OCRRouter

GPT vs Docling

Pick GPT when you need handwriting, custom JSON extraction with reasoning, or document question answering through a hosted API. Pick Docling when you ingest born-digital PDFs and Office files for RAG and want a free, MIT-licensed library you run yourself. The main split is a paid hosted model versus a self-hosted converter whose scanned-page accuracy depends on the OCR engine you plug in.

GPTopenai/gptDoclingibm/docling
TypeVision modelOpen source
Price11 credits / page2 credits / page
Per 1,000 pages$11.00$2.00
Typical speed2.4 s / page2.2 s / page
Best forMessy scans, custom instructionsStructured export for RAG
InputsPDF, imagesPDF, images, DOCX
Languages50+ languagesLatin scripts, CJK
Max pages per request100500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose GPT if

  • It handles handwritten notes: one HN user reported about 5% errors on messy cursive versus about 30% for Mistral OCR.
  • It can extract data into custom JSON and answer questions about a document, because you prompt it to do so.
  • It needs no infrastructure: send PDFs or images up to 50 MB per request to the OpenAI API.

Choose Docling if

  • It is free under the MIT license and runs locally on macOS, Linux and Windows, on CPU or GPU, so you pay only for compute.
  • It parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL through one API.
  • Its lossless JSON export keeps layout, reading order and table structure, and it has LangChain and LlamaIndex integrations.

Key differences

GPTDocling
How you run itHosted OpenAI APIPython library, runs locally
LicenseProprietaryMIT (individual models have their own licenses)
PriceToken-based per model; page images add input tokens, so cost per page is not fixedFree, self-hosted; you pay for compute
Input formatsImages and PDFs (up to 50 MB per request)PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRL
Output formatsMarkdown, JSON, plain textMarkdown, HTML, JSON, DocTags, plain text
BenchmarkGPT-5.2 scored 85.50 on OmniDocBench v1.5 and 86.59 on v1.6 (independent)Not published
Known failureNo bounding boxes or confidence scores in the standard responseOCR regression in 2.143.1 drops words and numbers with full-page Tesseract OCR; reading-order rule merges neighbouring columns on some layouts

Sources

What each one is

GPT

General vision model. Good at messy scans and following extraction instructions.

GPT details

Docling

IBM's open-source document converter with a structured document model.

Docling details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "openai/gpt","fallbacks": ["ibm/docling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GPT alternativesDocling alternativesBest OCR models in 2026