Chandra API
Datalab's OCR model that keeps layout and handles forms, tables and handwriting.
- Model ID
- datalab/chandra
- Type
- Open source
- Price
- 2 credits / page ($2.00 per 1,000 pages)
- Typical speed
- 2.0 s / page
- Inputs
- PDF, images
- Languages
- 40+ languages
- Max pages per request
- 500
- Output
- Markdown, JSON with positions
- Supports
- TablesMathHandwritingFormsBounding boxesMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "datalab/chandra",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Chandra is not connected yet. The price below is an estimate. You can call the models that are live today with the same request.
Chandra speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Chandra pricing
Chandra 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 200 free credits, enough for about 100 pages with this model. See pricing for credit packs.
Similar models
1Qwen-VLAlibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.
qwen/qwen-vl2 credits / page2Unlimited OCROpen-source model from Baidu that reads hundreds of pages in one pass with flat memory use.baidu/unlimited-ocr2 credits / page3MinerUOpen-source PDF to Markdown pipeline popular for academic and Chinese documents.opendatalab/mineru2 credits / pageCompare Chandra
Chandra vs Qwen-VLChandra vs Unlimited OCRChandra vs MinerUChandra vs MarkerChandra vs PaddleOCR-VLChandra vs Granite Docling