OCRRouter

GPT vs docTR

Pick GPT when you need handwriting, custom JSON extraction with reasoning, or document question answering through a hosted API. Pick docTR when you need word-level text with coordinates, run it on your own hardware, and want a free Apache-2.0 library. The main split is that GPT understands and extracts, while docTR only returns words, lines and boxes.

GPTopenai/gptdocTRmindee/doctr
TypeVision modelOpen source
Price11 credits / page1 credit / page
Per 1,000 pages$11.00$1.00
Typical speed2.4 s / page0.9 s / page
Best forMessy scans, custom instructionsWord-level OCR with positions
InputsPDF, imagesPDF, images
Languages50+ languagesMainly Latin scripts
Max pages per request100500
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNo✓ Yes
ConfidenceNo✓ Yes
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 messy handwriting: an HN user reported about 5% errors on cursive versus about 30% for Mistral OCR.
  • You can prompt it to return Markdown, JSON or plain text, which suits extraction into a custom JSON schema and document question answering.
  • It is a hosted API that takes files up to 50 MB per request, with no models to host or train.

Choose docTR if

  • It returns a nested page, block, line and word structure with coordinates as JSON, which GPT's standard response does not give you.
  • It is Apache-2.0 and free to self-host, so you pay only for compute and keep documents on your own machines.
  • You can pick the detection and recognition architectures, use straight or rotated boxes, and train your own models in Python.

Key differences

GPTdocTR
LicenceProprietaryApache-2.0
How you run itHosted OpenAI APIPython library on PyTorch, with Docker images; CPU or NVIDIA GPU (GPU images need CUDA 12.2 or newer on the host)
PriceToken-based per model; PDF page images add input tokens, so cost per page is not fixedFree, self-hosted; you pay for compute
Output formatsMarkdown, JSON, plain textJSON, plain text, bounding boxes. No Markdown, table or formula output
CoordinatesNo bounding boxes or confidence scores in the standard responseWord, line and block coordinates, with straight or rotated boxes
OmniDocBench overall85.50 on v1.5 and 86.59 on v1.6 (GPT-5.2, independent)Not published
Known failureScored below Gemini 3 Pro (90.33) on OmniDocBench v1.5 in the same paperCropped images give poorer results (issue #2007); split-crop merging can misjoin readings across repeated characters (issue #2229)

Sources

What each one is

GPT

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

GPT details

docTR

Open-source OCR library from Mindee with separate text detection and recognition models.

docTR 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": ["mindee/doctr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GPT alternativesdocTR alternativesBest OCR models in 2026