Mistral OCR API vs Nanonets API + MCP

Mistral OCR API

Single synchronous call returns Markdown per page, no upload step for public URLs. OCR API at 99.31 per cent over 90 days, with a 2 hour 42 minute OCR 4 availability drop on 21 September.

Nanonets API + MCP

Extraction API returns Markdown, CSV or JSON, with named fields or a JSON schema. No public changelog and no dated release in the last 90 days.

Mistral OCR API

1. Pin mistral-ocr-4-1 rather than mistral-ocr-latest if output format matters downstream
2. Set table_format to html for tables with merged cells
3. Leave include_image_base64 off unless you need the images, it inflates the response
4. Pass pages to OCR only the pages you need, since billing is per page
5. Upload private files through /v1/files and pass the signed URL

Nanonets API + MCP

1. Use the extraction API at extraction-api.nanonets.com, not app.nanonets.com, unless you already have a trained model
2. Pass a JSON schema in json_options when downstream code needs fixed field names
3. Use the async extract endpoints for long documents and poll /api/v1/extract/results/{record_id}
4. On a 429, wait 30 seconds and double the delay each retry
5. Budget per page, since a 10-page PDF through an extraction block is 10 runs