ChatPDF vs PDF-ChatGPT
ChatPDF
chatpdf.comPDF-ChatGPT
github.comSide by side
| Figure | ChatPDF | PDF-ChatGPT |
|---|---|---|
| Price from | $7.50/mo | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | Yes |
| iOS | Yes | — |
| Android | Yes | — |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 5 | 0 |
| Spec score · AI PDF Assistants | 9.3 (#3) | 7.4 (#22) |
| Citations | Built-in citations link answers to PDF references. | Answers include citations to the source document and page. |
| Purpose | ChatPDF lets users summarize PDFs and ask questions about them using conversational AI. | PDF-ChatGPT lets users ask natural-language questions about PDFs and receive answers grounded in document content with page citations. |
Plans
ChatPDF
- FreeFree
- FreeFree
- ChatPDF Plus monthly$14.99 a month
- ChatPDF Plus yearly$89.99 a year
- ChatPDF PlusPriced on request
In their own words
ChatPDF
ChatPDF lets users summarize documents and ask questions about their contents using conversational AI. Answers include citations that point to references in a PDF, and users can organize files in folders or discuss multiple PDFs in one conversation. It accepts PDFs in any language and supports conversations in any language; listed file types also include Word, PowerPoint, Markdown and text. Sharing links can be created, with access permissions managed or revoked. ChatPDF says documents are encrypted during transfer and storage and can be deleted by the user. Queries are routed dynamically between GPT-4o and GPT-4o-mini. The service works in a browser on any device and is listed for Android, iOS, Linux, macOS and Windows. Its backend API accepts uploaded PDFs or public URLs and lets users query them to build custom PDF chatbots. The API documentation limits each PDF to 2,000 pages or 32 MB and describes the chat API as stateless. The Free plan costs nothing and allows two documents per day.
PDF-ChatGPT
PDF-ChatGPT is a free, open-source, self-hosted application for asking natural-language questions about PDF files and receiving answers with document and page citations. It can index multiple PDFs and show document status, page counts, and chunk counts. Semantic search uses a persistent FAISS index, with a relevance threshold and optional per-document scoping. Answers come from OpenAI’s Responses API and can stream token by token; SQLite keeps conversation history for follow-up questions. The browser interface renders Markdown, offers dark and light themes, and adapts to mobile and tablet layouts. Uploaded PDFs, the index, and conversation history are stored locally, but text is sent to OpenAI for embeddings and chat generation. An OpenAI API key with billing enabled is required, and token use is metered. Uploads must be PDFs under 25 MB; scanned PDFs without extractable text need OCR, which is not included. The default setup is single-tenant and has no login, so the maker advises against public exposure without authentication or network restrictions. It runs locally or on documented hosting platforms, with persistent storage needed across redeploys.