Skip to content
  11.  
    12. © 2023 – 2025 OpenRouter, Inc
    Announcements

    Universal PDF Support

    4/23/2025

    Universal compatibility: Works with any LLM available on OpenRouter. All PDF types: Handles any PDF, including image-only scans. Native support: Automatically uses native PDF support for providers that support it, including Gemini, Anthropic, and OpenAI. Multimodal magic: For multimodal models, we automatically send embedded images from PDFs directly to the model. Combine with other integrations: Pair it with our web search feature to blend PDF data with real-time info, or with the Auto Router Flexible integration: Accessible via API and directly from the OpenRouter Chatroom - process multiple PDFs simultaneously with multiple models in a single request.

    ⚙️ Pricing: Two PDF processing engines to choose from:

    mistral-ocr (default): OCR support with text and embedded images extraction — $2 per 1000 pages. pdf-text: Text-only extraction without OCR or image support — free.

    📖 Documentation & Getting Started: Check out the full docs and implementation guide: → openrouter.ai/docs/features/images-and-pdfs

    Video demo here, and more info on the announcement: https://x.com/OpenRouterAI/status/1915083006349382033.