GOT-OCR 2.0 API
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
- Model ID
- stepfun/got-ocr-2
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 1.5 s / page
- Inputs
- images
- Languages
- Chinese, English
- Max pages per request
- 100
- Output
- Markdown, JSON with positions
- Supports
- TablesMathBounding boxes
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stepfun/got-ocr-2",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'GOT-OCR 2.0 is not connected yet. The price below is an estimate. You can call the models that are live today with the same request.
GOT-OCR 2.0 speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
GOT-OCR 2.0 pricing
GOT-OCR 2.0 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 200 free credits, enough for about 200 pages with this model. See pricing for credit packs.
Similar models
1Granite DoclingCompact IBM vision model that converts pages to DocTags for the Docling pipeline.
ibm/granite-docling1 credit / page2SmolDoclingTiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.huggingface/smoldocling1 credit / page3DoclingIBM's open-source document converter with a structured document model.ibm/docling2 credits / pageCompare GOT-OCR 2.0
GOT-OCR 2.0 vs Granite DoclingGOT-OCR 2.0 vs SmolDoclingGOT-OCR 2.0 vs DoclingGOT-OCR 2.0 vs Hunyuan OCRGOT-OCR 2.0 vs GLM-OCRGOT-OCR 2.0 vs docTR