Mistral OCR API
Fast document OCR that returns clean Markdown with tables and embedded images.
- Model ID
- mistral/mistral-ocr
- Type
- OCR API
- Price
- 6 credits / page ($6.00 per 1,000 pages)
- Typical speed
- 0.9 s / page
- Inputs
- PDF, images
- Languages
- 100+ languages
- Max pages per request
- 1,000
- Output
- Markdown, JSON with positions
- Supports
- TablesMathBounding boxesMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral/mistral-ocr",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Try Mistral OCR
Result
Your Markdown or JSON shows up here.
Mistral OCR speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Mistral OCR pricing
Mistral OCR costs 6 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $6.00. You only pay for pages that return a result.
New accounts get 200 free credits, enough for about 33 pages with this model. See pricing for credit packs.
Similar models
1LlamaParseDocument parser built for RAG pipelines, with several quality tiers.
llamaindex/llamaparse5 credits / page2MarkerHosted version of the open-source Marker and Surya models. Strong on books and papers.datalab/marker14 credits / page3ChunkrDocument parsing API that segments and chunks pages for RAG. Self-hostable version available.chunkr/chunkr14 credits / pageCompare Mistral OCR
Mistral OCR vs LlamaParseMistral OCR vs MarkerMistral OCR vs ChunkrMistral OCR vs PaddleOCR (PP-OCR)Mistral OCR vs Nanonets-OCRMistral OCR vs Unstructured