Overview

Upload a PDF, PNG, or JPEG. OpenParser can return the document's text and layout, or extract fields into a JSON shape you define.

Make a request

curl -X POST 'https://api.openparser.dev/parse' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Idempotency-Key: $(uuidgen 2>/dev/null || openssl rand -hex 16)" \
  -F 'request={"ocr_model":"paddleocr-vl-1.6","output_format":"openparser@1"};type=application/json' \
  -F 'file=@./document.pdf'

openparser parse sync ./document.pdf

const parsed = await client.parse.sync(
  { ocr_model: 'paddleocr-vl-1.6', output_format: 'openparser@1' },
  file,
);

from pathlib import Path

parsed = client.parse.sync(
    {"ocr_model": "paddleocr-vl-1.6", "output_format": "openparser@1"},
    file=Path("document.pdf"),
)

A completed request returns a ParsedDocument with plain text, Markdown, pages, and semantic elements. If the document needs more time, the API returns a job ID that you can poll.

Official clients cover the same API as curl: @openparser/cli, @openparser/sdk, and openparser on PyPI. Start with the client guides for installation, retries, async jobs, uploads, and typed errors.

Pick the right endpoint

Every request is scoped to the organization that owns the API key. Parse and extract requests are durable: once accepted, they continue even if your client disconnects.