Google Document AI
"A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume." [1]
Google Document AI is a REST API from Google Cloud that transforms unstructured documents into structured data, covering OCR, data extraction from invoices, receipts, and forms, identity document verification, and custom trained extraction models. Pricing is usage-based at $0.02 per 1,000 pages with self-serve signup and no sales call required. The API ships official SDKs for eight languages including Python, Java, Node.js, and Go, and is available across eight regions including US, EU, and Asia-Pacific endpoints. It carries SOC 2 Type 2, ISO 27001, HIPAA, GDPR, and PCI DSS compliance certifications.
Best for / Avoid if
Best for: Teams needing broad API coverage out of the box; Cost-sensitive teams - low, transparent entry price
Avoid if: You want to try it free before paying
Scores
- 30 / 100Agent friendliness
- 85 / 100Pricing transparency
- 60 / 100Setup speed
- 15 / 100Docs quality
- 85 / 100Procurement ease
- 100 / 100Trust readiness
Pricing & procurement
- Pricing model
- Usage-based [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✗ No [4]
- Self-serve signup
- ✓ Yes [5]
- Requires sales call
- ✗ No
- Enterprise plan
- ✗ No
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| 1–5,000,000 pages/month | Enterprise Document OCR Processor | 1,000 pages | $1.5 | source |
| 5,000,001+ pages/month | Enterprise Document OCR Processor | 1,000 pages | $0.6 | source |
| OCR add-ons | 1,000 pages | $6 | source | |
| 1–1,000,000 pages/month | Custom Extractor | 1,000 pages | $30 | source |
| 1,000,001+ pages/month | Custom Extractor | 1,000 pages | $20 | source |
| 1–1,000,000 pages/month | Form Parser | 1,000 pages | $30 | source |
| 1,000,001+ pages/month | Form Parser | 1,000 pages | $20 | source |
| 1–1,000,000 pages/month | Layout Parser (includes initial chunking) | 1,000 pages | $10 | source |
| 1,000,001+ pages/month | Layout Parser (includes initial chunking) | 1,000 pages | $10 | source |
| Re-chunking parsed documents | 1,000 pages | $0.02 | source | |
| 1–1,000,000 pages/month | Custom Splitter | 1,000 pages | $5 | source |
| 1,000,001+ pages/month | Custom Splitter | 1,000 pages | $3 | source |
| 1–1,000,000 pages/month | Custom Classifier | 1,000 pages | $5 | source |
| 1,000,001+ pages/month | Custom Classifier | 1,000 pages | $3 | source |
| 1–1,000,000 pages/month | Summarizer | 1,000 pages | $25 | source |
| 1,000,001+ pages/month | Summarizer | 1,000 pages | $25 | source |
| Invoice Parser | 10 pages | $0.1 | source | |
| Expense Parser | 10 pages | $0.1 | source | |
| Utility Parser | 10 pages | $0.1 | source | |
| Procurement Document Splitter & Classifier | classified document | $0.05 | source | |
| Bank Statement Parser | classified document | $0.75 | source | |
| Pay Slip Parser | classified document | $0.3 | source | |
| W2 Parser | classified document | $0.3 | source | |
| Lending Document Splitter & Classifier | classified document | $0.05 | source | |
| US Driver License Parser | document | $0.1 | source | |
| US Passport Parser | document | $0.1 | source | |
| Identity Document Proofing | document | $0.1 | source | |
| Provisioned (Reserved Capacity) | Reserved capacity (extra page-per-minute slot) | page-per-minute per month | $300 | source |
| Custom processor version hosting | hour per deployed processor version | $0.05 | source |
Capabilities
- Supported actions
- process (synchronous document processing), batchProcess (asynchronous batch document processing), create processor, delete processor, enable processor, disable processor, list processors, get processor, setDefaultProcessorVersion, deploy processor version, undeploy processor version, train processor version, delete processor version, list processor versions, evaluateProcessorVersion, fetchProcessorTypes, list processor types, get processor type, cancel operation, get operation, list operations, reviewDocument (human review, deprecated), importDocuments (dataset), listDocuments (dataset), getDocument (dataset), batchDeleteDocuments (dataset), updateDatasetSchema, getDatasetSchema, create schema, delete schema, get schema, list schemas, patch schema, create schema version, generate schema version, get schema version, list schema versions, patch schema version [6]
- Regions
- us (United States multi-region), eu (European Union multi-region), asia-south1 (Mumbai), asia-southeast1 (Singapore), australia-southeast1 (Sydney), europe-west2 (London), europe-west3 (Frankfurt), northamerica-northeast1 (Montréal) [7]
- Languages
- English, French, German, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Ukrainian, Chinese (Simplified), Chinese (Traditional), Japanese, Korean, Hindi, Bengali, Thai, Vietnamese, Arabic, Persian, Hebrew, Afrikaans, Albanian, Armenian, Bulgarian, Croatian, Czech, Danish, Estonian, Finnish, Greek, Hungarian, Icelandic, Indonesian, Latvian, Lithuanian, Macedonian, Malay, Marathi, Nepali, Norwegian, Romanian, Serbian, Slovak, Slovenian, Swedish, Turkish, Yiddish, 200+ languages supported for Enterprise Document OCR and Form Parser [8]
- Input types
- application/pdf, image/jpeg, image/png, image/tiff, image/gif, image/bmp, image/webp, text/html (Layout Parser only), application/vnd.openxmlformats-officedocument.wordprocessingml.document (Layout Parser only), application/vnd.openxmlformats-officedocument.presentationml.presentation (Layout Parser only), application/vnd.openxmlformats-officedocument.spreadsheetml.sheet (Layout Parser only) [9]
- Output types
- JSON [10]
- Webhooks
- ✗ No [11]
- Sandbox / test mode
- ✗ No [12]
- SDK languages
- Python, Java, Node.js, Go, C#, PHP, Ruby, C++ [13]
- MCP server
- ✗ No
Trust & compliance
- SOC 2
- SOC 2 Type II [14]
- HIPAA
- ✓ Yes [15]
- GDPR
- ✓ Yes [16]
- ISO 27001
- ✓ Yes [17]
- PCI DSS
- ✓ Yes [18]
- Published SLA
- ✓ Yes [19]
- Rate limits
- Online process requests per minute (US or EU multi-region): 120 per project per processor type; Online process requests per minute (single region): 6 per project per processor type; Concurrent batch requests (US or EU): 5 per project; Concurrent batch requests (single region): 5 per project; Base requests per minute: 1,800 per user; Default pages per minute (Best Effort, base processors): 120 PPM; Default pages per minute (Best Effort, Pro processors): 60 PPM; Concurrent training requests: 1 per project per region; Deployed custom processor versions: 5 per project per region; Deployed generative processor versions: 100 per project per custom extraction processor. [20]
- Known restrictions
- HTML and OOXML (DOCX, PPTX, XLSX) input supported only with Layout Parser, Custom Splitter only supports PDF, TIFF, TIF, and GIF input, Recommended minimum image resolution: 200 dpi; 300+ dpi for best results, Utility Parser and Procurement Document Splitter & Classifier require form submission for access (limited access), Custom processor hosting billed at $0.05 per hour per deployed processor version regardless of usage, Provisioned capacity reservation: $300 USD per extra page-per-minute per month, 4xx/5xx error responses are not billed, Only English officially supported for Custom Extractor when using generative AI extraction, Batch processing results stored in Cloud Storage (not returned inline), DOCX page unit: up to 3,000 characters = 1 page; XLSX: each tab = 1 page; PPTX: each slide = 1 page; HTML/parsed docs: up to 3,000 characters = 1 page [21]
Developer surface
Integration
- API style
- rest
- Base URL
- https://documentai.googleapis.com/v1
- Version
- v1
- Versioning
- url
- Stability
- ga
- Auth methods
- oauth2
- Idempotency keys
- ✗ No
- Error format
- google.rpc.Status
- Rate limit
- 600 / minute
Adoption & maturity
- Launched
- 2020-10-16
- GA
- 2021-03-31
- Notable customers
- Covered California, Gogolook
Other OCR & Document Parsing APIs
Amazon Textract
"Automatically extract printed text, handwriting, layout elements, and data from any document"
Veryfi
"Documents into Data - securely, in seconds"
Azure AI Document Intelligence
"Azure Document Intelligence in Foundry Tools is a machine-learning based OCR and intelligent document processing service to automate extraction of key data from forms and documents."
Nanonets
"AI Agents for Enterprise Data Processing."
Extend
"Turn documents into high quality data"
Mindee
"Turn your document data into structured JSON with high-reliability. Zero model training required."
References
- ↑Description: docs.cloud.google.com · docs.cloud.google.com
- ↑Pricing model: docs.cloud.google.com · cloud.google.com
- ↑Published pricing: cloud.google.com · cloud.google.com
- ↑Free tier: cloud.google.com
- ↑Self-serve signup: docs.cloud.google.com · docs.cloud.google.com
- ↑Supported actions: docs.cloud.google.com · docs.cloud.google.com · docs.cloud.google.com
- ↑Regions: docs.cloud.google.com · docs.cloud.google.com
- ↑Languages: docs.cloud.google.com · docs.cloud.google.com
- ↑Input types: docs.cloud.google.com · docs.cloud.google.com
- ↑Output types: docs.cloud.google.com · docs.cloud.google.com
- ↑Webhooks: docs.cloud.google.com
- ↑Sandbox: docs.cloud.google.com
- ↑SDK languages: docs.cloud.google.com · docs.cloud.google.com
- ↑SOC 2: cloud.google.com · docs.cloud.google.com
- ↑HIPAA: cloud.google.com · docs.cloud.google.com
- ↑GDPR: cloud.google.com · cloud.google.com
- ↑ISO 27001: docs.cloud.google.com · cloud.google.com
- ↑PCI DSS: docs.cloud.google.com · cloud.google.com
- ↑Published SLA: cloud.google.com
- ↑Rate limits: docs.cloud.google.com · docs.cloud.google.com
- ↑Known restrictions: cloud.google.com · docs.cloud.google.com · docs.cloud.google.com
Change history
- 2026-06-15 Score Agent Friendliness: 10 → 30
- 2026-06-14 Has Structured Data: (none) → Yes
- 2026-06-14 Robots Allows Agents: (none) → Yes
- 2026-06-14 Capabilities: {} → {"tables":true,"id_documents":true,"custom_models":true,"agentic_output":true,"…
- 2026-06-14 Summary Md: (none) → Google Document AI is a REST API from Google Cloud that transforms unstructured…
- 2026-06-14 Score Docs Quality: 0 → 15
- 2026-06-14 Docs URL: (none) → https://docs.cloud.google.com
- 2026-06-14 Rendering: (none) → static
- 2026-06-14 Status Page URL: (none) → https://status.cloud.google.com
- 2026-06-14 Llms Txt Present: (none) → No
- 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-14 Avoid If: (none) → You want to try it free before paying
- 2026-06-14 Score Agent Friendliness: (none) → 10
- 2026-06-14 Score Pricing Transparency: (none) → 85
- 2026-06-14 Score Setup Speed: (none) → 60
- 2026-06-14 Score Docs Quality: (none) → 0
- 2026-06-14 Score Procurement Friction: (none) → 85
- 2026-06-14 Score Trust Readiness: (none) → 100
- 2026-06-14 Best For: (none) → Teams needing broad API coverage out of the box, Cost-sensitive teams - low, tr…
- 2026-06-14 SDK Packages: Python, Java, Node.js, Go, C#, PHP, Ruby, C++ → Python, Java, Node.js, Go, C#, PHP, Ruby, C++
- 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
- 2026-06-14 Starting Price Usd: 0.02 → 0.02
- 2026-06-13 Requires Sales Call: set to No
- 2026-06-13 Enterprise Plan Available: set to No
- 2026-06-13 GDPR: set to Yes
- 2026-06-13 ISO 27001: set to Yes
- 2026-06-13 PCI DSS: set to Yes
- 2026-06-13 SLA Published: set to Yes
- 2026-06-13 SLA URL: set to https://cloud.google.com/document-ai/sla
- 2026-06-13 Data Retention Policy URL: set to https://cloud.google.com/document-ai/docs/security
- 2026-06-13 Documented Rate Limits: set to Online process requests per minute (US or EU multi-region): 120 per project per…
- 2026-06-13 Rate Limit Requests: set to 600
- 2026-06-13 Rate Limit Window: set to minute
- 2026-06-13 Known Restrictions: set to HTML and OOXML (DOCX, PPTX, XLSX) input supported only with Layout Parser, Cust…
- 2026-06-13 Auth Methods: set to oauth2
- 2026-06-13 Auth Docs URL: set to https://cloud.google.com/docs/authentication/provide-credentials-adc
- 2026-06-13 API Style: set to rest
- 2026-06-13 Base URL: set to https://documentai.googleapis.com/v1
- 2026-06-13 API Version: set to v1
- 2026-06-13 Versioning Scheme: set to url
- 2026-06-13 Stability: set to ga
- 2026-06-13 Deprecation Policy URL: set to https://cloud.google.com/document-ai/docs/deprecation
- 2026-06-13 Quickstart URL: set to https://cloud.google.com/document-ai/docs/process-documents-client-libraries
- 2026-06-13 Idempotency Supported: set to No
- 2026-06-13 Error Format: set to google.rpc.Status
- 2026-06-13 Requires Verification: set to Yes
- 2026-06-13 Starting Price Usd: set to 0.02
- 2026-06-13 Price Basis: set to 1,000 pages
- 2026-06-13 Slug: set to google-document-ai
- 2026-06-13 GA Date: set to 2021-03-31
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/google-document-ai \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/google-document-ai/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'