{
  "name": "Google Document AI",
  "slug": "google-document-ai",
  "website_url": "https://cloud.google.com/document-ai",
  "vendor_description": "\"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.\"",
  "categories": [
    "ocr"
  ],
  "summary": "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.",
  "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"
    ],
    "supported_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)"
    ],
    "supported_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"
    ],
    "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)"
    ],
    "output_types": [
      "JSON"
    ],
    "webhooks_supported": false,
    "sandbox_available": false,
    "sdk_languages": [
      "Python",
      "Java",
      "Node.js",
      "Go",
      "C#",
      "PHP",
      "Ruby",
      "C++"
    ],
    "mcp_server_available": false
  },
  "integration": {
    "api_style": "rest",
    "base_url": "https://documentai.googleapis.com/v1",
    "api_version": "v1",
    "versioning_scheme": "url",
    "stability": "ga",
    "deprecation_policy_url": "https://cloud.google.com/document-ai/docs/deprecation",
    "auth_methods": [
      "oauth2"
    ],
    "auth_docs_url": "https://cloud.google.com/docs/authentication/provide-credentials-adc",
    "idempotency_supported": false,
    "error_format": "google.rpc.Status",
    "webhook_signing": null,
    "webhook_events_url": null,
    "rate_limit_requests": 600,
    "rate_limit_window": "minute",
    "sdk_packages": [
      {
        "package": "google-cloud-documentai",
        "language": "Python",
        "official": true,
        "repo_url": "https://github.com/googleapis/python-documentai"
      },
      {
        "package": "com.google.cloud:google-cloud-document-ai",
        "language": "Java",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-java"
      },
      {
        "package": "@google-cloud/documentai",
        "language": "Node.js",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-node"
      },
      {
        "package": "cloud.google.com/go/documentai",
        "language": "Go",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-go"
      },
      {
        "package": "Google.Cloud.DocumentAI.V1",
        "language": "C#",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-dotnet"
      },
      {
        "package": "google/cloud-document-ai",
        "language": "PHP",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-php"
      },
      {
        "package": "google-cloud-document_ai",
        "language": "Ruby",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-ruby"
      },
      {
        "package": null,
        "language": "C++",
        "official": true,
        "repo_url": "https://github.com/googleapis/google-cloud-cpp"
      }
    ],
    "mcp_url": null,
    "quickstart_url": "https://cloud.google.com/document-ai/docs/process-documents-client-libraries"
  },
  "pricing": {
    "pricing_model": "usage_based",
    "has_published_pricing": true,
    "starting_price_usd": "0.0200",
    "price_basis": "1,000 pages",
    "free_tier_available": false,
    "free_tier_limit": null,
    "free_tier_details": null,
    "minimum_commitment": null,
    "self_serve_signup": true,
    "requires_sales_call": false,
    "requires_verification": true,
    "enterprise_plan_available": false,
    "price_points": [
      {
        "plan": "1–5,000,000 pages/month",
        "item": "Enterprise Document OCR Processor",
        "amount_usd": "1.5000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "5,000,001+ pages/month",
        "item": "Enterprise Document OCR Processor",
        "amount_usd": "0.6000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "OCR add-ons",
        "amount_usd": "6.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Custom Extractor",
        "amount_usd": "30.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Custom Extractor",
        "amount_usd": "20.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Form Parser",
        "amount_usd": "30.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Form Parser",
        "amount_usd": "20.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Layout Parser (includes initial chunking)",
        "amount_usd": "10.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Layout Parser (includes initial chunking)",
        "amount_usd": "10.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Re-chunking parsed documents",
        "amount_usd": "0.0200",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Custom Splitter",
        "amount_usd": "5.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Custom Splitter",
        "amount_usd": "3.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Custom Classifier",
        "amount_usd": "5.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Custom Classifier",
        "amount_usd": "3.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1–1,000,000 pages/month",
        "item": "Summarizer",
        "amount_usd": "25.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "1,000,001+ pages/month",
        "item": "Summarizer",
        "amount_usd": "25.0000",
        "amount_percent": null,
        "per": "1,000 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Invoice Parser",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "10 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Expense Parser",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "10 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Utility Parser",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "10 pages",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Procurement Document Splitter & Classifier",
        "amount_usd": "0.0500",
        "amount_percent": null,
        "per": "classified document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Bank Statement Parser",
        "amount_usd": "0.7500",
        "amount_percent": null,
        "per": "classified document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Pay Slip Parser",
        "amount_usd": "0.3000",
        "amount_percent": null,
        "per": "classified document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "W2 Parser",
        "amount_usd": "0.3000",
        "amount_percent": null,
        "per": "classified document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Lending Document Splitter & Classifier",
        "amount_usd": "0.0500",
        "amount_percent": null,
        "per": "classified document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "US Driver License Parser",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "US Passport Parser",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Identity Document Proofing",
        "amount_usd": "0.1000",
        "amount_percent": null,
        "per": "document",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": "Provisioned (Reserved Capacity)",
        "item": "Reserved capacity (extra page-per-minute slot)",
        "amount_usd": "300.0000",
        "amount_percent": null,
        "per": "page-per-minute per month",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      },
      {
        "plan": null,
        "item": "Custom processor version hosting",
        "amount_usd": "0.0500",
        "amount_percent": null,
        "per": "hour per deployed processor version",
        "currency": "USD",
        "source_url": "https://cloud.google.com/document-ai/pricing"
      }
    ]
  },
  "compliance": {
    "soc2": "type_2",
    "hipaa": true,
    "gdpr": true,
    "iso_27001": true,
    "pci_dss": true,
    "sla_published": true,
    "sla_url": "https://cloud.google.com/document-ai/sla",
    "data_retention_policy_url": "https://cloud.google.com/document-ai/docs/security",
    "documented_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.",
    "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"
    ]
  },
  "developer": {
    "docs_url": "https://docs.cloud.google.com",
    "api_reference_url": null,
    "openapi_spec_url": null,
    "postman_collection_url": null,
    "changelog_url": null,
    "status_page_url": "https://status.cloud.google.com",
    "llms_txt_url": null,
    "markdown_docs_url": null,
    "rendering": "static"
  },
  "adoption": {
    "launched_at": "2020-10-16",
    "ga_date": "2021-03-31",
    "github_stars": null,
    "github_stars_at": null,
    "notable_customers": [
      "Covered California",
      "Gogolook"
    ]
  },
  "scores": {
    "agent_friendliness": 30,
    "pricing_transparency": 85,
    "setup_speed": 60,
    "docs_quality": 15,
    "procurement_friction": 85,
    "trust_readiness": 100,
    "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"
    ]
  },
  "sources": [
    {
      "field": "vendor_description",
      "url": "https://docs.cloud.google.com/document-ai/docs/overview",
      "excerpt": "A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data",
      "confidence": "high"
    },
    {
      "field": "vendor_description",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest",
      "excerpt": "Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI",
      "confidence": "high"
    },
    {
      "field": "primary_use_cases",
      "url": "https://docs.cloud.google.com/document-ai/docs/overview",
      "excerpt": "Processing medical intake forms at doctor's offices; Parsing receipts and invoices for expense report validation; Authenticating identity based on ID cards; Extracting income information from tax forms for approving loans",
      "confidence": "high"
    },
    {
      "field": "primary_use_cases",
      "url": "https://docs.cloud.google.com/document-ai/docs/overview",
      "excerpt": "Digitize documents using OCR to get text, layout, and various add ons; Extract text and layout information, from document files and normalize entities; Classify document types to drive downstream processes; Split and classify documents by type",
      "confidence": "high"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/process",
      "excerpt": "Processes a single document.",
      "confidence": "high"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors.processorVersions/train",
      "excerpt": "Trains a new processor version. Operation metadata is returned as TrainProcessorVersionMetadata.",
      "confidence": "high"
    },
    {
      "field": "supported_regions",
      "url": "https://docs.cloud.google.com/document-ai/docs/regions",
      "excerpt": "You must specify either a regional or multi-regional location for data storage and document processing.",
      "confidence": "high"
    },
    {
      "field": "supported_languages",
      "url": "https://docs.cloud.google.com/document-ai/docs/languages",
      "excerpt": "Extract key-value pairs, checkboxes, and tables from documents more than 200 languages.",
      "confidence": "high"
    },
    {
      "field": "input_types",
      "url": "https://docs.cloud.google.com/document-ai/docs/file-types",
      "excerpt": "Microsoft Word Office Open XML (OOXML) (.docx), Microsoft PowerPoint OOXML (.pptx), and Microsoft Excel OOXML (.xlsx). HyperText Markup Language (HTML) (.html).",
      "confidence": "high"
    },
    {
      "field": "output_types",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/batchProcess",
      "excerpt": "LRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format.",
      "confidence": "high"
    },
    {
      "field": "sandbox_available",
      "url": "https://docs.cloud.google.com/document-ai/docs/try-docai",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "sdk_languages",
      "url": "https://docs.cloud.google.com/document-ai/docs/process-documents-client-libraries",
      "excerpt": "npm install @google-cloud/documentai",
      "confidence": "high"
    },
    {
      "field": "pricing_model",
      "url": "https://docs.cloud.google.com/document-ai/docs/overview",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "has_published_pricing",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "Custom extractor: $30 per 1,000 pages (1-1M pages/month) or $20 per 1,000 pages (1M+ pages/month)",
      "confidence": "high"
    },
    {
      "field": "self_serve_signup",
      "url": "https://docs.cloud.google.com/document-ai/docs/setup",
      "excerpt": "This guide provides all required setup steps to start using Document AI.",
      "confidence": "high"
    },
    {
      "field": "soc2",
      "url": "https://cloud.google.com/security/compliance/soc-2",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "hipaa",
      "url": "https://cloud.google.com/security/compliance/hipaa",
      "excerpt": "Document AI is HIPAA compliant",
      "confidence": "high"
    },
    {
      "field": "gdpr",
      "url": "https://cloud.google.com/privacy/gdpr",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "iso_27001",
      "url": "https://docs.cloud.google.com/document-ai/docs/security",
      "excerpt": "Google Cloud has regular audits for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.",
      "confidence": "high"
    },
    {
      "field": "pci_dss",
      "url": "https://docs.cloud.google.com/document-ai/docs/security",
      "excerpt": "Google Cloud has regular audits for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.",
      "confidence": "high"
    },
    {
      "field": "sla_published",
      "url": "https://cloud.google.com/document-ai/sla",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "documented_rate_limits",
      "url": "https://docs.cloud.google.com/document-ai/quotas",
      "excerpt": "120 per project per processor type applies to both US and EU regions for provisioned sync generic RPM.",
      "confidence": "high"
    },
    {
      "field": "known_restrictions",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "You are not billed for failed requests (4xx or 5xx response codes).",
      "confidence": "high"
    },
    {
      "field": "auth_methods",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/process",
      "excerpt": "OAuth scope required: https://www.googleapis.com/auth/cloud-platform",
      "confidence": "high"
    },
    {
      "field": "api_style",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest",
      "excerpt": "v1: https://documentai.googleapis.com/$discovery/rest?version=v1",
      "confidence": "high"
    },
    {
      "field": "base_url",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest",
      "excerpt": "https://documentai.googleapis.com",
      "confidence": "high"
    },
    {
      "field": "api_version",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest",
      "excerpt": "v1: https://documentai.googleapis.com/$discovery/rest?version=v1",
      "confidence": "high"
    },
    {
      "field": "error_format",
      "url": "https://docs.cloud.google.com/document-ai/docs/error-messages",
      "excerpt": "details { [type.googleapis.com/google.rpc.ErrorInfo] { reason: \"ERROR_CODE\" domain: \"documentai.googleapis.com\" } }",
      "confidence": "high"
    },
    {
      "field": "rate_limit_requests",
      "url": "https://docs.cloud.google.com/document-ai/quotas",
      "excerpt": "1,800 per user is the default value for base requests per minute.",
      "confidence": "high"
    },
    {
      "field": "starting_price_usd",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "Enterprise Document OCR Processor: 1-5,000,000 pages/month: $1.50 per 1,000 pages",
      "confidence": "high"
    },
    {
      "field": "launched_at",
      "url": "https://cloud.google.com/blog/products/ai-machine-learning/google-cloud-announces-document-ai-platform",
      "excerpt": "Today, the DocAI platform is available in preview",
      "confidence": "high"
    },
    {
      "field": "notable_customers",
      "url": "https://cloud.google.com/customers/gogolook",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/create",
      "excerpt": "Creates a processor from the ProcessorType provided. The processor will be at ENABLED state by default after its creation.",
      "confidence": "high"
    },
    {
      "field": "supported_regions",
      "url": "https://docs.cloud.google.com/document-ai/docs/regions",
      "excerpt": "\"asia-south1\" (Mumbai), \"asia-southeast1\" (Singapore), \"australia-southeast1\" (Sydney), \"eu\" (European Union), \"europe-west2\" (London), \"europe-west3\" (Frankfurt), \"northamerica-northeast1\" (Montréal), \"us\" (United States)",
      "confidence": "high"
    },
    {
      "field": "supported_languages",
      "url": "https://docs.cloud.google.com/document-ai/docs/languages",
      "excerpt": "Identify and extract text, including handwritten text, from documents in more than 200 languages.",
      "confidence": "high"
    },
    {
      "field": "input_types",
      "url": "https://docs.cloud.google.com/document-ai/docs/file-types",
      "excerpt": "Portable Document Format (PDF) (.pdf), Graphics Interchange Format (GIF) (.gif), Tag Image File Format (TIFF) (.tiff, .tif), Joint Photographic Experts Group (JPEG) (.jpg, .jpeg), Portable Network Graphics (PNG) (.png), Bitmap (BMP) (.bmp), and WebP (.webp)",
      "confidence": "high"
    },
    {
      "field": "output_types",
      "url": "https://docs.cloud.google.com/document-ai/docs/send-request",
      "excerpt": "the response in JSON format. The response body contains an instance of Document",
      "confidence": "high"
    },
    {
      "field": "webhooks_supported",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/process",
      "excerpt": "Processes a single document.",
      "confidence": "medium"
    },
    {
      "field": "sdk_languages",
      "url": "https://docs.cloud.google.com/document-ai/docs/process-documents-client-libraries",
      "excerpt": "pip install --upgrade google-cloud-documentai",
      "confidence": "high"
    },
    {
      "field": "pricing_model",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "You are not billed for failed requests (4xx or 5xx response codes).",
      "confidence": "high"
    },
    {
      "field": "has_published_pricing",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "Enterprise Document OCR Processor: 1-5,000,000 pages/month: $1.50 per 1,000 pages; 5,000,001+ pages/month: $0.60 per 1,000 pages",
      "confidence": "high"
    },
    {
      "field": "free_tier_available",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "self_serve_signup",
      "url": "https://docs.cloud.google.com/document-ai/docs/setup",
      "excerpt": "You must enable the Document AI API for your project.",
      "confidence": "high"
    },
    {
      "field": "soc2",
      "url": "https://docs.cloud.google.com/document-ai/docs/security",
      "excerpt": "Google Cloud has regular audits for standards such as ISO 27001, ISO 27017, ISO 27018, SOC 2, SOC 3, and PCI DSS.",
      "confidence": "high"
    },
    {
      "field": "hipaa",
      "url": "https://docs.cloud.google.com/document-ai/docs/security",
      "excerpt": "Document AI is HIPAA compliant",
      "confidence": "high"
    },
    {
      "field": "gdpr",
      "url": "https://cloud.google.com/terms/data-processing-addendum",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "iso_27001",
      "url": "https://cloud.google.com/security/compliance/iso-27001",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "pci_dss",
      "url": "https://cloud.google.com/security/compliance/pci-dss",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "documented_rate_limits",
      "url": "https://docs.cloud.google.com/document-ai/quotas",
      "excerpt": "1,800 per user is the default value for base requests per minute.",
      "confidence": "high"
    },
    {
      "field": "known_restrictions",
      "url": "https://docs.cloud.google.com/document-ai/docs/file-types",
      "excerpt": "Scans should be a minimum of 200 dpi with 300 dpi and higher producing optimal results.",
      "confidence": "high"
    },
    {
      "field": "known_restrictions",
      "url": "https://docs.cloud.google.com/document-ai/docs/languages",
      "excerpt": "Only the English language is officially supported for generative AI extraction",
      "confidence": "high"
    },
    {
      "field": "auth_methods",
      "url": "https://docs.cloud.google.com/docs/authentication/provide-credentials-adc",
      "excerpt": "How you set up Application Default Credentials (ADC) for use by Cloud Client Libraries, Google API Client Libraries, and the REST and RPC APIs depends on the environment where your code is running.",
      "confidence": "high"
    },
    {
      "field": "api_style",
      "url": "https://docs.cloud.google.com/document-ai/docs/send-request",
      "excerpt": "POST https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process",
      "confidence": "high"
    },
    {
      "field": "base_url",
      "url": "https://docs.cloud.google.com/document-ai/docs/send-request",
      "excerpt": "POST https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process",
      "confidence": "high"
    },
    {
      "field": "api_version",
      "url": "https://docs.cloud.google.com/document-ai/docs/reference/rest/v1/projects.locations.processors/process",
      "excerpt": "POST https://documentai.googleapis.com/v1/{name}:process",
      "confidence": "high"
    },
    {
      "field": "rate_limit_requests",
      "url": "https://docs.cloud.google.com/document-ai/quotas",
      "excerpt": "120 per project per processor type applies to both US and EU regions for provisioned sync generic RPM.",
      "confidence": "high"
    },
    {
      "field": "starting_price_usd",
      "url": "https://cloud.google.com/document-ai/pricing",
      "excerpt": "Re-chunking parsed documents: $0.02 per 1,000 pages",
      "confidence": "high"
    },
    {
      "field": "launched_at",
      "url": "https://docs.cloud.google.com/document-ai/docs/release-notes",
      "excerpt": "Document AI Preview released with General processors: Document OCR (Optical Character Recognition), form parser, and document splitter",
      "confidence": "high"
    },
    {
      "field": "notable_customers",
      "url": "https://cloud.google.com/customers/coveredcalifornia",
      "excerpt": "In 2023, Covered California ran a small pilot program with Google Cloud to test the viability of Document AI to meet its accuracy, efficiency, and scalability requirements.",
      "confidence": "high"
    }
  ],
  "fields_not_found": [
    "sla_uptime_percentage (SLA page exists but exact monthly uptime percentage not extractable from public page)",
    "free_tier_limit",
    "mcp_url",
    "webhook_signing",
    "webhook_events_url",
    "idempotency_supported (not documented; treated as false)"
  ],
  "source_confidence": "high",
  "last_verified_at": "2026-06-14T00:00:00.000Z",
  "contribute": {
    "note": "This data is crowd-editable. Suggest corrections or leave a review via these endpoints - no auth required, requests are rate-limited, and every submission is reviewed before it goes live. For a field edit, {field} is any key in this response and a citation is required.",
    "endpoints": [
      {
        "action": "review",
        "label": "Leave a review or comment",
        "method": "POST",
        "url": "https://apio.sh/api/feedback/google-document-ai",
        "example_body": {
          "kind": "review",
          "rating": 5,
          "body": "Your experience with this API…"
        }
      },
      {
        "action": "field_edit",
        "label": "Suggest a correction to a field (cite a source)",
        "method": "POST",
        "url": "https://apio.sh/api/suggest/google-document-ai/{field}",
        "example_body": {
          "value": "corrected value",
          "citations": [
            {
              "url": "https://source.example/page",
              "excerpt": "supporting quote"
            }
          ],
          "note": "what changed and why"
        }
      },
      {
        "action": "new_api",
        "label": "Suggest a new API to add",
        "method": "POST",
        "url": "https://apio.sh/api/suggest/api",
        "example_body": {
          "value": {
            "name": "Acme API",
            "website_url": "https://acme.example"
          },
          "citations": [
            {
              "url": "https://acme.example"
            }
          ]
        }
      },
      {
        "action": "token",
        "label": "Optional - raise your rate limit",
        "method": "GET",
        "url": "https://apio.sh/api/feedback/token"
      }
    ]
  }
}