Extract text from PDFs and images using open-weight AI vision models
Processing Mode
⚠️
Cloud Mode Privacy Notice:
Your documents will be sent to OpenRouter API (QWEN 2.5 VL) for processing.
Data is not stored, but consider using Local Mode for sensitive content.
OCR Service Upload a PDF or image (JPG, PNG, WEBP) to extract text using advanced OCR engines. Important: All AI-generated text should be reviewed manually for accuracy and appropriateness before use.
📄
Drag & drop a document here, or click to browse
Supports PDF, JPG, PNG, WEBP (max 25MB)
Model Settings
Privacy-focused, no external data sharing, no API costs. Handles all document types - printed text, handwritten notes, mixed documents, tables, forms. GPU-accelerated for fast processing. Best for sensitive documents and high-volume processing.
Your API key is stored locally and never sent to our servers. Get your key at openrouter.ai/keys. Cost: ~$0.001 per page.
Advanced Settings
Provide specific guidance for text extraction
Enables spatial coordinates for detected text regions
Choose whether to process all pages or just the first page
