All models
Document AIPreview
Google CloudGoogle 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.
Plain-English overview
What Google Document AI Custom Extractor 3.5 actually is
Custom Extractor 3.5 is for jobs where plain OCR is not enough. A team defines fields such as supplier, renewal date, line items, or risk clauses, and the processor returns those named entities from documents with variable layouts.
The Gemini 3.5 Flash version can also populate nested or derived information, such as calculating a value or inferring a category from the document. That makes it closer to configurable intelligent document processing than a generic vision model.
Good fit for
- Contracts, invoices, statements, and business forms
- Schema-driven fields across changing layouts
- Derived values that are not copied verbatim from one spot
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
- $30 / 1K pages to 1M · $20 / 1K aboveA current provider rate and the exact page or annotation unit it covers.
- Accepted documents
- PDF and image documents with a custom field schemaThe file and document types the listed endpoint is designed to process.
- What you get back
- Named entities, nested fields, and derived valuesMarkdown, tables, chunks, fields, descriptions, or another machine-readable result.
- Layout & confidence
- Field-level document entities; confidence not promised for v3.5Whether 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; US/EU processingDirect 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 Document AI Custom Extractor 3.5
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 Document AI Custom Extractor 3.5
Availability
Regions and access stage
Release-candidate access through Google Cloud Document AI, powered by Gemini 3.5 Flash.
Machine-learning processing is listed for US and EU locations, but fine-tuning is not available for this processor version.
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 Document AI Custom Extractor 3.5 FAQ
What is 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. Custom Extractor 3.5 is for jobs where plain OCR is not enough. A team defines fields such as supplier, renewal date, line items, or risk clauses, and the processor returns those named entities from documents with variable layouts.
When was Google Document AI Custom Extractor 3.5 released?
Google Document AI Custom Extractor 3.5 was released on May 26, 2026 according to the cited provider materials.
Where can I access Google Document AI Custom Extractor 3.5?
Release-candidate access through Google Cloud Document AI, powered by Gemini 3.5 Flash. The access routes listed in this guide are Google Cloud.
How much does Google Document AI Custom Extractor 3.5 cost?
$30 / 1,000 pages for the first 1M pages. Google lists $20 per 1,000 pages above one million. The prediction price is the same for generative and custom-model extractor versions.
Where is Google Document AI Custom Extractor 3.5 available?
Release-candidate access through Google Cloud Document AI, powered by Gemini 3.5 Flash. Machine-learning processing is listed for US and EU locations, but fine-tuning is not available for this processor version.
Is my Google Document AI Custom Extractor 3.5 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 Document AI Custom Extractor 3.5 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 Document AI Custom Extractor 3.5 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 Document AI Custom Extractor 3.5 vs 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.
Open full comparison
