Gemini Flash vs Chunkr
Pick Gemini Flash for cheap, bulk PDF to Markdown or JSON extraction through a hosted API, especially on long or mixed-language documents. Pick Chunkr when you need layout parsing with bounding boxes and chunks for RAG, or when you must self-host. The main split is a prompt-driven general model billed by token versus a dedicated parsing service you can run yourself.
Gemini Flashgoogle/gemini-flash | Chunkrchunkr/chunkr | |
|---|---|---|
| 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 | 3.0 s / page |
| Best for | Handwriting and mixed layouts | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | Multilingual |
| 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, close to Gemini 3 Pro at 92.91, and Chunkr has no published benchmark to set against it.
- Pricing is public and low: $0.50 per 1M input tokens and $3.00 per 1M output tokens, or $0.25 and $1.50 on Batch/Flex.
- A context window of up to 1M tokens fits long documents in one request, and it handles mixed-language documents.
Choose Chunkr if
- You can self-host it with Docker on GPU, CPU-only or Mac ARM, so documents stay in your own environment, which Gemini Flash cannot offer.
- It returns OCR with bounding boxes plus semantic chunking, which suits RAG pipelines. Gemini Flash gives no coordinates or confidence scores by default.
- It accepts PDF, PPT, Word and images, and works with any OpenAI-compatible LLM endpoint.
Key differences
| Gemini Flash | Chunkr | |
|---|---|---|
| Deployment | Hosted API only (Gemini API or Vertex AI) | Cloud API or self-hosted via Docker |
| Licence | Proprietary | AGPL-3.0 or commercial licence; closed-source use needs the commercial one |
| Pricing | Gemini 3 Flash Preview: $0.50 input and $3.00 output per 1M tokens; Batch/Flex $0.25 and $1.50 | Hosted credit-based plans, prices not published here; open-source version is free but you pay for compute and an LLM endpoint |
| Output formats | Markdown, JSON, HTML, plain text, shaped by your prompt with no fixed schema | HTML, Markdown, JSON and bounding boxes |
| Benchmark | 92.62 on OmniDocBench v1.6 (Gemini 3 Flash) | Not published |
| Input types | Images and PDFs | PDF, PPT, Word and images; no Excel in the open-source version |
| Known weakness | Token billing makes cost per page vary with page density and output length. Several newer Flash models rise from $0.75/$3.75 to $1.50/$7.50 per 1M tokens on January 1, 2027. | The open-source version uses community models that are less accurate than the cloud's, and it still needs an external LLM endpoint |
Sources
- Gemini API pricing
- OmniDocBench leaderboard
- Gemini pricing changes 2026
- Chunkr GitHub README
- Chunkr site
What each one is
Gemini Flash
General vision model with strong handwriting and layout understanding at a low price.
Gemini Flash detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Gemini Flash alternativesChunkr alternativesBest OCR models in 2026