Frequently Asked Questions

DocsOCR is an AI-powered OCR API specialized in extracting structured data from Brazilian documents. It turns scanned documents into clean, structured JSON data ready for your systems.

Currently, DocsOCR specializes in Brazilian birth certificates (certidões de nascimento), with full field extraction including names, dates, registration numbers, and issuing office details. More document types are being added.

You send a document image via our REST API (PDF*, JPG, PNG, WebP or GIF). Our AI engines read the certificate, extract its fields and return structured JSON in seconds. *Only the first page of a PDF is read.

Accuracy depends on the image quality and the document's condition: that is why our standard takes images of 1344 to 2048 px on the long side, where extraction reads best. If one AI engine fails on a document, another processes it automatically. We recommend testing with your own documents.

DocsOCR has three AI engines: fast, mini and large. By default a request goes to the standard engines, mini and large, and if one fails, the next one answers automatically — no manual intervention needed. A request can also ask for the fast engine, which is tried first, with the standard engines behind it. If no engine can answer, the answer comes back as 201 with success: false and an errorCode, at no charge: send it again later.

We accept PDF*, JPG, PNG, WebP and GIF files, up to 10 MB per document. You can send files via URL or Base64-encoded content in the API request. Our image standard is 1344 to 2048 px on the long side (for an A4 scan, about 120 to 175 DPI), where extraction reads best: an image outside it is refused at no charge, or resized on our side for 1 extra credit when the request sets resizeImage: true, which adds a little time to the answer. *Only the first page of a PDF is read.

DocsOCR uses a pay-as-you-go credit system. Each extraction that returns data costs 1 credit on the standard engines. A request can ask for the fast engine instead: it costs 1.8 credits when it answers, and if fast cannot answer, a standard engine answers for 1 credit. A refused request, or one that no engine could serve, is free. New accounts receive free credits to get started — no credit card required.

Create a free account, generate an API key from the dashboard, and make your first API call. Check our interactive API documentation for code examples in multiple languages.

Yes. DocsOCR is 100% compliant with LGPD (Brazilian data protection law), GDPR, and CCPA. Document images are processed in real time and are not stored after extraction. Communication uses TLS 1.2 or 1.3, and stored data is encrypted at rest.

Absolutely. Every new account receives free credits to test the API with real documents. No credit card is required to sign up, and you can upgrade to a paid plan whenever you're ready.