gptpdf vs docling
PDF-to-Markdown tools compared
gptpdf and docling both convert documents into structured content for downstream workflows. gptpdf focuses on PDF-to-Markdown conversion using a vision-capable model API, while docling covers more document formats and offers local processing and multiple export options.
gptpdf: Convert PDFs into Markdown with Vision Models
gptpdf turns PDF pages into Markdown using a vision-capable model, aiming to preserve layouts such as tables, formulas, and figures. It suits developers who need an API-based PDF parsing component and can provide access to a compatible model.
docling: Convert Documents into Structured Content
Docling parses documents such as PDFs, Word files, spreadsheets, and images into structured content for applications and generative AI workflows. It offers local processing, a Python library, and a command-line interface.
| gptpdf | docling | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 3.6k | 68.7k |
| Forks | 261 | 5k |
| Last analyzed | Oct 3, 2026 | Oct 12, 2026 |
Key differences
- gptpdf focuses on PDFs, while docling also parses office documents, web formats, images, audio, and video.
- gptpdf uses PyMuPDF to identify non-text areas and relies on a compatible multimodal model API for interpretation; docling offers layout analysis, OCR, and visual-language-model pipelines.
- gptpdf returns Markdown and paths to extracted images; docling supports exports including Markdown, HTML, WebVTT, DocTags, and lossless JSON.
- gptpdf requires model API access and may incur per-page costs; docling can run locally and can also be exposed through an API server or MCP server.
- Both projects are Python libraries under the MIT license; docling also provides a command-line interface and integrations with several workflow frameworks.
- The provided repository figures list 3.6k stars and 261 forks for gptpdf, compared with 68.7k stars and 5k forks for docling.
Choose gptpdf if you…
- need a focused PDF-to-Markdown component that uses a vision-capable model API.
- want to configure prompts, model settings, and worker threads for PDF page parsing.
- can provide compatible model API access and accept possible per-page costs.
Choose docling if you…
- need to process PDFs alongside office documents, images, or other supported formats.
- want local processing, OCR, multiple export formats, or a command-line interface.
- are building a workflow that can use its listed framework integrations or MCP server.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.