Unlimited OCR vs Google Cloud Vision OCR
Pick Unlimited OCR when you need Markdown or bounding boxes from long PDFs, such as reports and books for RAG, and can run an NVIDIA GPU under an MIT licence. Pick Google Cloud Vision OCR when you want a hosted API for photos, labels, handwritten notes or high-volume plain text, with no hardware to run. The main split is self-hosted layout-aware parsing versus a hosted plain-text API with no table or Markdown output.
Unlimited OCRbaidu/unlimited-ocr | Google Cloud Vision OCRgoogle/cloud-vision | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 1.0 s / page |
| Best for | Books and very long documents | Photos and simple scans |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | 100+ languages |
| Max pages per request | 1,000 | 2,000 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | ✓ Yes |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose Unlimited OCR if
- It parses 40+ pages in a single forward pass, so long reports and books go through in one request.
- It emits Markdown, plain text and bounding boxes with block types, which suits RAG and layout-aware extraction.
- It is MIT licensed and free to self-host, so you can use it commercially and you pay only for compute.
Choose Google Cloud Vision OCR if
- It is a hosted API called over REST or client libraries, so you run no GPU and manage no model.
- It supports handwriting through DOCUMENT_TEXT_DETECTION with language hints, and works on photos of signs and labels.
- The first 1,000 units per month are free per feature, then $1.50 per 1,000, dropping to $0.60 per 1,000 above 5M units.
Key differences
| Unlimited OCR | Google Cloud Vision OCR | |
|---|---|---|
| Licence | MIT, commercial use allowed, no copyleft | Proprietary |
| How you run it | Self-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR product | Hosted API only; no on-premise deployment |
| Price | Free to self-host, you pay for compute | First 1,000 units per month free, then $1.50 per 1,000 up to 5M, $0.60 per 1,000 above; one unit per PDF page |
| Output formats | Markdown, plain text, bounding boxes | JSON, plain text, bounding boxes; no Markdown, so you rebuild reading order yourself |
| Long documents | 40+ pages in one pass; context capped at 32,768 tokens; multi-page input only in base mode | PDF and TIFF need async processing via Cloud Storage; async batch accepts up to 2,000 image files per request |
| Tables and layout | Emits block types and bounding boxes; text styling mostly lost (ParseBench text formatting 0.97) | No table or layout structure; Google points to Document AI for forms and tables |
| Known failure | Text repetition and looping, hallucinated text, SGLang bbox loops on GB10 GPUs; version 2 runs out of memory on 12 GB GPUs | Billing must be enabled even to use the free 1,000 units |
Sources
- Hugging Face model card
- GitHub repo
- MarkTechPost on Unlimited OCR 2
- Issue #116 OOM on 12 GB
- Vision pricing
- OCR docs
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsGoogle Cloud Vision OCR
Google Cloud's image OCR with text and document text detection, word boxes and confidence.
Google Cloud Vision OCR detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "baidu/unlimited-ocr","fallbacks": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026