Driver's License OCR API for 50 US States & 9 Countries

The API supports all 50 US states plus driver’s licenses from Canada, the United Kingdom, Australia, New Zealand, Japan, the Philippines, Thailand, Sweden and more. Every supported license has its own field reference, linked from the supported-countries grid on this page. The list grows continuously — if you need a country we don’t list yet, request it and we add most new document types in 1–2 days.

For a US license you get first and last name, license number, date of birth, issue and expiry dates, the address split into street, city, state and ZIP, gender, height, eye color, vehicle class and restrictions. Licenses in other countries return their own field set — for example the UK adds place of birth and vehicle categories, Australia adds the issuing state. The exact keys for each document are listed in that country’s reference, linked from the grid below.

For US licenses the address is returned as separate street, city, state and ZIP fields, so you can validate and store each part without parsing a raw string. Licenses in other countries return the full printed address as a single string, since their layouts don’t separate the components the same way. Check the country reference for the exact address shape per document.

documentType is country-specific for driver’s licenses — for example us_drivers_license, gb_drivers_license, au_drivers_license — and it tells the engine which format to read. You pass it with the image in the same request. The complete list of values is in the supported-countries grid on this page, and each entry links to that document’s reference. If you don’t know the country in advance, capture it from your onboarding flow and map it to the matching documentType.

Yes — the engine is built for real-world capture, not just clean scans. Detection and preprocessing handle glare, rotation, perspective skew and moderate blur on handheld photos. Image quality still matters: well-lit, in-focus, fully-in-frame photos yield better extraction, so guiding users to capture the license flat and well-lit measurably improves results.

Yes. US licenses come in horizontal and vertical (under-21) layouts and in Real ID compliant designs; the engine reads all of them, plus older format variations still in circulation. You pass the same us_drivers_license documentType regardless of the specific state layout.

The API is designed for the data-extraction step of KYC, age and identity verification: it turns a license into structured fields — name, license number, date of birth, expiry, address — that you can match against an application or use to gate by age. It is an OCR and data-extraction tool, not a full verification or authenticity-scoring service; liveness and document-authenticity checks are separate concerns you combine around it.

Sign up for a free trial, get an API key, and POST your first license image with the matching documentType — you’ll have structured JSON back in seconds. Pricing is usage-based with a free tier to start; see the pricing page for current tiers. Most teams begin by running the licenses they already collect through the API to measure extraction on their real traffic before going to production.