OCRRouter

Qianfan OCR vs Pixtral

Pick Qianfan OCR for new document parsing work, especially multilingual pages, handwriting, tables and formulas that you host yourself. Pixtral 12B only makes sense if you already run it through the Mistral API and mainly ask questions about charts and documents. Mistral marks it as deprecated and no longer maintained, and it is reported to miss on dense, small-font and non-Latin text.

Qianfan OCRbaidu/qianfan-ocrPixtralmistral/pixtral
TypeOCR APIVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page3.0 s / page
Best forChinese documentsQuestions about document images
InputsPDF, imagesimages
LanguagesChinese, English and moreMultilingual
Max pages per request200500
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
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 Qianfan OCR if

  • It is built for document parsing and scores 93.12 on OmniDocBench v1.5, the top end-to-end score in Baidu's table.
  • It covers 192 languages, handwriting and scene text, and returns Markdown, JSON, HTML, LaTeX and bounding boxes.
  • It is a 4B model under Apache-2.0, benchmarked on a single A100 with vLLM, so self-hosting is cheaper than running a 12B model.

Choose Pixtral if

  • You already have an integration on the Mistral API and want to keep it, at a launch price of $0.15 per million input and output tokens.
  • You need question answering over charts and documents, where Mistral reports 90.7 ANLS on DocVQA and 81.8 on ChartQA.
  • You want many images in one request, since the 128K token context allows it.

Key differences

Qianfan OCRPixtral
Model type4B end-to-end document parsing model from Baidu (Qwen3-4B language model)12.4B general vision language model from Mistral AI (12B decoder + 400M vision encoder)
Maintenance statusCurrent, with weights on Hugging Face and hosted access on the Baidu Qianfan platformMarked deprecated and no longer maintained by Mistral
LicenceApache-2.0, commercial use allowedApache-2.0 open weights
PricingFree to self-host (you pay for compute); hosted access via Baidu Qianfan platform, price not publishedMistral API launch price $0.15 per million input and output tokens; free to self-host
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesPlain text, Markdown, JSON
Headline benchmarkOmniDocBench v1.5 93.12, olmOCR-Bench 79.8, OCRBench 880 (reported by the authors)DocVQA 90.7 ANLS, ChartQA 81.8, MMMU 52.5 (reported by Mistral)
Handwriting and non-Latin textCovers 192 languages, handwriting and scene textReported accuracy drop on handwriting, small fonts and non-Latin scripts; Q4 quantization reported to degrade small text OCR

Sources

What each one is

Qianfan OCR

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

Qianfan OCR details

Pixtral

Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.

Pixtral 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": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesPixtral alternativesBest OCR models in 2026