OCRRouter

Mistral OCR vs InternVL3.5

Pick Mistral OCR for high-volume PDF to Markdown and scanned business documents when you want a hosted API at $2 per 1,000 pages. Pick InternVL3.5 when you need to self-host under Apache-2.0, or want one model family at sizes from 1B to 241B for document question answering. The main split is a priced hosted OCR API versus an open-weight general vision language model you run on your own GPUs.

Mistral OCRmistral/mistral-ocrInternVL3.5opengvlab/internvl
TypeOCR APIVision model
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed0.9 s / page3.0 s / page
Best forHigh-volume PDF to MarkdownSelf-hosted document understanding
InputsPDF, imagesimages
Languages100+ languagesMultilingual
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ 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 Mistral OCR if

  • It costs $2 per 1,000 pages, or $1 per 1,000 pages through the Batch API, with no GPUs to run.
  • OCR 3 rebuilds tables as HTML with rowspan and colspan, and returns Markdown, HTML, JSON and extracted images.
  • It has independent OmniDocBench scores (85.66 on v1.6), while InternVL3.5 has none published as text.

Choose InternVL3.5 if

  • It is Apache-2.0 and self-hosted, so you pay only for compute and keep documents on your own machines.
  • Nine sizes from 1B to 241B-A28B let you trade accuracy for cost, and models up to 30B fit on a single A100.
  • As a general vision language model it can answer questions about a document, not only transcribe it.

Key differences

Mistral OCRInternVL3.5
DeploymentHosted API from Mistral AISelf-host with Transformers, LMDeploy or vLLM
LicenceProprietaryApache-2.0
Price$2 per 1,000 pages; $3 with structured annotations; $1 via Batch APIFree to download; you pay for compute
Output formatsMarkdown, HTML, JSON, imagesPlain text, Markdown, JSON
Layout and coordinatesTables returned as HTML with rowspan and colspanNo bounding boxes or layout output by default
OmniDocBench78.83 for the first version (v1.5); 85.66 overall on v1.6Not published as text; the model card shows OCR scores only as chart images
Known failureHallucinated text on unreadable handwriting; changed checkbox states and misread characters on a dense financial tableThe 38B model needs two A100s and the 241B-A28B model needs eight, so large sizes are hard to run without a GPU cluster

Sources

What each one is

Mistral OCR

Fast document OCR that returns clean Markdown with tables and embedded images.

Mistral OCR 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": "mistral/mistral-ocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mistral OCR alternativesInternVL3.5 alternativesBest OCR models in 2026