OCRRouter

TrOCR vs InternVL3.5

Pick InternVL3.5 for full pages and PDFs, because TrOCR only reads single text-line images and has no page or layout output. Pick TrOCR only when you already have cropped lines, such as English handwriting or receipt lines, or want to fine-tune a recognizer on your own line images.

TrOCRmicrosoft/trocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forHandwritten text linesSelf-hosted document understanding
Inputsimagesimages
LanguagesEnglishMultilingual
Max pages per request100500
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxesNoNo
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ Yes
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 TrOCR if

  • The large model reports 2.89 character error rate on the IAM handwriting set, per the paper.
  • It has separate checkpoints fine-tuned for handwritten (IAM), printed (SROIE) and scene text.
  • It loads in a few lines with Hugging Face transformers and is MIT licensed, which suits fine-tuning on custom line images.

Choose InternVL3.5 if

  • It reads whole pages and answers questions about documents, and it can return plain text, Markdown or JSON.
  • It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost, and models up to 30B fit on a single A100.
  • It uses the Apache-2.0 license and can run through Transformers, LMDeploy or vLLM.

Key differences

TrOCRInternVL3.5
Input it handlesSingle text-line images only; you need a separate line detectorGeneral vision language model that takes document images and questions
Output formatsPlain textPlain text, Markdown, JSON
Layout and tablesNo layout, table or page-level outputNo bounding boxes or layout output by default
LanguagesReleased checkpoints are English-focused; other languages need fine-tuningNot published
Model sizeBase 334M, large 558M parameters1B to 241B-A28B; the 8B variant is 8.5B
LicenceMIT (microsoft/unilm repository)Apache-2.0
Published OCR benchmarkIAM handwriting CER 2.89 (TrOCR-large), reported by the authorsNot published as text; the model card shows OCR scores only as chart images

Sources

What each one is

TrOCR

Transformer text recognition model. Reads single text lines, including handwriting.

TrOCR details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": "microsoft/trocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

TrOCR alternativesInternVL3.5 alternativesBest OCR models in 2026