DeepSeek OCR
Turns document images into markdown with layout preserved
$1 in free creditsInput $0.10/1M · Output $0.30/1M
Overview
DeepSeek-OCR is a roughly 3B vision-language model from DeepSeek's "Contexts Optical Compression" work, aimed at reading document images. A grounding prompt makes it emit markdown that keeps the page's structure. The checkpoint defines several resolution modes (Tiny through Large, plus a tiled Gundam mode); this deployment runs one fixed mode, and the mode is not selectable per request.
Strengths
- Markdown output with layout grounding
- MIT licensed
Use cases
- PDF and scan to markdown conversion
- Reading dense multi-column pages
Good to know
A conversion utility rather than an assistant -- it is deliberately kept out of the agent and chat model pickers.
API access
One OpenAI-compatible API for every model in the catalog, plus the CLI and the function SDK inside workflows. Sign up and try $1 of inference free, then get $10 more once you've spent $5, and these requests work:
# OCR models are called through the # platform APIs and workflows; list what is deployed: curl https://model.graphn.ai/v1/models \ -H "Authorization: Bearer $GRAPHN_API_KEY"
graphn model get deepseek-ocr
@function
async def read_document(image_url: str) -> str:
return await vision.extract_text(image_url)