Gemini Flash vs MinerU
Pick Gemini Flash for cheap, bulk PDF to Markdown or JSON extraction through a hosted API, especially with mixed-language documents. Pick MinerU when documents must stay on your own hardware, or when you need Office files, LaTeX or DOCX output. Avoid MinerU for bank statements with merged header rows, and avoid Gemini Flash if you need an air-gapped or on-prem setup.
Gemini Flashgoogle/gemini-flash | MinerUopendatalab/mineru | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 15 credits / page | 2 credits / page |
| Per 1,000 pages | $15.00 | $2.00 |
| Typical speed | 1.6 s / page | 2.0 s / page |
| Best for | Handwriting and mixed layouts | Academic PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | 80+ languages |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| 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 Gemini Flash if
- Gemini 3 Flash scores 92.62 on OmniDocBench v1.6, close to Gemini 3 Pro at 92.91.
- The context window of up to 1M tokens fits long documents in one request.
- It costs $0.50 per 1M input tokens and $3.00 per 1M output tokens, or $0.25 and $1.50 with Batch/Flex, with no GPU to run.
Choose MinerU if
- It is self-hosted and free, so documents stay on your machine and you pay only for compute.
- It reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and writes Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
- The basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
Key differences
| Gemini Flash | MinerU | |
|---|---|---|
| Deployment | Hosted API (Gemini API or Vertex AI) | Self-host as CLI, API or WebUI |
| Licence | Proprietary | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 |
| Price | Gemini 3 Flash Preview: $0.50 input and $3.00 output per 1M tokens; Batch/Flex $0.25 and $1.50 | Free software; you pay for compute |
| Output formats | Markdown, JSON, HTML, plain text, shaped by your prompt with no fixed schema | Markdown, HTML, LaTeX, DOCX, EPUB, JSON |
| Benchmark | 92.62 on OmniDocBench v1.6 (Gemini 3 Flash) | 75.2 on olmOCR-Bench (MinerU 2.5.4); 45.9 on ParseBench mean (MinerU2.5). Different benchmarks, so scores are not directly comparable |
| Hardware | None to run; Google hosts it | Basic tier: CPU and 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM |
| Known failure | Cost per page varies with page density and output length; some newer Flash models rise from $0.75/$3.75 to $1.50/$7.50 per 1M tokens on January 1, 2027 | VLM tiers drop merged header rows in tables such as bank statement account lines; the VLM pipeline can repeat content and produce 300 KB figure blocks |
Sources
- Gemini API pricing
- OmniDocBench leaderboard
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
What each one is
Gemini Flash
General vision model with strong handwriting and layout understanding at a low price.
Gemini Flash detailsMinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU 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": "google/gemini-flash","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Gemini Flash alternativesMinerU alternativesBest OCR models in 2026