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.

From the source
Datalab’s state-of-the-art document parsing and text extraction models are now on Replicate.
replicate.com

Visit source ↗replicate.com

Announced: 21 Oct 2025 00:00 UTC
Detected: 03 Aug 2026 21:12 UTC (+286d after)
Pricing

Other stories

Amazon · 27 AugIntroducing OpenAI models on Amazon Bedrock for in-country inferencing in IndiaAvailability change

Amazon · 27 AugIntroducing India cross-Region inference for OpenAI GPT-5.6 models on Amazon BedrockAvailability change

OpenAI · 27 AugExpanding OpenAI’s presence in BrazilAvailability change

Anthropic · 27 AugExpanding our support for scientists

$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.

Availability change

Cohere · 27 AugIntroducing Parse: Enterprise document intelligence at scaleAvailability change

GitHub · 26 AugGlobal model policy generally availableAvailability change