OCRRouter

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-flashMarkerdatalab/marker
TypeVision modelOCR API
Price15 credits / page14 credits / page
Per 1,000 pages$15.00$14.00
Typical speed1.6 s / page2.5 s / page
Best forHandwriting and mixed layoutsBooks and research papers
InputsPDF, imagesPDF, images, DOCX
Languages100+ languages90+ languages
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 FlashMarker
DeploymentHosted API only (Gemini API or Vertex AI)Self-hosted on GPU, CPU or MPS, or Datalab's hosted API
LicenceProprietaryCode 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 lengthFree self-hosted within the weight license, you pay for compute; hosted API has about 5,000 free pages per month
Output formatsMarkdown, JSON, HTML, plain text, driven by your prompt with no fixed schema or confidence scoresMarkdown, HTML, JSON, chunks, LaTeX, images
Benchmark92.62 on OmniDocBench v1.6 (Gemini 3 Flash), independent83.7 on olmOCR-bench and 85.9 on OmniParseBench in vllm mode, both published by Datalab
HardwareNone needed on your sidevllm mode needs an NVIDIA GPU; CPU fast mode drops to 66.6 on olmOCR-bench
Known issueSeveral newer Flash models rise from $0.75/$3.75 to $1.50/$7.50 per 1M tokens on January 1, 2027Weight license blocks commercial use for companies above $5M without a paid license

Sources

What each one is

Gemini Flash

General vision model with strong handwriting and layout understanding at a low price.

Gemini Flash details

Marker

Hosted version of the open-source Marker and Surya models. Strong on books and papers.

Marker details

Try 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": ["datalab/marker"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Gemini Flash alternativesMarker alternativesBest OCR models in 2026