response logging for audit and dispute resolution
Latency, error-rate and usage monitoring with alerting
OpenAPI specification, sandbox environment and client examples
Backups, failover design and a documented recovery procedure
An agreed support arrangement once the service is live

How we would build it

about 12 weeks

Discovery and data review

Weeks 1–2

We agree the exact question the API answers, review the sources you already hold, check what has to be licensed, and write down the response contract your developers will code against.

Architecture and prototype

Weeks 3–4

You get a written architecture plus a working endpoint on real data — narrow, but genuinely callable — so integration can be tested against something concrete rather than a document.

Production build

Weeks 5–10

Pipelines, models, storage, authentication, rate limiting, logging, tests and documentation. Security and observability are part of this phase, not a later one.

Integration and handover

Weeks 11–12

We support your engineers through their integration, run load tests at your expected volume, and agree how the service is monitored and supported once it is live.

Commercial models

There is no fixed price list, because the cost is driven by data complexity, integration count, model requirements, request volume and the support level you need. Scope is agreed in writing before development starts.

Fixed-scope prototype

A defined slice of the service, built and priced as one piece of work. The usual first step when the business case needs proving internally.

Fixed-price build

An agreed scope against a written architecture, delivered for an agreed price. Best when the requirements are already clear.

Build then retainer

We build the service, then operate and improve it under a monthly agreement covering monitoring, updates and model maintenance.

White-label product

The service runs under your brand, your domain and your pricing, with MLPivot invisible to your customers.

Questions buyers ask

How accurate can a concept-stage estimate be?

Not very, and anyone claiming otherwise is misrepresenting the problem. At concept stage, with no ground investigation and an outline design, the plausible range on a project like this is commonly plus or minus ten to fifteen per cent, and wider on constrained or unusual sites. The API returns that range rather than a single figure, because the figure alone invites a decision the information cannot support.

Will it replace a quantity surveyor?

No. It produces early-stage estimates and keeps them current; it does not measure a design, price a bill of quantities, or exercise the judgement a surveyor applies to a specific site. The useful framing is that it handles the feasibility stage so the surveyor's time goes where measurement actually matters.

Can you use published cost benchmark libraries?

Only within their licence terms, which commonly permit internal use but not redistribution through an API to your customers. That distinction determines the architecture, so we establish it in discovery. Where redistribution is not permitted we build on indices, your own project history, and sources whose terms allow it.

What does it not include?

Land, finance costs, professional fees, planning obligations and tax are excluded unless you explicitly configure them in, and the response says so. Those lines are highly specific to the deal and silently bundling an assumption about them is how a feasibility estimate becomes misleading.

How much of our own cost history do you need?

It works on published indices and benchmarks alone, at benchmark accuracy. Twenty or thirty completed final accounts of comparable project types is usually enough to begin calibrating to how you build, and the improvement from that is larger than any modelling refinement we could make without it.

All Real Estate & Property offers →

Want this built for your platform?

Tell us what your product does today and what you want another system to be able to ask it. We will come back with an approach, a scope and a price.

Discuss This Build Browse All Offers