Gemini Flash vs Marker
Pick Gemini Flash for cheap, hosted bulk conversion of PDFs to Markdown or JSON, especially mixed-language documents, with no GPU to run. Pick Marker when you need to self-host, keep documents on your own hardware, or run on CPU, and your company is under the $5M weight-license limit or you pay for a licence. The main split is a pay-per-token proprietary API versus open code you run yourself.
Gemini Flashgoogle/gemini-flash | Markerdatalab/marker | |
|---|---|---|
| Type | Vision model | OCR API |
| Price | 15 credits / page | 14 credits / page |
| Per 1,000 pages | $15.00 | $14.00 |
| Typical speed | 1.6 s / page | 2.5 s / page |
| Best for | Handwriting and mixed layouts | Books and research papers |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | 90+ languages |
| Max pages per request | 1,000 | 1,000 |
| 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, an independent leaderboard, close to Gemini 3 Pro at 92.91.
- A context window of up to 1M tokens fits long documents in one request, and you can prompt it for Markdown, JSON, HTML or plain text.
- Pricing is $0.50 per 1M input tokens and $3.00 per 1M output tokens, or $0.25 and $1.50 on Batch/Flex, with no hardware to manage.
Choose Marker if
- It runs locally on GPU, CPU or Apple Silicon, so documents never leave your machine, which Gemini Flash cannot do for air-gapped or on-prem setups.
- Fast mode runs on CPU at 23.6 pages per second with about 18 MB of ONNX weights.
- It suits books and papers with equations, and outputs Markdown, HTML, JSON block trees, LaTeX and RAG chunks.
Key differences
| Gemini Flash | Marker | |
|---|---|---|
| Deployment | Hosted API only (Gemini API or Vertex AI) | Self-hosted on GPU, CPU or MPS, or Datalab's hosted API |
| Licence | Proprietary | Code Apache-2.0; weights under a modified AI Pubs Open Rail-M license, free for research, personal use and startups under $5M |
| Price | $0.50 input / $3.00 output per 1M tokens (Gemini 3 Flash Preview); cost per page varies with page density and output length | Free self-hosted within the weight license, you pay for compute; hosted API has about 5,000 free pages per month |
| Output formats | Markdown, JSON, HTML, plain text, driven by your prompt with no fixed schema or confidence scores | Markdown, HTML, JSON, chunks, LaTeX, images |
| Benchmark | 92.62 on OmniDocBench v1.6 (Gemini 3 Flash), independent | 83.7 on olmOCR-bench and 85.9 on OmniParseBench in vllm mode, both published by Datalab |
| Hardware | None needed on your side | vllm mode needs an NVIDIA GPU; CPU fast mode drops to 66.6 on olmOCR-bench |
| Known issue | Several newer Flash models rise from $0.75/$3.75 to $1.50/$7.50 per 1M tokens on January 1, 2027 | Weight license blocks commercial use for companies above $5M without a paid license |
Sources
- Gemini API pricing
- OmniDocBench leaderboard
- Gemini pricing changes 2026
- Marker GitHub README
- Datalab pricing
What each one is
Gemini Flash
General vision model with strong handwriting and layout understanding at a low price.
Gemini Flash detailsMarker
Hosted version of the open-source Marker and Surya models. Strong on books and papers.
Marker 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": ["datalab/marker"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Gemini Flash alternativesMarker alternativesBest OCR models in 2026