OCRRouter

olmOCR vs InternVL3.5

Pick olmOCR for bulk PDF to Markdown conversion, especially academic papers with equations and pages mixing print and handwriting. It publishes a score of 82.4 on olmOCR-Bench and a self-hosted cost under $200 per million pages. Pick InternVL3.5 if you need a general vision language model for document question answering, or one model family you can run at sizes from 1B to 241B-A28B.

olmOCRallenai/olmocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forBulk PDF to text for datasetsSelf-hosted document understanding
InputsPDF, imagesimages
LanguagesMainly EnglishMultilingual
Max pages per request1,000500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ 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 olmOCR if

  • It scores 82.4 on olmOCR-Bench, above Marker (76.1), MinerU 2.5.4 (75.2) and Mistral OCR (72.0) in the same table.
  • Ai2 puts self-hosted cost under $200 per million pages, and a hosted olmOCR-2-7B is available on DeepInfra at $0.09 input / $0.19 output per million tokens.
  • It handles equations, tables and handwriting, and strips headers and footers in natural reading order.

Choose InternVL3.5 if

  • Nine sizes from 1B to 241B let you trade accuracy for cost, and models up to 30B fit on a single A100.
  • It suits document question answering and self-hosted multimodal pipelines, not only PDF conversion.
  • The MoE variants 20B-A4B and 30B-A3B activate few parameters per token.

Key differences

olmOCRInternVL3.5
What it is7B toolkit and model from Ai2 for PDF and image to MarkdownGeneral vision language model family from OpenGVLab, 1B to 241B-A28B
LicenceApache-2.0 (toolkit)Apache-2.0
How you run itSelf-host with vLLM on a GPU, or use third-party hosted endpointsSelf-host only, with Transformers, LMDeploy or vLLM
PriceUnder $200 per million pages self-hosted; DeepInfra $0.09 input / $0.19 output per million tokensFree software; you pay for compute
HardwareNVIDIA GPU with at least 12 GB VRAM and 30 GB free diskUp to 30B on one A100; 38B needs two A100s; 241B-A28B needs eight A100s
Output formatsMarkdown, JSONPlain text, Markdown, JSON
OCR benchmark82.4 on olmOCR-Bench (v0.4.0), per the authorsNot published as text; the model card shows OCR scores only as chart images
Known failureOut of memory on a 12 GB GPU (issue #424), gets stuck on the last pages (issue #433), unreliable image bounding boxes (issue #437)No bounding boxes or layout output by default, so no word coordinates

Sources

What each one is

olmOCR

Open-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.

olmOCR 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": "allenai/olmocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

olmOCR alternativesInternVL3.5 alternativesBest OCR models in 2026