Gemini Flash vs Docling
Pick Gemini Flash for bulk PDF to Markdown or JSON extraction when a hosted API is fine and you want a published OmniDocBench score (92.62 for Gemini 3 Flash). Pick Docling for RAG ingestion of born-digital PDFs and Office files, or when documents must stay on your own machines. The main split is a paid, token-billed API versus an MIT-licensed library you run yourself.
Gemini Flashgoogle/gemini-flash | Doclingibm/docling | |
|---|---|---|
| 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 | 2.2 s / page |
| Best for | Handwriting and mixed layouts | Structured export for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | Latin scripts, CJK |
| 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 | 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 Gemini Flash if
- It scores 92.62 on OmniDocBench v1.6 (Gemini 3 Flash), close to Gemini 3 Pro at 92.91.
- A context window of up to 1M tokens fits long documents in one request.
- Gemini 3 Flash Preview costs $0.50 per 1M input tokens and $3.00 per 1M output tokens, or $0.25 and $1.50 on Batch/Flex, which suits cheap bulk PDF to Markdown and mixed-language documents.
Choose Docling if
- It is MIT-licensed and runs locally on macOS, Linux and Windows, so it works where a hosted API does not, such as air-gapped setups.
- One API parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL.
- Lossless JSON export keeps layout, reading order and table structure for downstream tools, and it plugs into LangChain and LlamaIndex.
Key differences
| Gemini Flash | Docling | |
|---|---|---|
| How you run it | Hosted API (Gemini API or Vertex AI) | Python library that runs locally; CPU works, GPU speeds up model stages |
| Licence | Proprietary | MIT (individual models have their own licences) |
| Price | Token-based: $0.50 input and $3.00 output per 1M tokens for Gemini 3 Flash Preview; cost per page varies with page density and output length | Free and self-hosted; you pay for compute |
| Output formats | Markdown, JSON, HTML, plain text; shaped by your prompt, with no fixed schema or confidence scores | Markdown, HTML, JSON, DocTags, plain text; structured DoclingDocument with lossless JSON |
| OmniDocBench v1.6 overall | 92.62 (Gemini 3 Flash) | Not published |
| Input formats | Images and PDFs read directly | PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL |
| Known failure | Several newer Flash models move from $0.75/$3.75 to $1.50/$7.50 per 1M tokens on January 1, 2027 | Version 2.143.1 drops words and numbers with full-page Tesseract OCR (issue #5254); neighbouring columns can merge on some layouts (issue #5132) |
Sources
- Gemini API pricing
- OmniDocBench leaderboard
- Docling GitHub README
- Supported formats
- Issue #5254 OCR regression
- Issue #5132 reading order
What each one is
Gemini Flash
General vision model with strong handwriting and layout understanding at a low price.
Gemini Flash detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "google/gemini-flash","fallbacks": ["ibm/docling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Gemini Flash vs TesseractGemini Flash vs MinerUGPT vs DoclingMistral OCR vs DoclingLlamaParse vs DoclingPaddleOCR-VL vs DoclingMinerU vs DoclingDocling vs Tesseract
Gemini Flash alternativesDocling alternativesBest OCR models in 2026