OCRRouter

Reducto Parse vs InternVL3.5

Pick Reducto Parse when you need dense tables, layout and bounding boxes out of PDFs through a hosted API, or when you need SOC 2 and HIPAA coverage. Pick InternVL3.5 when you want Apache-2.0 weights you run on your own GPUs, in a size that fits your budget. The main split is a paid, structured parsing service against a free, general vision model that you host.

Reducto Parsereducto/parseInternVL3.5opengvlab/internvl
TypeOCR APIVision model
Price20 credits / page2 credits / page
Per 1,000 pages$20.00$2.00
Typical speed4.0 s / page3.0 s / page
Best forHigh-stakes complex documentsSelf-hosted document understanding
InputsPDF, images, DOCXimages
Languages50+ languagesMultilingual
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
Forms✓ YesNo
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 Reducto Parse if

  • It returns Markdown, JSON, HTML and bounding boxes, so you get layout, tables and figures as LLM-ready chunks.
  • It reports 90.2% on RD-TableBench, versus 82.7% for Azure and 80.9% for Textract, though Reducto built and ran that benchmark itself.
  • It has SOC 2 Type II, HIPAA with BAAs and zero data retention, and it can run hosted, in a VPC, on-prem or air-gapped.

Choose InternVL3.5 if

  • The Apache-2.0 licence costs nothing. You pay only for compute.
  • It comes in nine sizes from 1B to 241B-A28B, so you can trade accuracy for cost. Models up to 30B run on a single A100.
  • It suits document question answering and self-hosted multimodal pipelines where one model family covers several jobs.

Key differences

Reducto ParseInternVL3.5
LicenceProprietaryApache-2.0
How you run itHosted, or deployed in a VPC or on-premSelf-host only, with Transformers, LMDeploy or vLLM
Price15,000 free credits, then $0.015 per credit. Standard parse is 1 credit per page. Batch queue is 20% off.Free. You pay for compute.
Output formatsMarkdown, JSON, HTML, bounding boxesPlain text, Markdown, JSON. No bounding boxes or layout output by default.
Table benchmark90.2% on RD-TableBench, self-built and self-runNot published. The model card shows OCR scores only as chart images.
HardwareNone to manage on the hosted API38B needs two A100s. 241B-A28B needs eight A100s.
ComplianceSOC 2 Type II, HIPAA with BAAs, zero data retentionNot published

Sources

What each one is

Reducto Parse

High-accuracy parsing for complex financial and legal documents, with citations.

Reducto Parse 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": "reducto/parse","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Reducto Parse alternativesInternVL3.5 alternativesBest OCR models in 2026