Back to API services

Developer API REST Lead enrichment

Website to Company data

AI-first REST API that turns a website URL into structured company, contact, and lead data.

Website to Company data is an AI-first REST API service for lead aggregators, CRMs, enrichment workflows, and internal automations. It crawls a website with depth 2, prepares deterministic parser context from structured data and page content, validates discovered emails, and sends the gathered website context to OpenRouter AI for strict structured extraction on every successful request. The response uses fixed category keys so downstream systems can parse it safely.

GET /api/website-to-company-data/v1/extract

View API documentation Login

Starting at Free

REST API service

Turn a company website into structured lead data

Website to Company data is built for lead aggregators, enrichment products, CRM imports, and internal automations that start with only a website URL. The API crawls relevant pages, extracts structured company data, validates emails, and returns a stable JSON schema that can be parsed without guessing dynamic keys.

The extraction flow is AI-first. The crawler collects high-signal pages, deterministic parsing prepares support context, and selected HTML is sent to the default OpenRouter model with a strict extraction prompt on every successful request. The API still keeps fixed categories for sales, support, info, billing, careers, press, legal, technical, general, and other.

Depth 2 crawling

Homepage plus relevant contact, about, team, location, legal, and support pages.

Stable categories

Emails, phones, and people always use the same fixed category keys.

Email validation

Invalid, example, demo, and no-MX email addresses are filtered out.

AI-first extraction

OpenRouter extraction is always used as the primary extraction layer.

How it works

AI-first company data extraction

Validate URL and token

The service checks the token, quota, URL shape, and blocks private/local network targets.

Crawl relevant pages

The crawler fetches the homepage and high-signal internal pages up to depth 2.

Prepare parser context

HTML, JSON-LD, meta tags, mailto links, tel links, and page text are parsed as support context.

Force AI extraction

Selected HTML and parser context are sent to OpenRouter for strict JSON extraction on every successful request.

Stable schema

Fixed contact categories

Every response keeps the same category keys for email addresses, phone numbers, and people, even when a category is empty.

sales support info billing careers press legal technical general other

Use cases

Built for lead and enrichment workflows

Lead aggregators that need contact data from website URLs.
CRM enrichment before importing raw company domains.
Sales ops workflows that need sales/support/info emails separated.
Internal automation that needs company name, address, phone, and people from websites.
Quality checks for landing pages and business websites.

Extraction Capabilities

AI-first extraction with deterministic parser context, fixed categories, and validated email results.

Depth 2 website crawler

Fetches the homepage and relevant candidate pages such as contact, about, team, legal, and location pages.

Structured company profile

Returns company name, industry, address, city, country, location, and source confidence in a stable JSON schema.

Fixed contact categories

Emails, phones, and contact person names are returned under stable keys such as sales, support, info, billing, careers, legal, technical, general, and other.

Validated emails

Discovered email addresses are filtered, deduplicated, checked for syntax and MX records, and generic demo addresses are ignored.

AI-first extraction

Every successful extraction sends selected website HTML and parser context to the default OpenRouter model for structured JSON output.

Token and quota control

Every request is tied to a service token and plan-based lifetime or daily website quota.

API Plans

Website extraction quotas for enrichment workflows of different sizes.

Free

Test the API with a one-time lifetime allowance.

Free

25 websites lifetime

25 website extractions lifetime
Depth 2 parser and structured extraction
Email syntax and MX validation
AI fallback when parser data is incomplete

Plus

Daily capacity for small lead enrichment workflows and internal tools.

EUR 19.99/mo billed monthly

200 websites per day

200 website extractions per day
Depth 2 parser and structured extraction
Email syntax and MX validation
AI fallback when parser data is incomplete

Recommended

Pro

Higher daily capacity for production lead aggregators and CRM pipelines.

EUR 89.99/mo billed monthly

1000 websites per day

1000 website extractions per day
Depth 2 parser and structured extraction
Email syntax and MX validation
AI fallback when parser data is incomplete

Ultimate

Large daily quota for high-volume enrichment systems.

EUR 399.99/mo billed monthly

20000 websites per day

20000 website extractions per day
Depth 2 parser and structured extraction
Email syntax and MX validation
AI fallback when parser data is incomplete

Endpoint pattern

One URL in, structured company data out

Use the documentation page to generate your token, inspect quotas, and test live responses.

GET https://ai.mihajlo.mk/api/website-to-company-data/v1/extract?website=https://example.com&token={serviceTokenHere}