TrOCR online
Transformer text recognition model. Reads single text lines, including handwriting.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- microsoft/trocr
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 1.2 s / page
- Inputs
- images
- Languages
- English
- Max pages per request
- 100
- Output
- Markdown, JSON
- License
- MIT
- Supports
- Handwriting
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/trocr",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'TrOCR speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
TrOCR pricing
TrOCR costs 1 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $1.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 50 pages with this model. See pricing for credit packs.
Similar models
1RolmOCRReducto's open PDF-to-text model, built on Qwen2.5-VL-7B with the olmOCR recipe. Needs no PDF metadata and handles rotated pages.
reducto/rolmocr2 credits / page2olmOCROpen-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.allenai/olmocr2 credits / page3KrakenOCR engine for historical documents and manuscripts, with trainable models for unusual scripts.kraken/kraken1 credit / pageAll TrOCR alternativesBest OCR models by use case
Compare TrOCR
TrOCR vs RolmOCRTrOCR vs olmOCRTrOCR vs KrakenTrOCR vs Azure Document IntelligenceTrOCR vs Phi-4-multimodalTrOCR vs Google Cloud Vision OCR