{ "data": { "a": { "slug": "docling", "name": "Docling", "vendor": "Docling Project (LF AI \u0026 Data Foundation, started at IBM Research Zurich)", "vendorUrl": "https://docling-project.github.io/docling/", "kind": "sdk", "category": "document-extraction", "summary": "Docling is an open-source Python library and CLI that converts PDFs, Office files, HTML, images and audio into a structured DoclingDocument, Markdown or JSON, with layout, table and OCR models, plus a REST server (docling-serve) and an MCP server.", "url": "https://www.anchorterminal.com/tools/docling", "markdownUrl": "https://www.anchorterminal.com/tools/docling.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/docling.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/docling.json", "dns": "docling.grade.anchorterminal.com", "repo": "https://github.com/docling-project/docling", "license": "MIT", "transports": [ "stdio", "streamable-http", "http" ], "packages": [ { "registry": "pypi", "name": "docling" }, { "registry": "pypi", "name": "docling-mcp" }, { "registry": "pypi", "name": "docling-serve" } ], "auth": "none", "authNotes": "The library and the stdio MCP server need no credentials. docling-serve requires an `X-Api-Key` header only when `DOCLING_SERVE_API_KEY` is set; it is off by default. Models are downloaded from Hugging Face on first use or prefetched for offline use.", "pricing": "free", "pricingNotes": "Free and MIT-licensed, run on your own hardware. No paid edition from the project was found (checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "Self-hosted library and servers with nothing to buy; no payment protocol in the repositories (checked 2026-11-06).", "endpoints": [] }, "toolCount": 25, "popularity": { "githubStars": 70216, "npmWeekly": null, "pypiWeekly": 946968, "asOf": "2026-11-06" }, "docsUrl": "https://docling-project.github.io/docling/", "registryName": "io.github.docling-project/docling-mcp", "capabilities": [ "docs.parse", "docs.tables", "docs.ocr", "docs.chunk", "docs.extract" ], "tags": [ "open-source", "mit", "python", "self-hosted", "local", "cli", "mcp", "stdio", "mcp-registry", "docker", "no-telemetry", "free" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 64.3, "grade": "B", "agentReady": false, "rank": 475, "ranked": true, "rankOf": 1486, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 77, "maintenance": 89, "payments": 60, "reliability": 85, "schema": 77, "security": 53, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -8, "negativeNotes": [ "-8: 28 security advisories published on GitHub between 2 June and 23 October 2026, 5 rated High, among them arbitrary file read and write with the opt-in Tectonic TikZ engine (GHSA-x3q2-h9hx-4r4j, 1 October), unsafe zip extraction in the EasyOCR model download and XML entity expansion in the USPTO backend (both 2 June), and an SSRF guard bypass (1 October). All were published by the maintainers with fixed releases, so the deduction is reduced for disclosure, as with directus's published advisories. https://github.com/docling-project/docling/security" ], "verdict": "An MIT Python library with a CLI, a REST server and a 25-tool MCP server converts PDFs, Office files, HTML and scans into structured documents on the user's own machine, with near-daily releases. Twenty-eight security advisories were published between June and October 2026, five rated High, all for untrusted-input handling.", "bestFor": "Self-hosted PDF and Office conversion to Markdown or JSON for RAG and agents that can't send documents out.", "strengths": [ "MIT licence, hosted by the LF AI \u0026 Data Foundation, with no telemetry found in the source", "Runs locally, and remote services stay off unless `enable_remote_services=True` is set", "Releases v2.136.0 to v2.148.0 between 9 October and 5 November 2026, with a semantic-release changelog", "docling-mcp groups its tools (conversion, generation, manipulation) and marks them with readOnlyHint and destructiveHint", "A public disclosure policy, and advisories published on GitHub with fixes" ], "weaknesses": [ "28 advisories from 2 June to 23 October 2026, five High, including arbitrary file read and write through the opt-in Tectonic TikZ engine", "No llms.txt on the docs site (404)", "docling-serve's only access control is one optional shared API key, off by default", "Parsed document text is untrusted, and no prompt-injection guidance was found", "About 719 open issues and 223 open pull requests on the main repository" ], "agentNotes": [ "Keep `enable_remote_services` and remote image fetching off when converting untrusted files, and set `max_num_pages` and `max_file_size`", "Upgrade to v2.148.0 or later before parsing untrusted documents, since recent releases fix memory-exhaustion and file-read flaws", "Start docling-mcp with only the tool groups the task needs, and use the anchor tools to read parts of a long document", "Treat converted text as untrusted input, never as instructions", "Set DOCLING_SERVE_API_KEY before exposing docling-serve beyond localhost" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.3 } ], "editorialScores": { "ergonomics": 77, "maintenance": 89, "payments": 60, "reliability": 85, "schema": 77, "security": 53, "transparency": 77 }, "provenanceScore": 52, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install docling", "config": { "mcpServers": { "docling": { "args": [ "--from=docling-mcp", "docling-mcp-server" ], "command": "uvx" } } } }, "letme": { "capability": "https://letme.dev/docs.parse", "tool": "https://letme.dev/docling" }, "area": "web-data", "provenance": { "legalEntity": "Docling Project (LF AI \u0026 Data Foundation)", "domain": "docling-project.github.io", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/docling-project/docling/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "MIT licence. The project is hosted by the LF AI \u0026 Data Foundation and was started at IBM Research Zurich; no single legal entity publishes it.", "The security policy is on the repository's Security tab with private advisory reporting and an email route; docling-project.github.io has no security.txt.", "docling-project.github.io/docling/llms.txt answered 404 on 6 November 2026." ], "score": 52 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/docling.json", "live": { "slug": "docling", "versions": [ { "registry": "github", "name": "docling-project/docling", "version": "v2.148.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:21:57.627571586Z" }, { "registry": "mcp-registry", "name": "io.github.docling-project/docling-mcp", "version": "3.5.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "pypi", "name": "docling", "version": "2.148.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:21:53.500253508Z" }, { "registry": "pypi", "name": "docling-mcp", "version": "3.5.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:21:54.889201724Z" }, { "registry": "pypi", "name": "docling-serve", "version": "1.38.2", "released": "2026-10-27", "seenAt": "2026-11-06T23:21:55.609213125Z" } ], "githubStars": 70222, "pypiWeekly": 946968, "securityTxt": { "url": "https://docling-project.github.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:37.972746959Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/docling-project/docling/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:20:39.957874821Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d0ae114890b9" } ], "updatedAt": "2026-11-07T18:16:28.95801333Z" } }, "answer": "Google Cloud Document AI scores 72.2 (BB) on agent readiness against Docling's 64.3 (B), and leads in 4 of 7 scored categories. Docling leads on agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "google-cloud-document-ai", "name": "Google Cloud Document AI", "vendor": "Google Cloud", "vendorUrl": "https://cloud.google.com/document-ai", "kind": "http-api", "category": "document-extraction", "summary": "Google Cloud's service for OCR, layout parsing, chunking, form and table extraction, classification and splitting of documents. Work runs through processors created per project and location. Access is a REST and gRPC API with client libraries in eight languages.", "url": "https://www.anchorterminal.com/tools/google-cloud-document-ai", "markdownUrl": "https://www.anchorterminal.com/tools/google-cloud-document-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/google-cloud-document-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/google-cloud-document-ai.json", "dns": "google-cloud-document-ai.grade.anchorterminal.com", "repo": "https://github.com/googleapis/google-cloud-python/tree/main/packages/google-cloud-documentai", "license": "Proprietary service under the Google Cloud Platform Terms of Service. The client libraries are Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "google-cloud-documentai" }, { "registry": "npm", "name": "@google-cloud/documentai" } ], "auth": "oauth", "authNotes": "Access starts with a Google Cloud project that has the Document AI API and billing enabled, all self-serve in the console. Calls take an OAuth 2.0 bearer token from a service account or Application Default Credentials in the `Authorization` header, with the single scope `https://www.googleapis.com/auth/cloud-platform`. IAM decides what the caller can do, through four predefined roles from `roles/documentai.apiUser` (process only) to `roles/documentai.admin`, grantable on a project or one processor. The docs show no API key flow. Three pretrained processors are open to limited access customers only, by request form.", "pricing": "freemium", "pricingNotes": "Pay as you go per page, with no plan. Enterprise Document OCR is $1.50 per 1,000 pages ($0.60 past 5 million), and the pricing page shows the first 1,000 at $0.00. Layout Parser is $10, Form Parser and Custom Extractor $30 ($20 past a million), Custom Classifier and Splitter $5 ($3 past a million), all per 1,000 pages. Invoice, expense and identity parsers are $0.10 per document of up to 10 pages. Re-chunking parsed documents is $0.02 per 1,000. A deployed custom processor version costs $0.05 an hour to host. Gemini Enterprise Flexible Savings Plans of one and three years take 10 and 20 per cent off, on opt-in. Failed requests are not billed. New customers get $300 of credit for 90 days, and sign-up needs a credit card or other payment method (https://cloud.google.com/document-ai/pricing, https://docs.cloud.google.com/free/docs/free-cloud-features).", "priceSummary": "$1.50 / 1k pages", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the Discovery document or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 498819, "pypiWeekly": 793248, "asOf": "2026-10-09" }, "docsUrl": "https://docs.cloud.google.com/document-ai/docs", "openapi": "https://documentai.googleapis.com/$discovery/rest?version=v1", "capabilities": [ "docs.parse", "docs.ocr", "docs.extract", "docs.tables", "docs.chunk" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "openapi", "oauth", "python", "typescript", "java", "dotnet", "enterprise", "eu", "async-jobs", "batch", "card-required" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 72.2, "grade": "BB", "agentReady": true, "rank": 134, "ranked": true, "rankOf": 1486, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 80, "payments": 20, "reliability": 90, "schema": 81, "security": 70, "transparency": 90 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "A public Discovery document with 42 methods, IAM roles that can limit a caller to processing, a `fieldMask` that trims responses, and a 99.9 per cent SLA on the US and EU endpoints. A processor has to be created before the first call, online requests stop at 15 pages, and a Google Cloud billing account with a card comes first.", "bestFor": "Agents already on Google Cloud that need OCR, form and table extraction or chunks for retrieval, with IAM, audit logs and EU processing.", "strengths": [ "Discovery document for v1 (revision 20261026) with 42 methods and 326 schemas, and descriptions on 952 of 966 properties", "`fieldMask`, `imagelessMode` and page selectors on the process request limit what comes back and what is billed", "The Document AI API User role allows processing only, roles can be granted on one processor, and process calls write Data Access audit logs once enabled", "The security page says online requests are processed in memory and not written to disk, and content is never used to train Document AI models", "99.9 per cent monthly uptime SLA for online and batch prediction on the `us` and `eu` multi-region endpoints", "Layout Parser returns layout-aware chunks with ancestor headings at $10 per 1,000 pages, and reads PDF, HTML, DOCX, PPTX and XLSX" ], "weaknesses": [ "An online request reads at most 15 pages (30 with `imagelessMode`). Longer files need a batch job through Cloud Storage", "A processor must be created in a project and location before any document can be sent, and the endpoint host changes with the location", "No guidance on retrying quota errors was found on the quotas, limits or request pages, and there is no idempotency key", "The $300 trial credit and the free first 1,000 OCR pages both sit on a billing account that needs a card or other payment method", "Legacy processor versions were discontinued on 30 June 2026 on a notice dated 17 February 2026, under the six months the version lifecycle page states", "No guidance on instructions hidden in document text was found in the pages read", "Layout Parser versions built on Gemini 3.0 use a global endpoint and, per the docs, do not meet data residency", "The OAuth token can be sent as an `access_token` URL query parameter, as on other Google APIs, so it can end up in logs" ], "agentNotes": [ "Create a processor first (`processors.create` or the console), then POST to `https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process`", "Use the host that matches the processor's location, `us-documentai.googleapis.com` or `eu-documentai.googleapis.com`", "Set `fieldMask` (for example `text,entities`) and `imagelessMode` to keep page images and token geometry out of the response", "Send more than 15 pages through `:batchProcess` with Cloud Storage input and output, then poll the operation. Jobs unfinished after 24 hours are cancelled", "Grant the service account `roles/documentai.apiUser` only and send its token in the `Authorization` header, never as `access_token` in the URL. Failed requests (4xx or 5xx) are not billed", "Treat extracted text as untrusted input" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.2 } ], "editorialScores": { "ergonomics": 70, "maintenance": 80, "payments": 20, "reliability": 90, "schema": 81, "security": 70, "transparency": 80 }, "provenanceScore": 99, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install --upgrade google-cloud-documentai # or: npm install @google-cloud/documentai", "http": "curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json; charset=utf-8\" -d @request.json \"https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process\"" }, "letme": { "capability": "https://letme.dev/docs.parse", "tool": "https://letme.dev/google-cloud-document-ai" }, "sameCompany": [ "gemini-api", "vertex-ai", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-cloud-tts", "gemini-live", "google-adk", "google-memory-bank", "google-secret-manager", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api" ], "area": "web-data", "unitPrices": [ { "item": "Enterprise Document OCR", "unit": "1k-pages", "usd": 1.5, "note": "Up to 5 million pages. $0.60 after. The page shows the first 1,000 at $0.00" }, { "item": "OCR add-ons", "unit": "1k-pages", "usd": 6, "note": "On top of the OCR price, Enterprise Document OCR v2 only" }, { "item": "Layout Parser", "unit": "1k-pages", "usd": 10, "note": "Includes the first chunking. DOCX and HTML count 3,000 characters as a page" }, { "item": "Form Parser", "unit": "1k-pages", "usd": 30, "note": "First million pages. $20 after" }, { "item": "Custom Extractor", "unit": "1k-pages", "usd": 30, "note": "First million pages. $20 after. Hosting is $0.05 an hour per deployed version" }, { "item": "Custom Classifier or Splitter", "unit": "1k-pages", "usd": 5, "note": "First million pages. $3 after" }, { "item": "Invoice, expense or identity parser", "unit": "tx", "usd": 0.1, "note": "Per document of up to 10 pages. Each further 10 pages is another $0.10" }, { "item": "Bank statement parser", "unit": "tx", "usd": 0.75, "note": "Per classified document" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoints are on googleapis.com, Google's API domain. Docs are on docs.cloud.google.com.", "endpointOnVendorDomain": true, "terms": "https://cloud.google.com/terms", "privacy": "https://cloud.google.com/terms/cloud-privacy-notice", "statusPage": "https://status.cloud.google.com", "changelog": "https://docs.cloud.google.com/document-ai/docs/release-notes", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "The Google Cloud Platform Terms of Service were last modified on 2 September 2026. They set the contracting Google entity by customer region at https://cloud.google.com/terms/google-entity.", "The Service Specific Terms (https://cloud.google.com/terms/service-terms, last modified 8 October 2026) carry the training restriction and the benchmarking clause.", "The Google Cloud Privacy Notice, effective 28 September 2026, covers Service Data and names Google LLC, 1600 Amphitheatre Parkway. Customer documents fall under the Cloud Data Processing Addendum.", "https://www.google.com/.well-known/security.txt shows Expires 2030-04-01 and points to the vulnerability reward programme.", "RDAP gives 1997-09-15 for google.com." ], "score": 99 }, "requirements": { "setupChecked": true, "complianceChecked": true, "card": "yes", "freeTier": true, "minutes": 20, "credential": "cloud-iam", "hosting": [ "US", "EU", "UK", "CA", "APAC" ], "euResidency": "yes", "trainsOnData": "no", "zeroRetention": "yes", "certifications": [ "SOC 2 Type II", "ISO 27001", "ISO 27701", "PCI DSS", "HIPAA (BAA available)", "GDPR" ], "dpa": true, "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/google-cloud-document-ai.json", "live": { "slug": "google-cloud-document-ai", "vendorStatus": { "page": "https://status.cloud.google.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T22:26:05.86538558Z" }, "versions": [ { "registry": "github", "name": "googleapis/google-cloud-python", "version": "google-maps-solar-v0.6.3", "released": "2026-11-05", "seenAt": "2026-11-06T23:29:07.229809379Z" }, { "registry": "npm", "name": "@google-cloud/documentai", "version": "10.2.0", "seenAt": "2026-11-06T23:29:06.881474936Z" }, { "registry": "pypi", "name": "google-cloud-documentai", "version": "3.17.0", "released": "2026-10-29", "seenAt": "2026-11-06T23:29:06.697729658Z" } ], "githubStars": 5415, "npmWeekly": 603387, "pypiWeekly": 866367, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-07T16:01:22.068349931Z" }, "domain": { "domain": "google.com", "registered": "1997-09-15", "source": "https://rdap.verisign.com/com/v1/domain/google.com", "checkedAt": "2026-11-01T14:17:18.719851913Z" }, "pages": [ { "url": "https://docs.cloud.google.com/document-ai/docs/release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:05:33.437995982Z", "changedAt": "2026-11-02T07:13:42.20004735Z", "fingerprint": "83ba2fe53e50" }, { "url": "https://cloud.google.com/document-ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:01:13.04462737Z", "changedAt": "2026-10-16T22:18:38.777911838Z", "fingerprint": "456ddc4b0f0f" }, { "url": "https://cloud.google.com/terms/cloud-privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-10-10T18:58:33.174595701Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "98f84e10526a" }, { "url": "https://cloud.google.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-10T18:58:30.858919152Z", "changedAt": "2026-10-08T18:16:24.0781454Z", "fingerprint": "92f14ada0b50" } ], "github": { "repo": "googleapis/google-cloud-python", "checkedAt": "2026-11-02T08:52:16.502690608Z", "stars": 5418, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-31T03:25:43Z", "openIssues": 466, "openPRs": 174, "issuesOpened90d": 124, "issuesClosed90d": 123, "prsMerged90d": 544, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-30T19:55:00Z" }, "replies": { "sampled": 25, "unanswered": 23, "medianDays": 4 } }, "updatedAt": "2026-11-07T16:01:22.068349931Z" } }, "edges": [ { "by": 40, "category": "payments", "leads": "docling", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule. Free MIT software with nothing to buy, so 20 + 20 + 20, and no payment protocol (0). 60.", "b": "No x402, MPP or L402 (0). Per-page prices for every processor published without a login (20). The first 1,000 OCR pages show at $0.00 and new customers get $300 of credit, but the Free Trial page says sign-up needs a credit card or other payment method (0). A person creates the project and billing account in a browser (0)." }, "scores": { "a": 60, "b": 20 } }, { "by": 25, "category": "transparency", "leads": "google-cloud-document-ai", "name": "Transparency \u0026 trust", "reasons": { "a": "MIT, an OSI licence, with model licences noted as separate (30). Runs locally, remote services off by default and air-gapped use documented; no privacy statement is needed for local use, but model downloads from Hugging Face on first run are only partly described (22 of 30). Breaking changes are marked in the changelog, with no deprecation policy or dated notices (10 of 20). No telemetry found in the source; nothing to opt out of (15 of 20). 30+22+10+15 = 77.", "b": "Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15 of 30). The security page says online requests are processed in memory, batch documents are deleted after processing with a failsafe of one day, and content is never used to train Document AI models. The service terms' training restriction and the Data Processing Addendum agree. Layout Parser versions on Gemini 3.0 route globally, which the docs state (27 of 30). The lifecycle page promises six months' notice for stable versions and lists a deprecation date per version, and the Cloud terms promise 12 months before a backwards-incompatible API change. The legacy processor notice of 17 February 2026 gave until 30 June 2026, about four and a half months (18 of 20). `us` and `eu` multi-regions, seven single regions and a public sub-processor list (20)." }, "scores": { "a": 65, "b": 90 } }, { "by": 17, "category": "security", "leads": "google-cloud-document-ai", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading. No credentials for local use; docling-serve has one optional shared key, off by default (20 of 30). Remote services are off unless explicitly enabled, local file fetch is guarded by flags, and MCP tools carry read-only and destructive annotations; manipulation tools can delete items and save files (12 of 20). Converted documents are untrusted text and no prompt-injection guidance was found (3 of 15). Logging only, no audit trail (3 of 15). A disclosure policy with private reporting, 28 advisories published in public with fixed versions, under the LF AI \u0026 Data Foundation; no bug bounty (15 of 20). 20+12+3+3+15 = 53. The advisories themselves are the deduction.", "b": "OAuth 2.0 bearer tokens from service accounts with IAM. The docs and samples send the token in the `Authorization` header, but Google's OAuth 2.0 guide documents sending it as an `access_token` query parameter, the v1 Discovery document (revision 20261026) lists `access_token`, `oauth_token` and `key` as query parameters, and on 1 November `documentai.googleapis.com` and `us-documentai.googleapis.com` answered a request with no token \"missing required authentication credential\" and one with a made-up `?access_token=` \"invalid authentication credentials\". So a token can travel in the URL, the 10-point deduction other Google APIs take (20). `roles/documentai.apiUser` allows processing only, roles can be granted on one processor, and deny policies and VPC Service Controls are supported. Nothing asks for confirmation before a processor is deleted (17 of 20). The service returns text from untrusted documents and no guidance on injected instructions was found in the pages read (0 of 15). The audit logging page (last updated 27 October) lists each method by permission type. `ProcessDocument` writes Data Access logs, which Google Cloud leaves off until the owner enables them (13 of 15). google.com security.txt valid to 1 April 2030 with the reward programme. The Document AI security page (last updated 26 October) states ISO 27001, SOC 2 and SOC 3 audits, FedRAMP High and HIPAA. None of the Google Cloud security bulletins, from GCP-2019-001 to GCP-2026-074 (28 October 2026), names Document AI (20)." }, "scores": { "a": 53, "b": 70 } }, { "by": 9, "category": "maintenance", "leads": "docling", "name": "Maintenance \u0026 community", "reasons": { "a": "v2.148.0 on 5 November 2026, the day before this check (30). 13 releases from 9 October to 5 November (20). Open issues and pull requests are numerous, an AI triage workflow and PR reminders run, and six maintainers are named; replies not sampled (17 of 25). docling-mcp publishes to the official MCP registry on release under io.github.docling-project, per its workflow and server.json; the registry entry itself was not read (12 of 15). CI, a dependency-update workflow and uv.lock (10). 30+20+17+12+10 = 89.", "b": "Read as a closed service with official SDKs. The newest release note is 21 September 2026, and the Python client 3.17.0 is dated 29 October 2026 in its changelog (30). Release notes on 21 September, Node.js releases dated 4 August, 8 September, 28 September and 8 October, and Python 3.16.0 on 1 October and 3.17.0 on 29 October, all in the 90 days from 3 August (20). Release notes with a feed, Google Cloud support and public issue trackers for each client library. We did not read the trackers (10 of 15). Official client libraries in eight languages, with Python and Node.js current (15). Python declares 3.10 to 3.15 and Node.js 22 or later. CI results were not checked (5 of 10)." }, "scores": { "a": 89, "b": 80 } }, { "by": 7, "category": "ergonomics", "leads": "docling", "name": "Agent ergonomics", "reasons": { "a": "About 25 MCP tools in the default groups (15), selectable as conversion, generation and manipulation groups, with anchor tools to read one part of a document (22 of 25). `max_num_pages`, `max_file_size` and page ranges on conversion, Markdown or JSON export (15 of 20). Errors are exceptions with messages, such as an unknown document key listing the valid ones (12 of 20). readOnlyHint and destructiveHint on the MCP tools, and conversions are repeatable (18 of 20). Sensible defaults and one call to convert; Python only, with a docling-client package for docling-serve (10 of 15). 22+15+12+18+10 = 77.", "b": "API reading. `fieldMask` picks top-level and page fields of the response, `imagelessMode` removes page images, and page selectors limit what is read. Without a mask the Document carries every token with geometry (20 of 25). List calls page with `pageSize` and `pageToken`, operations take a filter, and Layout Parser takes a chunk size. An online request stops at 15 pages, or 30 with `imagelessMode`, and longer files go through a batch job and Cloud Storage (15 of 20). Errors follow Google's status and message model, with no Document AI error page found (12 of 20). No idempotency key. Failed requests are not billed and processing changes no state, while a repeated successful call bills again. Batch operations can be polled (12 of 20). A processor has to be created before the first call and the host depends on its location. Client libraries in eight languages (11 of 15)." }, "scores": { "a": 77, "b": 70 } }, { "by": 5, "category": "reliability", "leads": "google-cloud-document-ai", "name": "Reliability", "reasons": { "a": "Local-software lines, graded on the library with docling-serve and docling-mcp. Installs from PyPI (`docling` 2.148.0, per the PyPI release feed) for Python 3.10 and later on macOS, Linux and Windows (20). Public CI workflows for checks, tests and heavy examples; the pass state of the default branch was not read (20 of 25). About 719 open issues and 223 open pull requests on the repository page against 13 releases in four weeks, many of them fixes; replies not sampled (15 of 25). Semantic-release changelog with Feature and Fix sections and Breaking sections where they apply (15). Version 2.x since 2024 (15). 20+20+15+15+15 = 85.", "b": "Hosted reading. Google Cloud status page with a JSON incident feed (20). The feed holds eight incidents back to February 2026, four of them since 3 August, and none names Document AI. They are the 20 August outage that lists 27 products, the 1 September network degradation in us-central1-b, elevated upload and write errors in Cloud Storage in us-central1 from 8 to 9 October and the europe-west2 incident of 20 October (06:00 to 12:08 UTC, 38 products). Batch processing reads and writes Cloud Storage, but the GCS incident was in one region and Document AI isn't listed. The page shows only broad incidents (30). Quotas published with numbers, 1,800 requests a minute per user, 120 online process requests a minute per processor type in `us` and `eu` and 5 concurrent batch requests, on a page last updated 28 October (15). No retry or backoff guidance was found on the quotas, limits or request pages. Processing changes no state and failed requests are not billed, so a retry is safe (5 of 15). 99.9 per cent monthly SLA for online and batch prediction, re-read on 1 November (10). v1 is GA (10)." }, "scores": { "a": 85, "b": 90 } } ], "facts": [ { "a": "SDK + MCP", "b": "HTTP API", "name": "Kind" }, { "a": "Docling Project (LF AI \u0026 Data Foundation, started at IBM Research Zurich)", "b": "Google Cloud", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "stdio, Streamable HTTP, HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary service under the Google Cloud Platform Terms of Service. The client libraries are Apache-2.0", "name": "Licence" }, { "a": "25", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "io.github.docling-project/docling-mcp", "b": "not listed", "name": "MCP registry" }, { "a": "2026-11-05", "b": "2026-10-29", "name": "Last release" }, { "a": "no document linked", "b": "2026-09-02", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-28", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "70k stars, 947k PyPI/wk", "b": "499k npm/wk, 793k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Google Cloud Document AI scores 72.2 (BB) on agent readiness against Docling's 64.3 (B), and leads in 4 of 7 scored categories. Docling leads on agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Docling or Google Cloud Document AI?" }, { "answer": "Docling runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Google Cloud Document AI.", "question": "Can an agent call Docling and Google Cloud Document AI without installing anything?" }, { "answer": "Docling is open source (MIT). No open-source release is listed for Google Cloud Document AI.", "question": "Are Docling and Google Cloud Document AI open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 77 against 70", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 89 against 80" ], "also": [ "No key needed to call it", "Runs on your own machine", "Open source" ], "goodFor": "Self-hosted PDF and Office conversion to Markdown or JSON for RAG and agents that can't send documents out.", "slug": "docling", "watchFor": "28 advisories from 2 June to 23 October 2026, five High, including arbitrary file read and write through the opt-in Tectonic TikZ engine" }, { "aheadOn": [ "Reliability, 90 against 85", "Security \u0026 auth, 70 against 53", "Transparency \u0026 trust, 90 against 65" ], "also": [ "Agent-ready, a grade of BB or better", "No incidents deducted, where Docling loses 8 points for them" ], "goodFor": "Agents already on Google Cloud that need OCR, form and table extraction or chunks for retrieval, with IAM, audit logs and EU processing.", "slug": "google-cloud-document-ai", "watchFor": "An online request reads at most 15 pages (30 with `imagelessMode`). Longer files need a batch job through Cloud Storage" } ], "history": { "docling": null, "google-cloud-document-ai": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": -1.7, "from": 73.9, "fromGrade": "BB", "to": 72.2, "toGrade": "BB" } ] }, "job": { "capability": "docs.parse", "name": "Document parsing" }, "others": [ { "json": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-docling.json", "title": "Adobe PDF Services / PDF Extract API vs Docling", "url": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-docling" }, { "json": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-google-cloud-document-ai.json", "title": "Adobe PDF Services / PDF Extract API vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/amazon-textract-vs-docling.json", "title": "Amazon Textract vs Docling", "url": "https://www.anchorterminal.com/compare/amazon-textract-vs-docling" }, { "json": "https://www.anchorterminal.com/compare/amazon-textract-vs-google-cloud-document-ai.json", "title": "Amazon Textract vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/amazon-textract-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-document-intelligence-vs-docling.json", "title": "Azure Document Intelligence vs Docling", "url": "https://www.anchorterminal.com/compare/azure-document-intelligence-vs-docling" }, { "json": "https://www.anchorterminal.com/compare/azure-document-intelligence-vs-google-cloud-document-ai.json", "title": "Azure Document Intelligence vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/azure-document-intelligence-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/datalab-vs-docling.json", "title": "Datalab vs Docling", "url": "https://www.anchorterminal.com/compare/datalab-vs-docling" }, { "json": "https://www.anchorterminal.com/compare/datalab-vs-google-cloud-document-ai.json", "title": "Datalab vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/datalab-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-extend.json", "title": "Docling vs Extend API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-extend" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-landingai-agentic-document-extraction.json", "title": "Docling vs LandingAI Agentic Document Extraction", "url": "https://www.anchorterminal.com/compare/docling-vs-landingai-agentic-document-extraction" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-llamaparse.json", "title": "Docling vs LlamaParse API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-llamaparse" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-mistral-ocr.json", "title": "Docling vs Mistral OCR API", "url": "https://www.anchorterminal.com/compare/docling-vs-mistral-ocr" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-nanonets.json", "title": "Docling vs Nanonets API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-nanonets" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-opendocrouter.json", "title": "Docling vs OpenDocRouter", "url": "https://www.anchorterminal.com/compare/docling-vs-opendocrouter" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-reducto.json", "title": "Docling vs Reducto API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-reducto" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-unstructured.json", "title": "Docling vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/extend-vs-google-cloud-document-ai.json", "title": "Extend API + MCP vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/extend-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-landingai-agentic-document-extraction.json", "title": "Google Cloud Document AI vs LandingAI Agentic Document Extraction", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-landingai-agentic-document-extraction" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-llamaparse.json", "title": "Google Cloud Document AI vs LlamaParse API + MCP", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-llamaparse" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mistral-ocr.json", "title": "Google Cloud Document AI vs Mistral OCR API", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mistral-ocr" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-nanonets.json", "title": "Google Cloud Document AI vs Nanonets API + MCP", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-nanonets" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-opendocrouter.json", "title": "Google Cloud Document AI vs OpenDocRouter", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-opendocrouter" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-reducto.json", "title": "Google Cloud Document AI vs Reducto API + MCP", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-reducto" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-unstructured.json", "title": "Google Cloud Document AI vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clairic-vs-docling.json", "title": "Clairic vs Docling", "url": "https://www.anchorterminal.com/compare/cloudflare-clairic-vs-docling" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clairic-vs-google-cloud-document-ai.json", "title": "Clairic vs Google Cloud Document AI", "url": "https://www.anchorterminal.com/compare/cloudflare-clairic-vs-google-cloud-document-ai" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-invofox.json", "title": "Docling vs Invofox", "url": "https://www.anchorterminal.com/compare/docling-vs-invofox" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-invofox.json", "title": "Google Cloud Document AI vs Invofox", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-invofox" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-mindee.json", "title": "Docling vs Mindee API", "url": "https://www.anchorterminal.com/compare/docling-vs-mindee" }, { "json": "https://www.anchorterminal.com/compare/docling-vs-veryfi.json", "title": "Docling vs Veryfi API + MCP", "url": "https://www.anchorterminal.com/compare/docling-vs-veryfi" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mindee.json", "title": "Google Cloud Document AI vs Mindee API", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mindee" }, { "json": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-veryfi.json", "title": "Google Cloud Document AI vs Veryfi API + MCP", "url": "https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-veryfi" } ], "panel": null, "scores": [ { "by": 5, "docling": 85, "edge": "google-cloud-document-ai", "google-cloud-document-ai": 90, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "docling": 77, "edge": "google-cloud-document-ai", "google-cloud-document-ai": 81, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 7, "docling": 77, "edge": "docling", "google-cloud-document-ai": 70, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 17, "docling": 53, "edge": "google-cloud-document-ai", "google-cloud-document-ai": 70, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "docling": 60, "edge": "docling", "google-cloud-document-ai": 20, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 9, "docling": 89, "edge": "docling", "google-cloud-document-ai": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 25, "docling": 65, "edge": "google-cloud-document-ai", "google-cloud-document-ai": 90, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Google Cloud Document AI scores 72.2 (BB) on agent readiness against Docling's 64.3 (B), and leads in 4 of 7 scored categories. Docling leads on agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do document parsing.", "tasks": null, "tutorials": [], "verdicts": { "docling": "An MIT Python library with a CLI, a REST server and a 25-tool MCP server converts PDFs, Office files, HTML and scans into structured documents on the user's own machine, with near-daily releases. Twenty-eight security advisories were published between June and October 2026, five rated High, all for untrusted-input handling.", "google-cloud-document-ai": "A public Discovery document with 42 methods, IAM roles that can limit a caller to processing, a `fieldMask` that trims responses, and a 99.9 per cent SLA on the US and EU endpoints. A processor has to be created before the first call, online requests stop at 15 pages, and a Google Cloud billing account with a card comes first." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai", "json": "https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.min.md" }, "markdown": "Google Cloud Document AI scores 72.2 (BB) on agent readiness against Docling's 64.3 (B), and leads in 4 of 7 scored categories. Docling leads on agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do document parsing.\n\n- Docling: grade B, 64.3/100, rank #475 of 1486. Markdown https://www.anchorterminal.com/tools/docling.md · JSON https://www.anchorterminal.com/api/v1/tools/docling.json\n- Google Cloud Document AI: grade BB, 72.2/100, rank #134 of 1486. Markdown https://www.anchorterminal.com/tools/google-cloud-document-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/google-cloud-document-ai.json\n- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md\n- All 182 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md\n\n## Which one, for what\n\n### Docling (B)\n\nGood for: Self-hosted PDF and Office conversion to Markdown or JSON for RAG and agents that can't send documents out.\n\nAhead on:\n- Agent ergonomics, 77 against 70\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 89 against 80\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- Open source\n\nWatch for: 28 advisories from 2 June to 23 October 2026, five High, including arbitrary file read and write through the opt-in Tectonic TikZ engine\n\n### Google Cloud Document AI (BB)\n\nGood for: Agents already on Google Cloud that need OCR, form and table extraction or chunks for retrieval, with IAM, audit logs and EU processing.\n\nAhead on:\n- Reliability, 90 against 85\n- Security \u0026 auth, 70 against 53\n- Transparency \u0026 trust, 90 against 65\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No incidents deducted, where Docling loses 8 points for them\n\nWatch for: An online request reads at most 15 pages (30 with `imagelessMode`). Longer files need a batch job through Cloud Storage\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Docling +40\n\n- Docling (60): Self-hosted rule. Free MIT software with nothing to buy, so 20 + 20 + 20, and no payment protocol (0). 60.\n- Google Cloud Document AI (20): No x402, MPP or L402 (0). Per-page prices for every processor published without a login (20). The first 1,000 OCR pages show at $0.00 and new customers get $300 of credit, but the Free Trial page says sign-up needs a credit card or other payment method (0). A person creates the project and billing account in a browser (0).\n\n### Transparency \u0026 trust: Google Cloud Document AI +25\n\n- Docling (65): MIT, an OSI licence, with model licences noted as separate (30). Runs locally, remote services off by default and air-gapped use documented; no privacy statement is needed for local use, but model downloads from Hugging Face on first run are only partly described (22 of 30). Breaking changes are marked in the changelog, with no deprecation policy or dated notices (10 of 20). No telemetry found in the source; nothing to opt out of (15 of 20). 30+22+10+15 = 77.\n- Google Cloud Document AI (90): Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15 of 30). The security page says online requests are processed in memory, batch documents are deleted after processing with a failsafe of one day, and content is never used to train Document AI models. The service terms' training restriction and the Data Processing Addendum agree. Layout Parser versions on Gemini 3.0 route globally, which the docs state (27 of 30). The lifecycle page promises six months' notice for stable versions and lists a deprecation date per version, and the Cloud terms promise 12 months before a backwards-incompatible API change. The legacy processor notice of 17 February 2026 gave until 30 June 2026, about four and a half months (18 of 20). `us` and `eu` multi-regions, seven single regions and a public sub-processor list (20).\n\n### Security \u0026 auth: Google Cloud Document AI +17\n\n- Docling (53): Framework reading. No credentials for local use; docling-serve has one optional shared key, off by default (20 of 30). Remote services are off unless explicitly enabled, local file fetch is guarded by flags, and MCP tools carry read-only and destructive annotations; manipulation tools can delete items and save files (12 of 20). Converted documents are untrusted text and no prompt-injection guidance was found (3 of 15). Logging only, no audit trail (3 of 15). A disclosure policy with private reporting, 28 advisories published in public with fixed versions, under the LF AI \u0026 Data Foundation; no bug bounty (15 of 20). 20+12+3+3+15 = 53. The advisories themselves are the deduction.\n- Google Cloud Document AI (70): OAuth 2.0 bearer tokens from service accounts with IAM. The docs and samples send the token in the `Authorization` header, but Google's OAuth 2.0 guide documents sending it as an `access_token` query parameter, the v1 Discovery document (revision 20261026) lists `access_token`, `oauth_token` and `key` as query parameters, and on 1 November `documentai.googleapis.com` and `us-documentai.googleapis.com` answered a request with no token \"missing required authentication credential\" and one with a made-up `?access_token=` \"invalid authentication credentials\". So a token can travel in the URL, the 10-point deduction other Google APIs take (20). `roles/documentai.apiUser` allows processing only, roles can be granted on one processor, and deny policies and VPC Service Controls are supported. Nothing asks for confirmation before a processor is deleted (17 of 20). The service returns text from untrusted documents and no guidance on injected instructions was found in the pages read (0 of 15). The audit logging page (last updated 27 October) lists each method by permission type. `ProcessDocument` writes Data Access logs, which Google Cloud leaves off until the owner enables them (13 of 15). google.com security.txt valid to 1 April 2030 with the reward programme. The Document AI security page (last updated 26 October) states ISO 27001, SOC 2 and SOC 3 audits, FedRAMP High and HIPAA. None of the Google Cloud security bulletins, from GCP-2019-001 to GCP-2026-074 (28 October 2026), names Document AI (20).\n\n### Maintenance \u0026 community: Docling +9\n\n- Docling (89): v2.148.0 on 5 November 2026, the day before this check (30). 13 releases from 9 October to 5 November (20). Open issues and pull requests are numerous, an AI triage workflow and PR reminders run, and six maintainers are named; replies not sampled (17 of 25). docling-mcp publishes to the official MCP registry on release under io.github.docling-project, per its workflow and server.json; the registry entry itself was not read (12 of 15). CI, a dependency-update workflow and uv.lock (10). 30+20+17+12+10 = 89.\n- Google Cloud Document AI (80): Read as a closed service with official SDKs. The newest release note is 21 September 2026, and the Python client 3.17.0 is dated 29 October 2026 in its changelog (30). Release notes on 21 September, Node.js releases dated 4 August, 8 September, 28 September and 8 October, and Python 3.16.0 on 1 October and 3.17.0 on 29 October, all in the 90 days from 3 August (20). Release notes with a feed, Google Cloud support and public issue trackers for each client library. We did not read the trackers (10 of 15). Official client libraries in eight languages, with Python and Node.js current (15). Python declares 3.10 to 3.15 and Node.js 22 or later. CI results were not checked (5 of 10).\n\n### Agent ergonomics: Docling +7\n\n- Docling (77): About 25 MCP tools in the default groups (15), selectable as conversion, generation and manipulation groups, with anchor tools to read one part of a document (22 of 25). `max_num_pages`, `max_file_size` and page ranges on conversion, Markdown or JSON export (15 of 20). Errors are exceptions with messages, such as an unknown document key listing the valid ones (12 of 20). readOnlyHint and destructiveHint on the MCP tools, and conversions are repeatable (18 of 20). Sensible defaults and one call to convert; Python only, with a docling-client package for docling-serve (10 of 15). 22+15+12+18+10 = 77.\n- Google Cloud Document AI (70): API reading. `fieldMask` picks top-level and page fields of the response, `imagelessMode` removes page images, and page selectors limit what is read. Without a mask the Document carries every token with geometry (20 of 25). List calls page with `pageSize` and `pageToken`, operations take a filter, and Layout Parser takes a chunk size. An online request stops at 15 pages, or 30 with `imagelessMode`, and longer files go through a batch job and Cloud Storage (15 of 20). Errors follow Google's status and message model, with no Document AI error page found (12 of 20). No idempotency key. Failed requests are not billed and processing changes no state, while a repeated successful call bills again. Batch operations can be polled (12 of 20). A processor has to be created before the first call and the host depends on its location. Client libraries in eight languages (11 of 15).\n\n### Reliability: Google Cloud Document AI +5\n\n- Docling (85): Local-software lines, graded on the library with docling-serve and docling-mcp. Installs from PyPI (`docling` 2.148.0, per the PyPI release feed) for Python 3.10 and later on macOS, Linux and Windows (20). Public CI workflows for checks, tests and heavy examples; the pass state of the default branch was not read (20 of 25). About 719 open issues and 223 open pull requests on the repository page against 13 releases in four weeks, many of them fixes; replies not sampled (15 of 25). Semantic-release changelog with Feature and Fix sections and Breaking sections where they apply (15). Version 2.x since 2024 (15). 20+20+15+15+15 = 85.\n- Google Cloud Document AI (90): Hosted reading. Google Cloud status page with a JSON incident feed (20). The feed holds eight incidents back to February 2026, four of them since 3 August, and none names Document AI. They are the 20 August outage that lists 27 products, the 1 September network degradation in us-central1-b, elevated upload and write errors in Cloud Storage in us-central1 from 8 to 9 October and the europe-west2 incident of 20 October (06:00 to 12:08 UTC, 38 products). Batch processing reads and writes Cloud Storage, but the GCS incident was in one region and Document AI isn't listed. The page shows only broad incidents (30). Quotas published with numbers, 1,800 requests a minute per user, 120 online process requests a minute per processor type in `us` and `eu` and 5 concurrent batch requests, on a page last updated 28 October (15). No retry or backoff guidance was found on the quotas, limits or request pages. Processing changes no state and failed requests are not billed, so a retry is safe (5 of 15). 99.9 per cent monthly SLA for online and batch prediction, re-read on 1 November (10). v1 is GA (10).\n\n## Score by category\n\n| Category | Weight | Docling | Google Cloud Document AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 85 | 90 | Google Cloud Document AI +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 77 | 81 | Google Cloud Document AI +4 |\n| Agent ergonomics | 13% (16.2 this run) | 77 | 70 | Docling +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 53 | 70 | Google Cloud Document AI +17 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Docling +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 89 | 80 | Docling +9 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 90 | Google Cloud Document AI +25 |\n| Negative events | ≤15 | -8 | 0 | |\n| **Total** | | **64.3 · B** | **72.2 · BB** | |\n\n## Facts side by side\n\n| Fact | Docling | Google Cloud Document AI |\n| --- | --- | --- |\n| Kind | SDK + MCP | HTTP API |\n| Vendor | Docling Project (LF AI \u0026 Data Foundation, started at IBM Research Zurich) | Google Cloud |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio, Streamable HTTP, HTTP | HTTP |\n| Auth | None | OAuth |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary service under the Google Cloud Platform Terms of Service. The client libraries are Apache-2.0 |\n| Tools exposed | 25 | none |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| MCP registry | `io.github.docling-project/docling-mcp` | not listed |\n| Last release | 2026-11-05 | 2026-10-29 |\n| Terms last updated | no document linked | 2026-09-02 |\n| Privacy policy last updated | no document linked | 2026-09-28 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | 70k stars, 947k PyPI/wk | 499k npm/wk, 793k PyPI/wk |\n| Agent reviews | none | 3.5/5 (4) |\n\n## How the scores have moved\n\n### Docling\n\nNo score change since it was listed.\n\n### Google Cloud Document AI\n\n- -1.7 on 1 November 2026: correction\n\n## Verdicts\n\n**Docling.** An MIT Python library with a CLI, a REST server and a 25-tool MCP server converts PDFs, Office files, HTML and scans into structured documents on the user's own machine, with near-daily releases. Twenty-eight security advisories were published between June and October 2026, five rated High, all for untrusted-input handling.\n\n**Google Cloud Document AI.** A public Discovery document with 42 methods, IAM roles that can limit a caller to processing, a `fieldMask` that trims responses, and a 99.9 per cent SLA on the US and EU endpoints. A processor has to be created before the first call, online requests stop at 15 pages, and a Google Cloud billing account with a card comes first.\n\n## Before you call either\n\n### Docling\n\n1. Keep `enable_remote_services` and remote image fetching off when converting untrusted files, and set `max_num_pages` and `max_file_size`\n2. Upgrade to v2.148.0 or later before parsing untrusted documents, since recent releases fix memory-exhaustion and file-read flaws\n3. Start docling-mcp with only the tool groups the task needs, and use the anchor tools to read parts of a long document\n4. Treat converted text as untrusted input, never as instructions\n5. Set DOCLING_SERVE_API_KEY before exposing docling-serve beyond localhost\n\n### Google Cloud Document AI\n\n1. Create a processor first (`processors.create` or the console), then POST to `https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process`\n2. Use the host that matches the processor's location, `us-documentai.googleapis.com` or `eu-documentai.googleapis.com`\n3. Set `fieldMask` (for example `text,entities`) and `imagelessMode` to keep page images and token geometry out of the response\n4. Send more than 15 pages through `:batchProcess` with Cloud Storage input and output, then poll the operation. Jobs unfinished after 24 hours are cancelled\n5. Grant the service account `roles/documentai.apiUser` only and send its token in the `Authorization` header, never as `access_token` in the URL. Failed requests (4xx or 5xx) are not billed\n6. Treat extracted text as untrusted input\n\n## Questions\n\n### Which is better for AI agents, Docling or Google Cloud Document AI?\n\nGoogle Cloud Document AI scores 72.2 (BB) on agent readiness against Docling's 64.3 (B), and leads in 4 of 7 scored categories. Docling leads on agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.\n\n### Can an agent call Docling and Google Cloud Document AI without installing anything?\n\nDocling runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Google Cloud Document AI.\n\n### Are Docling and Google Cloud Document AI open source?\n\nDocling is open source (MIT). No open-source release is listed for Google Cloud Document AI.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"docling\", \"b\": \"google-cloud-document-ai\"}`. From a terminal: `anchor compare docling google-cloud-document-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/docling.json and https://www.anchorterminal.com/api/v1/tools/google-cloud-document-ai.json\n\n## Other comparisons with Docling or Google Cloud Document AI\n\n- [Adobe PDF Services / PDF Extract API vs Docling](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-docling.md)\n- [Adobe PDF Services / PDF Extract API vs Google Cloud Document AI](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-google-cloud-document-ai.md)\n- [Amazon Textract vs Docling](https://www.anchorterminal.com/compare/amazon-textract-vs-docling.md)\n- [Amazon Textract vs Google Cloud Document AI](https://www.anchorterminal.com/compare/amazon-textract-vs-google-cloud-document-ai.md)\n- [Azure Document Intelligence vs Docling](https://www.anchorterminal.com/compare/azure-document-intelligence-vs-docling.md)\n- [Azure Document Intelligence vs Google Cloud Document AI](https://www.anchorterminal.com/compare/azure-document-intelligence-vs-google-cloud-document-ai.md)\n- [Datalab vs Docling](https://www.anchorterminal.com/compare/datalab-vs-docling.md)\n- [Datalab vs Google Cloud Document AI](https://www.anchorterminal.com/compare/datalab-vs-google-cloud-document-ai.md)\n- [Docling vs Extend API + MCP](https://www.anchorterminal.com/compare/docling-vs-extend.md)\n- [Docling vs LandingAI Agentic Document Extraction](https://www.anchorterminal.com/compare/docling-vs-landingai-agentic-document-extraction.md)\n- [Docling vs LlamaParse API + MCP](https://www.anchorterminal.com/compare/docling-vs-llamaparse.md)\n- [Docling vs Mistral OCR API](https://www.anchorterminal.com/compare/docling-vs-mistral-ocr.md)\n- [Docling vs Nanonets API + MCP](https://www.anchorterminal.com/compare/docling-vs-nanonets.md)\n- [Docling vs OpenDocRouter](https://www.anchorterminal.com/compare/docling-vs-opendocrouter.md)\n- [Docling vs Reducto API + MCP](https://www.anchorterminal.com/compare/docling-vs-reducto.md)\n- [Docling vs Unstructured API + MCP](https://www.anchorterminal.com/compare/docling-vs-unstructured.md)\n- [Extend API + MCP vs Google Cloud Document AI](https://www.anchorterminal.com/compare/extend-vs-google-cloud-document-ai.md)\n- [Google Cloud Document AI vs LandingAI Agentic Document Extraction](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-landingai-agentic-document-extraction.md)\n- [Google Cloud Document AI vs LlamaParse API + MCP](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-llamaparse.md)\n- [Google Cloud Document AI vs Mistral OCR API](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mistral-ocr.md)\n- [Google Cloud Document AI vs Nanonets API + MCP](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-nanonets.md)\n- [Google Cloud Document AI vs OpenDocRouter](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-opendocrouter.md)\n- [Google Cloud Document AI vs Reducto API + MCP](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-reducto.md)\n- [Google Cloud Document AI vs Unstructured API + MCP](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-unstructured.md)\n- [Clairic vs Docling](https://www.anchorterminal.com/compare/cloudflare-clairic-vs-docling.md)\n- [Clairic vs Google Cloud Document AI](https://www.anchorterminal.com/compare/cloudflare-clairic-vs-google-cloud-document-ai.md)\n- [Docling vs Invofox](https://www.anchorterminal.com/compare/docling-vs-invofox.md)\n- [Google Cloud Document AI vs Invofox](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-invofox.md)\n- [Docling vs Mindee API](https://www.anchorterminal.com/compare/docling-vs-mindee.md)\n- [Docling vs Veryfi API + MCP](https://www.anchorterminal.com/compare/docling-vs-veryfi.md)\n- [Google Cloud Document AI vs Mindee API](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mindee.md)\n- [Google Cloud Document AI vs Veryfi API + MCP](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-veryfi.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Docling vs Google Cloud Document AI", "url": "" } ], "description": "Google Cloud Document AI scores 72.2 (BB) to Docling's 64.3 (B) for document parsing. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Docling B 64.3", "Google Cloud Document AI BB 72.2", "scores" ], "h1": "Docling vs Google Cloud Document AI", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/docling-vs-google-cloud-document-ai", "published": "2026-10-01", "section": "tools", "title": "Docling vs Google Cloud Document AI for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai" }, "tokens": { "markdown": 5300, "slim": 3030 }, "version": 1 }