OCRRouterGet API key

GLM-OCR vs TrOCR

TrOCR is cheaper per page; TrOCR is faster; only GLM-OCR supports tables, math, bounding boxes, confidence, multilingual; only TrOCR supports handwriting.

GLM-OCRzai/glm-ocrTrOCRmicrosoft/trocr
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.3 s / page1.2 s / page
Best forLow-cost general documentsHandwritten text lines
InputsPDF, imagesimages
Languages100+ languagesEnglish
Max pages per request500100
Tables✓ YesNo
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableComing soon

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

What each one is

GLM-OCR

Small open-source OCR model from Z.ai with layout regions. MIT licensed.

GLM-OCR details

TrOCR

Transformer text recognition model. Reads single text lines, including handwriting.

TrOCR details

Use one, fall back to the other

Request body
{
  "model": "zai/glm-ocr",
  "fallbacks": ["microsoft/trocr"],
  "file_url": "https://example.com/document.pdf"
}

Questions

More comparisons

GLM-OCR alternativesTrOCR alternatives