All models
Document AIPreview
Google CloudGoogle Gemini Layout Parser 1.6
Google Cloud's Gemini-assisted parser for preserving document hierarchy and creating context-rich chunks for enterprise search and RAG.
Plain-English overview
What Google Gemini Layout Parser 1.6 actually is
Gemini Layout Parser 1.6 combines Google OCR with Gemini 3.0 Flash. It identifies headings, paragraphs, lists, tables, figures, headers, and footers, then builds a document tree so a retrieved passage can keep the context of the section it came from.
This is a parsing and chunking service rather than a general chat model. It is especially useful when flat OCR would separate a table from its headers or a paragraph from its parent section.
Good fit for
- RAG over reports, manuals, and filings
- Layout-aware chunks with inherited headings
- Mixed PDF, presentation, document, and spreadsheet ingestion
Category comparison
The facts that matter for documents models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price per page
- $10 / 1K pages, including initial chunkingA current provider rate and the exact page or annotation unit it covers.
- Accepted documents
- PDF, HTML, DOCX, PPTX, XLSX, XLSMThe file and document types the listed endpoint is designed to process.
- What you get back
- DocumentLayout hierarchy, contextual chunks, table/figure descriptionsMarkdown, tables, chunks, fields, descriptions, or another machine-readable result.
- Layout & confidence
- OCR-grounded headings, tables, figures, lists, headers and footersWhether the output preserves boxes, hierarchy, labels, reading order, or confidence information.
- Language coverage
- Not enumerated for this versionProvider-documented language support without inferring unlisted languages.
- Where it runs
- Google Cloud Document AI; global Gemini endpointDirect API, batch service, private environment, marketplace, or regional cloud route.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Counts pages, not files. A 10-page PDF counts as 10 pages. The estimate uses the document-processing rate available for each model.
Google Gemini Layout Parser 1.6
Google Cloud
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Google Gemini Layout Parser 1.6
Availability
Regions and access stage
Release-candidate access through Google Cloud Document AI.
This version uses the global Vertex AI Gemini endpoint and is explicitly not compliant with Google's data-residency standard, even when called through US or EU endpoints.
Check live availabilityData and training
The route matters.
Google says Document AI customer documents and predictions are not used to train its models. Online documents are processed in memory without disk persistence; batch inputs have a failsafe retention of up to one day.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Google Gemini Layout Parser 1.6 FAQ
What is Google Gemini Layout Parser 1.6?
Google Cloud's Gemini-assisted parser for preserving document hierarchy and creating context-rich chunks for enterprise search and RAG. Gemini Layout Parser 1.6 combines Google OCR with Gemini 3.0 Flash. It identifies headings, paragraphs, lists, tables, figures, headers, and footers, then builds a document tree so a retrieved passage can keep the context of the section it came from.
When was Google Gemini Layout Parser 1.6 released?
Google Gemini Layout Parser 1.6 was released on January 13, 2026 according to the cited provider materials.
Where can I access Google Gemini Layout Parser 1.6?
Release-candidate access through Google Cloud Document AI. The access routes listed in this guide are Google Cloud.
How much does Google Gemini Layout Parser 1.6 cost?
$10 / 1,000 pages. Google Cloud's Layout Parser price includes initial chunking. Re-chunking is billed separately.
Where is Google Gemini Layout Parser 1.6 available?
Release-candidate access through Google Cloud Document AI. This version uses the global Vertex AI Gemini endpoint and is explicitly not compliant with Google's data-residency standard, even when called through US or EU endpoints.
Is my Google Gemini Layout Parser 1.6 API data used for training?
Google says Document AI customer documents and predictions are not used to train its models. Online documents are processed in memory without disk persistence; batch inputs have a failsafe retention of up to one day. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Google Gemini Layout Parser 1.6 vs Cohere Parse 5
Cohere's compact document parser for turning enterprise PDFs, presentations, and scans into retrieval-ready Markdown and layout metadata.
Open full comparisonGoogle Gemini Layout Parser 1.6 vs Mistral OCR 4.1
Mistral's current Document AI OCR model for preserving reading order, tables, structure, locations, and confidence across multilingual files.
Open full comparisonGoogle Gemini Layout Parser 1.6 vs Google Document AI Custom Extractor 3.5
Google Cloud's Gemini-powered Document AI processor for extracting the exact fields and derived values defined in a business schema.
Open full comparison
