Skip to content
SPECIFICTION
Get listed

PDF.chat vs PDF-ChatGPT

PDF.chat

pdf.chat

PDF-ChatGPT

github.com

Side by side

FigurePDF.chatPDF-ChatGPT
Price from$4/mo—
Free planYes—
Free trialYes—
Open source——
WebYesYes
Windows—Yes
macOS—Yes
Linux—Yes
APIYesYes
Self-hosted—Yes
Plans published100
Spec score · AI PDF Assistants8.6 (#5)7.4 (#22)

Plans

PDF.chat

  • FreeFree
  • Small pack$5, paid once
  • Starter$5 a month
  • Medium pack$15, paid once
  • Pro$19 a month
  • Large pack$40, paid once
  • Starter$48 a year
  • Business$49 a month
  • Pro$182 a year
  • Business$470 a year

PDF.chat pricing →

PDF-ChatGPT

No plans published.

PDF-ChatGPT pricing →

In their own words

PDF.chat

PDF.chat lets users upload documents, ask questions, and receive answers cited to exact pages in over 100 languages. It accepts PDFs, Word and PowerPoint files, text files, and images, including scanned or photographed documents that its OCR models read on its own infrastructure. Long documents are indexed so questions can retrieve relevant pages from reports, textbooks, and dockets. Users can compare Claude, GPT, Gemini, Llama, and DeepSeek answers side by side in one chat, then export results as plain text, Markdown, DOCX, searchable PDF, CSV, or JSON. The service runs in a browser without a download or installation. Its REST API ingests documents, returns per-page text and metadata, and supports chat with page citations; API use is metered per page. The Free plan costs nothing, with pages resetting at midnight UTC and no credit card required. Starter costs $5 a month and includes 750 pages per month. PDF.chat says files are automatically deleted shortly after processing and are not sold, shared, or used for training; on paid tiers, relevant passages may be sent to third-party AI providers.

Visit pdf.chat

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.

Visit github.com