Marker vs Phi-4-multimodal
Pick Marker to turn PDFs of books and papers into Markdown, HTML, JSON or RAG chunks on your own hardware, as long as your company is under the $5M weight-license limit. Pick Phi-4-multimodal for English document Q&A under an MIT licence, or when you also need audio in the same model. The main split is the job: Marker converts whole PDFs, Phi-4-multimodal answers questions about page images.
Markerdatalab/marker | Phi-4-multimodalmicrosoft/phi-4-multimodal | |
|---|---|---|
| Type | OCR API | Vision model |
| Price | 14 credits / page | 2 credits / page |
| Per 1,000 pages | $14.00 | $2.00 |
| Typical speed | 2.5 s / page | 2.5 s / page |
| Best for | Books and research papers | Small model for OCR and questions |
| Inputs | PDF, images, DOCX | images |
| Languages | 90+ languages | English for vision |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose Marker if
- You want PDF to Markdown with equations, and Datalab reports 83.7 on olmOCR-bench in vllm mode.
- You need RAG chunks, JSON block trees, HTML or LaTeX output, not only text.
- You have no GPU: fast mode runs on CPU at 23.6 pages per second, though it drops to 66.6 on olmOCR-bench.
Choose Phi-4-multimodal if
- You need permissive MIT licensing for commercial use with no revenue cap.
- You want to ask questions about English documents, where Microsoft reports DocVQA 93.2 and OCRBench 84.4 at 5.6B parameters.
- You run mixed audio and image pipelines, since one model takes both, with a 128K token context.
Key differences
| Marker | Phi-4-multimodal | |
|---|---|---|
| Licence | Code Apache-2.0; weights under a modified AI Pubs Open Rail-M licence, free for research, personal use and startups under $5M | MIT |
| Main job | PDF to Markdown converter built on the Surya OCR models | General multimodal model taking text, image and audio input |
| Output formats | Markdown, HTML, JSON, chunks, LaTeX, images | Plain text, Markdown, JSON |
| Hardware | GPU, CPU or Apple Silicon; vllm mode needs an NVIDIA GPU; fast mode uses about 18 MB of ONNX weights on CPU | Flash attention, tested on A100, A6000 and H100; V100 and older need eager attention |
| Hosted option and price | Free self-hosted within the weight licence; Datalab hosted API with about 5,000 free pages per month | Free self-hosted (you pay for compute); also available via Azure AI Foundry |
| Benchmarks | olmOCR-bench 83.7 and OmniParseBench 85.9 in vllm mode, all from Datalab | DocVQA 93.2, OCRBench 84.4, ChartQA 81.4, InfoVQA 72.7, all from Microsoft |
| Known weakness | Commercial use blocked for companies above $5M without a paid licence | Vision is English only, weaker in other languages, and long chats can give repetitive output |
Sources
What each one is
Marker
Hosted version of the open-source Marker and Surya models. Strong on books and papers.
Marker detailsPhi-4-multimodal
Microsoft's 5.6B text, vision and audio model (February 2025). Scores 84.4 on OCRBench per its model card.
Phi-4-multimodal detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "datalab/marker","fallbacks": ["microsoft/phi-4-multimodal"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Marker alternativesPhi-4-multimodal alternativesBest OCR models in 2026