OCRRouter

GPT vs InternVL3.5

Pick GPT when you want a hosted API that extracts messy or handwritten documents into custom JSON and can reason over the content. Pick InternVL3.5 when you need to self-host under Apache-2.0 and choose a model size that fits your GPUs. GPT removes the infrastructure work, and InternVL3.5 gives you control over licence, hardware and cost.

GPTopenai/gptInternVL3.5opengvlab/internvl
TypeVision modelVision model
Price11 credits / page2 credits / page
Per 1,000 pages$11.00$2.00
Typical speed2.4 s / page3.0 s / page
Best forMessy scans, custom instructionsSelf-hosted document understanding
InputsPDF, imagesimages
Languages50+ languagesMultilingual
Max pages per request100500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNoNo
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 GPT if

  • An HN user reported about 5% errors on messy cursive, versus about 30% for Mistral OCR, so it suits handwritten notes.
  • You can prompt it to extract into custom JSON with reasoning, or to answer questions about a document.
  • PDFs go in directly through the API, which sends both extracted text and page images, with files up to 50 MB per request.

Choose InternVL3.5 if

  • The Apache-2.0 licence and open weights let you run it on your own hardware, and you pay only for compute.
  • Nine sizes from 1B to 241B let you trade accuracy for cost, and models up to 30B fit on a single A100.
  • MoE variants 20B-A4B and 30B-A3B activate few parameters per token, which suits self-hosted document question answering.

Key differences

GPTInternVL3.5
How you run itHosted OpenAI APISelf-host with Transformers, LMDeploy or vLLM
LicenceProprietaryApache-2.0, open weights
PricingToken-based per model. PDF page images add input tokens, so cost per page is not fixed.Free software. You pay for compute.
HardwareNone to manageUp to 30B on one A100, 38B on two A100s, 241B-A28B on eight A100s
BenchmarkGPT-5.2 scored 85.50 on OmniDocBench v1.5 and 86.59 on v1.6, versus 90.33 for Gemini 3 Pro in the same paperNo text scores. The model card publishes OCR results only as chart images.
HandwritingAn HN user reported about 5% errors on messy cursiveNot published
CoordinatesNo bounding boxes or confidence scores in the standard responseNo bounding boxes or layout output by default

Sources

What each one is

GPT

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

GPT 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": "openai/gpt","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GPT alternativesInternVL3.5 alternativesBest OCR models in 2026