# Replicate — Extract text from documents and images with Datalab Marker and OCR

- Company: Replicate (replicate.com)
- Announced: 2025-10-21T00:00:00+00:00
- Category: availability-change
- Subject: Platform
- Models affected: Marker, OCR
- Pricing: $4 per 1000 pages for Marker without page_schema in fast and balanced modes, $6 per 1000 pages for structured extraction or accurate mode, OCR $2 per 1000 pages.
- Source: https://replicate.com/blog/datalab-marker-and-ocr-fast-parsing
- Record: https://forck.live/items/2474-extract-text-from-documents-and-images-with-datalab-marker-and-ocr

Datalab's Marker and OCR models for document parsing and text extraction are now available on Replicate. Marker converts PDF, DOCX, PPTX, and images to markdown or JSON, supports structured extraction via JSON Schema, and is benchmarked against other models on olmOCR-Bench. OCR detects text in 90 languages. Both models are priced per page.

## Evidence

Verbatim from https://replicate.com/blog/datalab-marker-and-ocr-fast-parsing:

> Datalab’s state-of-the-art document parsing and text extraction models are now on Replicate.

---

Record: https://forck.live/items/2474-extract-text-from-documents-and-images-with-datalab-marker-and-ocr
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md