RolmOCR online
Reducto's open PDF-to-text model, built on Qwen2.5-VL-7B with the olmOCR recipe. Needs no PDF metadata and handles rotated pages.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- reducto/rolmocr
- Type
- Open source
- Price
- 2 credits / page ($2.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- PDF, images
- Languages
- Not stated by the authors
- Max pages per request
- 500
- Output
- Markdown, JSON
- License
- Apache-2.0
- Supports
- TablesHandwriting
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "reducto/rolmocr",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'RolmOCR speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
RolmOCR pricing
RolmOCR costs 2 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $2.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 25 pages with this model. See pricing for credit packs.
Similar models
1olmOCROpen-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 / page2Qwen-VLAlibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.qwen/qwen-vl2 credits / page3Qwen3-VLAlibaba's Qwen3 vision-language family (2025), with expanded OCR language support.qwen/qwen3-vl2 credits / pageAll RolmOCR alternativesBest OCR models by use case
Compare RolmOCR
RolmOCR vs olmOCRRolmOCR vs Qwen-VLRolmOCR vs Qwen3-VLRolmOCR vs Mathpix ConvertRolmOCR vs LLaVA-OneVisionRolmOCR vs Claude Sonnet 4.5