Skip to content


LlamaParse is the world's first genAI-native document parsing platform - built with LLMs and for LLM use cases.

Your LLM application performance is only as good as your data. The main goal of LlamaParse is to parse and clean your data, ensuring that it's good quality before passing to any downstream LLM use case such as advanced RAG.

It comes equipped with the following features:

  • State-of-the-art table extraction
  • Provide natural language instructions to parse the output in the exact format you want it.
  • JSON mode
  • Image extraction
  • Support for 10+ file types (.pdf, .pptx, .docx, .html, .xml, and more)
  • Foreign language support

LlamaParse exists as a standalone API and also as part of the LlamaCloud platform. The API is self-serve and available to everyone. The LlamaCloud platform is in private preview (come talk to us if interested).


You get 1k free pages a day. If you sign up for the paid plan, you get 7k free pages a week, and then $0.003 for each page.