Limits

This document lists the system limits that apply to Document AI. Unlike quotas, system limits can't be changed.

Content limits

The following content limits apply to all Document AI processors.

Content limit Value
Maximum image resolution
(limit does not apply to PDF files)		 40 megapixels (per page if image contains multiple pages)
Maximum file size for online processing requests 40 MB
Maximum file size for batch processing requests 1 GB
Files per batch processing request 5,000 files

Processor limits

Limits are defined in the current list.

Extraction processors

Processor Limits
Custom Extractor
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 200
Maximum pages (imageless mode online/synchronous requests): 30
Form Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 100
Maximum pages (imageless mode online/synchronous requests): 30
Layout Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 500
Maximum pages (imageless mode online/synchronous requests): 30

Classification processors

Processor Limits
Custom Classifier
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 200
Maximum pages (imageless mode online/synchronous requests): 30
Custom Splitter
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 1000
Maximum pages (imageless mode online/synchronous requests): 30

Digitize processors

Processor Limits
Enterprise Document OCR (Optical Character Recognition)
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 500
Maximum pages (imageless mode online/synchronous requests): 30

Pretrained processors

Processor Limits
Bank Statement Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 30
Maximum pages (imageless mode online/synchronous requests): 30
W2 Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 15
Maximum pages (imageless mode online/synchronous requests): 15
Identity Document Proofing Parser
Maximum pages (online/synchronous requests): 2
Maximum pages (batch/offline/asynchronous requests): 2
Maximum pages (imageless mode online/synchronous requests): 2
Pay Slip Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 50
Maximum pages (imageless mode online/synchronous requests): 30
US Driver License Parser
Maximum pages (online/synchronous requests): 2
Maximum pages (batch/offline/asynchronous requests): 2
Maximum pages (imageless mode online/synchronous requests): 2
Expense Parser
Maximum pages (online/synchronous requests): 10
Maximum pages (batch/offline/asynchronous requests): 10
Maximum pages (imageless mode online/synchronous requests): 10
Invoice Parser
Maximum pages (online/synchronous requests): 15
Maximum pages (batch/offline/asynchronous requests): 200
Maximum pages (imageless mode online/synchronous requests): 30

Limitations for Document AI

Document AI has the current limitations.

Criteria Stable release July 2023
Dataset
  • Maximum of 30,000 documents total
  • Maximum of 250,000 pages total
Processing time
    Batch jobs are processed asynchronously and are not designed for real-time applications. Most jobs finish within 12 to 24 hours after they start running (not counting the queue time). After 24 hours, incomplete jobs are canceled. You're only charged for completed requests.
Document import
  • Maximum of 5,000 documents per import
  • Maximum of 200 pages per document
Limits to train a Custom Document Extractor (CDE) Model-based training (GA)
  • Training dataset maximums: 25,000 documents; 100,000 pages
  • Training dataset minimum: each label needs to be present on at least 1 label per 10 documents
  • Test dataset maximums: 2,000 documents; 8,000 pages
  • Test dataset minimum: every label on at least 10 documents
  • Maximum of 200 pages per document

Template-based training (GA)
  • Training dataset maximums: 300 documents, 300 pages
  • Training dataset minimum: every label on at least on at least 3 documents
  • Test dataset maximums: 2,000 documents; 8,000 pages
  • Test dataset minimum: every label on at least 3 documents
  • Maximum of 20 pages per document
Limits to train a Custom Document Classifier (CDC) or a Custom Document Splitter (CDS)
  • Training dataset maximums: 30,000 documents; 100,000 pages
  • Training dataset minimum: every label on at least 10 documents
  • Test dataset maximums: 2,000 documents; 8,000 pages
  • Test dataset minimum: every label on at least 2 documents
  • Maximum of 200 pages per document
Labeling
  • To get started, verify document labels meet defined minimum training and evaluation thresholds.
  • To begin evaluating model performance for documents with layout variation, label at least 100 documents. Specifically, verify that each label exists on 50 documents in training and 50 in evaluation.
  • Maximum allowed labels (fields): 150
  • Label size limits (characters): Long items aren't well supported, but there's no explicit limit. Chunk documents into 800- or 1,000-token pieces, with 100 to 200 tokens overlapping between chunks. (Items longer than the overlapping area might run into quality issues.)
  • Label occurrences in a document: No limit
Geographic coverage
  • Regions generally supported: US, EU (multiregion)
  • Regions with limited accessibility: Germany, Singapore, UK, Canada, India, Australia

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026年08月26日 UTC.