OCR for developers.

The fastest way to extract data from documents using AI.

$
bun i document-sdkcurl api.ocrbase.com/extract

Works with any model

Swap between PaddleOCR and GLM-OCR, or bring your own VLM with a single config change.

4 functions, that's it

parse, extract, batchParse, batchExtract. No bloat, no complexity.

Structured outputs

Extract data from documents directly into typed JSON with schema validation.

Start extracting today

ocrbase powers document extraction for some of the fastest growing teams.