$10 credits at signup, $1 per 1,000 pages

Hosted PaddleOCR API
at $1 per 1,000 pages.

OpenParser hosts PaddleOCR-VL-1.6 on POST /parse. Send PDFs and images; receive typed layout elements or markdown, then run /extract with source citations.

Create an API key
PaddleOCR-VL-1.6 hostedNormalized elements and markdownSync, async, or batch
[ get started ]

Get a PaddleOCR API key

Create a key in Studio, then authenticate your first parse request.

  1. Sign in to API keys in OpenParser Studio and create a key.
  2. Send the key in the Authorization: Bearer YOUR_API_KEY header.
  3. Set ocr_model to paddleocr-vl-1.6 and upload a PDF, PNG, or JPEG to POST /parse.

Your key authenticates with the OpenParser hosted service. You do not need a separate PaddleOCR account or your own GPUs. New accounts get $10 in free credits.

[ api ]

Hosted PaddleOCR-VL behind REST

Parse with paddleocr-vl-1.6, extract against your schema, poll /jobs, and retrieve files under the same API contract.

endpointsapi.openparser.dev
  • Full API reference
POST/parserequest
curl https://api.openparser.dev/parse \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F 'request={"ocr_model":"paddleocr-vl-1.6","output_format":"openparser@1"};type=application/json' \
  -F "file=@statement.pdf"
response200 · example
{
  "output_format": "openparser@1",
  "document_id": "doc_3f9a2c",
  "provenance": {
    "provider": "paddle",
    "model": "paddleocr-vl-1.6"
  },
  "text": "Total due: $4,318.20",
  "markdown": "Total due: $4,318.20\n",
  "pages": [
    {
      "number": 1,
      "width": 1700,
      "height": 2200,
      "unit": "pixel",
      "element_ids": [
        "elem-total"
      ],
      "reading_order": [
        "elem-total"
      ]
    }
  ],
  "elements": [
    {
      "id": "elem-total",
      "kind": "text",
      "role": "paragraph",
      "text": "Total due: $4,318.20",
      "spans": [
        {
          "start": 0,
          "end": 20
        }
      ],
      "locations": [
        {
          "page_number": 1,
          "bbox": {
            "left": 14,
            "top": 53,
            "right": 146,
            "bottom": 123
          }
        }
      ],
      "confidence": {
        "score": 0.98,
        "scope": "recognition",
        "calibrated": false
      }
    }
  ],
  "relations": [],
  "text_annotations": [],
  "assets": []
}
[ console ]

Try PaddleOCR-VL in Studio

Upload a PDF in the playground, create API keys, and review page usage. OpenParser runs PaddleOCR-VL-1.6 inference.

openparser.dev/playgroundsigned in
playgroundno code
statement.pdf1 page · 48 KB
parsePaddleOCR-VLMistral OCRAzure DITextract9 models
extractClaudeGPT-4oLlamalocalany LLM
Run{ total: "$4,318.20" } b4
Open StudioCreate an API key
[ output ]

Layout elements, markdown, and schema extraction

PaddleOCR-VL handles layout. OpenParser adds its document output, job modes, and /extract with source citations.

Typed elements and markdown

Each page returns layout elements for text, headings, tables, and figures. Request text, markdown, and elements in one response.

b1
0.99
b4
0.98
b6
0.70

Per-element confidence

Parsed elements include OCR confidence scores. Route low-confidence pages to review before you commit extracted values.

Pinned model version

OpenParser runs PaddleOCR-VL-1.6. You pass ocr_model in the request body. Upgrades roll out on the hosted side.

schema {
total
}
{
total: "$4,318"
}

Schema extraction with citations

Point /extract at a parse job and a JSON schema. Grounding citations link each field to element_id values in the parsed document.

b4

Normalized output

Responses use one OpenParser output format. Element types, bounding boxes, and markdown fields stay consistent across calls.

b2b4b6
x, y, w, h

Sync, async, and batch

Parse one file synchronously, queue a large PDF for async processing, or submit a batch of documents in one request.

[ pricing ]

PaddleOCR API pricing

Hosted PaddleOCR-VL-1.6 costs $1 per 1,000 parsed pages. Your $10 signup credits cover about 10,000 pages if used only for parsing. Schema extraction adds language-model token costs.

free credits
$10
at signup
pay per page
$1/ 1,000 pages
open-weight hosted, starting at
+
extraction
Per token
billed on llm_model tokens
  • No minimums
  • No per-seat fees
  • Sync, async, and batch
  • Source citations
  • Console and API keys
Create an API key
[ questions ]

PaddleOCR API FAQ

Hosting, output shape, extraction, and pricing for PaddleOCR-VL-1.6 on OpenParser.

What is PaddleOCR-VL-1.6?

PaddleOCR-VL-1.6 is an open-weights vision-language model for document layout parsing. OpenParser hosts it behind a REST API so you parse PDFs and images without running your own inference stack.

What does the /parse endpoint return?

A ParsedDocument with text, markdown, pages, and layout elements. Text elements carry recognized text; tables can carry structured cells. Locations and scoped OCR confidence depend on the model output.

How does schema extraction work?

Call /extract with a parse job id and a JSON schema. The response fills your fields and returns grounding metadata with citations that point to element_id values in the parsed document.

Can I process documents asynchronously?

Yes. Use /parse/async for a single file or /parse/batch for many files. Poll the job endpoint until status is succeeded, then fetch the result.

How much does parsing cost?

New accounts get $10 in credits at signup (about 10,000 pages at $1/1,000). After that, parsing costs $1 per 1,000 pages. Extraction adds the token cost of whichever language model you select.

Do I need my own GPUs?

No. You send files to the API with your API key. OpenParser operates the PaddleOCR-VL-1.6 inference infrastructure.

Parse with paddleocr-vl-1.6

Upload a PDF and call /parse with PaddleOCR-VL-1.6

Inspect typed elements, markdown, and schema-filled JSON with source citations in the playground. OpenParser hosts inference; you send files over HTTPS.

Open StudioCreate an API key