OCRRouter

Qianfan OCR vs olmOCR

Pick Qianfan OCR for self-hosted multilingual parsing that needs more than Markdown, such as JSON, HTML, LaTeX or bounding boxes, and for key information extraction. Pick olmOCR for large-scale PDF to Markdown for LLM training or RAG, where its stated cost is under $200 per million pages and it scores 82.4 on olmOCR-Bench. Qianfan OCR is the smaller model at 4B against 7B, but olmOCR has the clearer hardware floor of a 12 GB GPU.

Qianfan OCRbaidu/qianfan-ocrolmOCRallenai/olmocr
TypeOCR APIOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.5 s / page
Best forChinese documentsBulk PDF to text for datasets
InputsPDF, imagesPDF, images
LanguagesChinese, English and moreMainly English
Max pages per request2001,000
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
Math✓ Yes✓ Yes
Bounding boxesNoNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 Qianfan OCR if

  • It covers 192 languages, handwriting and scene text, which suits multilingual document parsing.
  • It outputs Markdown, JSON, HTML, LaTeX and bounding boxes, while olmOCR lists only Markdown and JSON.
  • It scores 93.12 on OmniDocBench v1.5 and is also offered hosted on the Baidu Qianfan platform.

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), and above the 79.8 that Qianfan OCR reports on the same benchmark.
  • Ai2 puts self-hosted cost under $200 per million pages, and hosted olmOCR-2-7B on DeepInfra costs $0.09 input and $0.19 output per million tokens.
  • It handles equations, tables and handwriting, and strips headers and footers in natural reading order, which fits academic papers and mixed printed and handwritten pages.

Key differences

Qianfan OCRolmOCR
Model size4B (Qwen3-4B language model)7B
LicenceApache-2.0Apache-2.0 (toolkit)
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesMarkdown, JSON
HardwareBenchmarked on one NVIDIA A100 with vLLM; no minimum VRAM statedNVIDIA GPU with at least 12 GB VRAM and 30 GB free disk
PricingFree self-hosted (you pay for compute); hosted via Baidu Qianfan platformSelf-hosted under $200 per million pages; DeepInfra $0.09 input / $0.19 output per million tokens
olmOCR-Bench score79.8 (reported by the authors)82.4 (v0.4.0, reported by the authors)
Known failureThinking mode can emit up to 16,384 tokens, adding latency; 1.024 pages per second on an A100 even with W8A8Out of memory on a 12 GB GPU (issue #424), gets stuck on the last few pages (issue #433), unreliable image bounding box coordinates (issue #437)

Sources

What each one is

Qianfan OCR

Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.

Qianfan OCR details

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

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": "baidu/qianfan-ocr","fallbacks": ["allenai/olmocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesolmOCR alternativesBest OCR models in 2026