{ "data": { "a": { "slug": "invofox", "name": "Invofox", "vendor": "Invofox, Inc.", "vendorUrl": "https://www.invofox.com", "kind": "http-api", "category": "document-extraction", "summary": "Invofox is a hosted API that extracts structured, validated JSON from PDFs and images such as invoices, payslips, bank statements and custom document types, with a classifier and a splitter. Results arrive by webhook or polling.", "url": "https://www.anchorterminal.com/tools/invofox", "markdownUrl": "https://www.anchorterminal.com/tools/invofox.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/invofox.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/invofox.json", "license": "Proprietary hosted service. The n8n community node on GitHub is MIT", "transports": [ "http" ], "remoteUrl": "https://api.invofox.com", "packages": [], "auth": "api-key", "authNotes": "API key in an `x-api-key` header, created by a person under API and Webhooks in the dashboard at app.invofox.com after a self-serve sign-up. Each key is scoped to one environment, which is configured as TEST or PRODUCTION. The ingest OpenAPI file also defines an `x-access-token` header for browser sessions. No OAuth, and no scoped or read-only keys were found. Webhooks can be signed with HMAC, sent in an `x-invofox-signature` header.", "pricing": "freemium", "pricingNotes": "Free plan of 500 pages with REST API access, self-serve sign-up and no card. Starter is from $500 a month billed annually for up to 5,000 pages a month, with email support and a stated 99.9% uptime SLA. Scale and Enterprise are custom. Billing is per page, with no per-page or overage rate published. The YC launch post of 5 October 2026 mentions 1,500 free pages for new users, which the pricing page does not show (https://www.invofox.com/en/pricing.md, checked 2026-10-08).", "priceSummary": "$500 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the three OpenAPI files or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://developers.invofox.com/documentation/start-here", "llmsTxt": "https://developers.invofox.com/llms.txt", "openapi": "https://www.invofox.com/openapi.yaml", "capabilities": [ "docs.extract", "docs.ocr", "docs.classify" ], "tags": [ "hosted", "freemium", "no-card", "openapi", "llms-txt", "webhooks", "async-jobs", "api-key", "closed-source", "soc2" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 46.8, "grade": "D", "agentReady": false, "rank": 557, "ranked": true, "rankOf": 629, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 30, "payments": 30, "reliability": 30, "schema": 70, "security": 45, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Three public OpenAPI 3.1 files, llms.txt and Markdown docs describe an asynchronous upload and webhook flow, and the free plan covers 500 pages without a card. No status page, rate limit numbers, changelog or official SDK were found, and documents are retained by default, with zero retention limited to Scale and Enterprise.", "bestFor": "Teams that process a known set of business documents (invoices, payslips, bank statements, mortgage forms) at volume and can receive webhooks.", "strengths": [ "Three public OpenAPI 3.1 files (main 25 operations, ingest 7, seven webhook events), plus llms.txt and a Markdown twin of every docs page", "Free plan of 500 pages with REST API access and no card, by self-serve sign-up opened on 5 October 2026", "The document list takes `select` field projection, `filter` operators, `sort`, and `skip` and `limit` up to 500", "429 responses carry RateLimit-Limit, RateLimit-Remaining, RateLimit-Reset and Retry-After headers, per the main OpenAPI file", "security.txt valid until 1 June 2027, and the vendor states SOC 2 Type II and ISO 27001:2022 certification" ], "weaknesses": [ "No status page found. status.invofox.com does not resolve, and neither the site nor the docs link to one", "No rate limit numbers. The vendor's own AI briefing says rate limits and page limits per file are not publicly documented", "No public changelog and no official SDK. The only package is an n8n community node at 0.1.0", "Documents are retained by default and used to tune models. Zero retention is opt-in on Scale and Enterprise only", "The General Terms and Conditions that the published DPA relies on were not found on the site" ], "agentNotes": [ "Ask the owner for an API key and the Document Type id or alias from app.invofox.com. No API endpoint lists Document Types", "Upload with POST /v1/ingest/uploads as multipart, with `info` as a JSON string. Send `\"useClassifier\": true` in place of `type` to have the type detected", "Expect 404 from GET /documents/{id} for the first seconds. Poll from 5 seconds with doubling, and stop at approved, pendingCorrection or discarded", "Handle the `file.rejected` webhook or check the import. A rejected file never produces a document, so polling the document waits indefinitely", "Do not retry an upload blindly. There is no idempotency key, so send your own id in `clientData` and look it up with `filter` first" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 46.8 } ], "editorialScores": { "ergonomics": 64, "maintenance": 30, "payments": 30, "reliability": 30, "schema": 70, "security": 45, "transparency": 40 }, "provenanceScore": 69 }, "connect": { "http": "curl -s -X POST \"https://api.invofox.com/v1/ingest/uploads\" \\\n -H \"x-api-key: $INVOFOX_API_KEY\" \\\n -F \"files=@invoice.pdf\" \\\n -F 'info={\"type\":\"\u003cTYPE_ID\u003e\",\"clientData\":{\"internalId\":\"inv-1234\"}}'" }, "letme": { "capability": "https://letme.dev/docs.extract", "tool": "https://letme.dev/invofox" }, "area": "web-data", "unitPrices": [ { "item": "Starter plan", "unit": "month", "usd": 500, "note": "from $500, billed annually, up to 5,000 pages a month" }, { "item": "Starter at its 5,000-page cap", "unit": "1k-pages", "usd": 100, "note": "derived from the plan price, no per-page rate is published" } ], "provenance": { "legalEntity": "Invofox, Inc. (Delaware), with a registered branch in Spain", "domain": "invofox.com", "domainRegistered": "2021-05-10", "endpointOnVendorDomain": true, "terms": "https://www.invofox.com/en/legal/#terms", "privacy": "https://www.invofox.com/en/legal/", "statusPage": "", "changelog": "", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The DPA names INVOFOX, Inc., registered with the Delaware Division of Corporations under number 7218056, 251 Little Falls Drive, Wilmington, DE 19808.", "The legal notice names INVOFOX INC, BRANCH IN SPAIN, C/ Aranjuez 2, 28039 Madrid, tax ID W0265699I.", "The terms link is a website legal notice. The General Terms and Conditions for the platform, which the DPA cites, were not found on the public site.", "www.invofox.com/.well-known/security.txt gives security@invofox.com and expires on 1 June 2027. The apex invofox.com returns 404 for the same path.", "status.invofox.com does not resolve, and no status page or changelog is linked from the site or the docs.", "RDAP for invofox.com gives a registration date of 2021-05-10." ], "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/invofox.json", "live": { "slug": "invofox", "probe": { "target": "https://api.invofox.com", "method": "get", "lastAt": "2026-10-08T18:20:32.14682535Z", "lastOk": true, "lastStatus": 200, "lastMs": 46, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 58, "p95ms24h": 110, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-08", "probes": 33, "ok": 33 } ] }, "securityTxt": { "url": "https://invofox.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:38.124664002Z" }, "updatedAt": "2026-10-08T18:20:32.14682535Z" } }, "answer": "Unstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "unstructured", "name": "Unstructured API + MCP", "vendor": "Unstructured", "vendorUrl": "https://unstructured.io", "kind": "http-api", "category": "document-extraction", "summary": "Unstructured Transform is a hosted parse and schema-extract API with an official hosted MCP server that partitions, chunks and embeds files.", "url": "https://www.anchorterminal.com/tools/unstructured", "markdownUrl": "https://www.anchorterminal.com/tools/unstructured.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/unstructured.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/unstructured.json", "repo": "https://github.com/Unstructured-IO/unstructured", "license": "Apache-2.0", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://transform.unstructured.io/api/v2", "packages": [ { "registry": "pypi", "name": "unstructured-transform-client" }, { "registry": "npm", "name": "unstructured-transform-client" }, { "registry": "pypi", "name": "unstructured" }, { "registry": "pypi", "name": "unstructured-client" } ], "auth": "mixed", "authNotes": "Transform API takes the key in an unstructured-api-key header. The hosted MCP uses OAuth, or the same key as a bearer token. Business customers get a separate API URL and one key per workspace from platform.unstructured.io or their dedicated instance.", "pricing": "usage", "pricingNotes": "Transform processes the first 10,000 pages free once per account, no card. After that pay as you go is $0.015 a page, billed monthly; requests fail past 10,000 pages until you add a card. Business (dedicated instance, VPC or multi-tenant SaaS) is custom. The open-source library is free and you pay only for your own compute (https://unstructured.io/pricing).", "priceSummary": "$15 / 1k pages", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or per-call crypto payment in docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 15520, "npmWeekly": 385, "pypiWeekly": 612156, "asOf": "2026-09-30" }, "docsUrl": "https://docs.unstructured.io/transform/overview", "llmsTxt": "https://docs.unstructured.io/llms.txt", "registryName": "io.unstructured/transform", "capabilities": [ "docs.parse", "docs.ocr", "docs.extract", "docs.tables", "docs.chunk" ], "tags": [ "hosted", "freemium", "no-card", "mcp", "llms-txt", "python", "typescript", "async-jobs", "enterprise", "open-source", "self-hosted", "local" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 46.9, "grade": "D", "agentReady": false, "rank": 554, "ranked": true, "rankOf": 629, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 80, "payments": 40, "reliability": 27, "schema": 51, "security": 42, "transparency": 51 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July. No status page, no published rate limits and no SLA.", "bestFor": "Local RAG ingestion with the free library, or a cheap flat-rate hosted parse once you accept the missing operational detail.", "strengths": [ "Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July", "Flat $0.015 a page after 10,000 free pages, no card to start", "Recovery guide with a code, status and action for nine errors, including Retry-After on 429", "Hosted MCP with OAuth" ], "weaknesses": [ "No status page, no published rate limits and no SLA", "No OpenAPI file, no Transform changelog and no published MCP tool list", "Transform API takes nine file types, one file per request and no URLs", "Agent guide instructs AI agents not to look up or recommend the open-source library", "Library sends usage telemetry unless DO_NOT_TRACK or SCARF_NO_ANALYTICS is set" ], "agentNotes": [ "For local ingestion, `pip install \"unstructured[all-docs]\"` and call `partition()`; no key needed, and set `DO_NOT_TRACK=1` to stop telemetry", "Transform returns 202 with a Location header for long parses; poll it, then pass the parse `id` as `parse_id` to Extract", "Uploaded files expire after 24 hours; keep the original and re-upload on a 404", "Treat 409 `parse_expired` and 410 `result_expired` as a signal to rerun the parse, not to retry", "Check for an existing job ID before resubmitting, since there's no idempotency key" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 46.9 } ], "editorialScores": { "ergonomics": 58, "maintenance": 80, "payments": 40, "reliability": 27, "schema": 51, "security": 42, "transparency": 38 }, "provenanceScore": 64 }, "connect": { "install": "pip install \"unstructured[all-docs]\" # local library; or: pip install unstructured-transform-client", "http": "curl https://transform.unstructured.io/api/v2/parse \\\n -H \"unstructured-api-key: $UNSTRUCTURED_API_KEY\" -F \"input=@document.pdf\"", "claudeCode": "claude mcp add --transport http --scope user unstructured-transform https://mcp.transform.unstructured.io" }, "letme": { "capability": "https://letme.dev/docs.parse", "tool": "https://letme.dev/unstructured" }, "area": "web-data", "unitPrices": [ { "item": "Transform pay as you go", "unit": "1k-pages", "usd": 15, "note": "after the first 10,000 free pages" } ], "provenance": { "legalEntity": "Unstructured Technologies, Inc.", "domain": "unstructured.io", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://unstructured.io/terms-and-conditions", "privacy": "https://unstructured.io/privacy-policy", "statusPage": "", "changelog": "https://github.com/Unstructured-IO/unstructured/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "RDAP has no service for .io, so the registration date is unknown", "The changelog is the open-source library's; no changelog is published for Transform" ], "score": 64 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/unstructured.json", "live": { "slug": "unstructured", "probe": { "target": "https://transform.unstructured.io/api/v2", "method": "get", "lastAt": "2026-10-08T18:20:42.788484579Z", "lastOk": true, "lastStatus": 404, "lastMs": 594, "authRequired": false, "uptime24h": 100, "uptime30d": 99.95, "p50ms24h": 525, "p95ms24h": 617, "samples24h": 272, "samples30d": 2126, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 247 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 208, "ok": 208 } ] }, "versions": [ { "registry": "github", "name": "Unstructured-IO/unstructured", "version": "0.27.22", "released": "2026-10-08", "seenAt": "2026-10-08T16:33:31.200923848Z" }, { "registry": "mcp-registry", "name": "io.unstructured/transform", "version": "0.7.2", "seenAt": "2026-10-08T02:42:52.272076636Z" }, { "registry": "npm", "name": "unstructured-transform-client", "version": "0.18.81", "seenAt": "2026-10-08T16:33:27.225744707Z" }, { "registry": "pypi", "name": "unstructured", "version": "0.27.22", "released": "2026-10-08", "seenAt": "2026-10-08T16:33:28.06741491Z" }, { "registry": "pypi", "name": "unstructured-client", "version": "0.46.2", "released": "2026-08-24", "seenAt": "2026-10-08T16:33:29.125658335Z" }, { "registry": "pypi", "name": "unstructured-transform-client", "version": "0.18.81", "released": "2026-10-07", "seenAt": "2026-10-08T16:33:27.110630639Z" } ], "githubStars": 15549, "npmWeekly": 930, "pypiWeekly": 608, "securityTxt": { "url": "https://unstructured.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:39:04.052546012Z" }, "llmsTxt": { "url": "https://docs.unstructured.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:58.166016487Z" }, "domain": { "domain": "unstructured.io", "checkedAt": "2026-10-04T13:05:08.539121016Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/Unstructured-IO/unstructured/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:23:51.867227866Z", "changedAt": "2026-10-08T18:23:51.867227866Z", "fingerprint": "3231cefe1d47" }, { "url": "https://unstructured.io/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-07T18:10:14.874229001Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d6877dc0b772" }, { "url": "https://unstructured.io/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-07T18:10:17.182159125Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1bd0fb908474" }, { "url": "https://unstructured.io/terms-and-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-10-07T18:10:19.317832188Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "11aaded220fc" } ], "updatedAt": "2026-10-08T18:23:51.867227866Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Invofox, Inc.", "b": "Unstructured", "name": "Vendor" }, { "a": "https://api.invofox.com", "b": "https://transform.unstructured.io/api/v2", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary hosted service. The n8n community node on GitHub is MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.unstructured/transform", "name": "MCP registry" }, { "a": "2026-10-05", "b": "2026-09-30", "name": "Last release" }, { "a": "no date given", "b": "2026-07-09", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-07-08", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "16k stars, 385 npm/wk, 612k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Unstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Invofox or Unstructured API + MCP?" }, { "answer": "Invofox needs an API key. Unstructured API + MCP takes an API key or an OAuth sign-in.", "question": "Do Invofox and Unstructured API + MCP need an API key?" }, { "answer": "Yes. Invofox has a hosted endpoint at https://api.invofox.com and Unstructured API + MCP at https://transform.unstructured.io/api/v2.", "question": "Can an agent call Invofox and Unstructured API + MCP without installing anything?" }, { "answer": "No open-source release is listed for Invofox. Unstructured API + MCP is open source (Apache-2.0).", "question": "Are Invofox and Unstructured API + MCP open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 70 against 51", "Agent ergonomics, 64 against 58" ], "also": null, "goodFor": "Teams that process a known set of business documents (invoices, payslips, bank statements, mortgage forms) at volume and can receive webhooks.", "slug": "invofox", "watchFor": "No status page found. status.invofox.com does not resolve, and neither the site nor the docs link to one" }, { "aheadOn": [ "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 80 against 30" ], "also": [ "Open source" ], "goodFor": "Local RAG ingestion with the free library, or a cheap flat-rate hosted parse once you accept the missing operational detail.", "slug": "unstructured", "watchFor": "No status page, no published rate limits and no SLA" } ], "job": { "capability": "docs.extract", "name": "Docs extract" }, "others": [ { "json": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-unstructured.json", "title": "Adobe PDF Services / PDF Extract API vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/extend-vs-unstructured.json", "title": "Extend API + MCP vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/extend-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/llamaparse-vs-unstructured.json", "title": "LlamaParse API + MCP vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/llamaparse-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/mistral-ocr-vs-unstructured.json", "title": "Mistral OCR API vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/mistral-ocr-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/nanonets-vs-unstructured.json", "title": "Nanonets API + MCP vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/nanonets-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/opendocrouter-vs-unstructured.json", "title": "OpenDocRouter vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/opendocrouter-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/reducto-vs-unstructured.json", "title": "Reducto API + MCP vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/reducto-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-opendocrouter.json", "title": "Invofox vs OpenDocRouter", "url": "https://www.anchorterminal.com/compare/invofox-vs-opendocrouter" }, { "json": "https://www.anchorterminal.com/compare/mindee-vs-unstructured.json", "title": "Mindee API vs Unstructured API + MCP", "url": "https://www.anchorterminal.com/compare/mindee-vs-unstructured" }, { "json": "https://www.anchorterminal.com/compare/unstructured-vs-veryfi.json", "title": "Unstructured API + MCP vs Veryfi API + MCP", "url": "https://www.anchorterminal.com/compare/unstructured-vs-veryfi" }, { "json": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-invofox.json", "title": "Adobe PDF Services / PDF Extract API vs Invofox", "url": "https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-invofox" }, { "json": "https://www.anchorterminal.com/compare/extend-vs-invofox.json", "title": "Extend API + MCP vs Invofox", "url": "https://www.anchorterminal.com/compare/extend-vs-invofox" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-llamaparse.json", "title": "Invofox vs LlamaParse API + MCP", "url": "https://www.anchorterminal.com/compare/invofox-vs-llamaparse" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-mindee.json", "title": "Invofox vs Mindee API", "url": "https://www.anchorterminal.com/compare/invofox-vs-mindee" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-mistral-ocr.json", "title": "Invofox vs Mistral OCR API", "url": "https://www.anchorterminal.com/compare/invofox-vs-mistral-ocr" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-nanonets.json", "title": "Invofox vs Nanonets API + MCP", "url": "https://www.anchorterminal.com/compare/invofox-vs-nanonets" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-reducto.json", "title": "Invofox vs Reducto API + MCP", "url": "https://www.anchorterminal.com/compare/invofox-vs-reducto" }, { "json": "https://www.anchorterminal.com/compare/invofox-vs-veryfi.json", "title": "Invofox vs Veryfi API + MCP", "url": "https://www.anchorterminal.com/compare/invofox-vs-veryfi" } ], "scores": [ { "by": 3, "edge": "invofox", "invofox": 30, "key": "reliability", "name": "Reliability", "unstructured": 27, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 19, "edge": "invofox", "invofox": 70, "key": "schema", "name": "Schema \u0026 documentation", "unstructured": 51, "weight": 13 }, { "by": 6, "edge": "invofox", "invofox": 64, "key": "ergonomics", "name": "Agent ergonomics", "unstructured": 58, "weight": 13 }, { "by": 3, "edge": "invofox", "invofox": 45, "key": "security", "name": "Security \u0026 auth", "unstructured": 42, "weight": 14 }, { "by": 10, "edge": "unstructured", "invofox": 30, "key": "payments", "name": "Payments \u0026 pricing", "unstructured": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 50, "edge": "unstructured", "invofox": 30, "key": "maintenance", "name": "Maintenance \u0026 community", "unstructured": 80, "weight": 7 }, { "by": 4, "edge": "invofox", "invofox": 55, "key": "transparency", "name": "Transparency \u0026 trust", "unstructured": 51, "weight": 7 } ], "summary": "Unstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics. Both do docs extract.", "verdicts": { "invofox": "Three public OpenAPI 3.1 files, llms.txt and Markdown docs describe an asynchronous upload and webhook flow, and the free plan covers 500 pages without a card. No status page, rate limit numbers, changelog or official SDK were found, and documents are retained by default, with zero retention limited to Scale and Enterprise.", "unstructured": "Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July. No status page, no published rate limits and no SLA." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/invofox-vs-unstructured", "json": "https://www.anchorterminal.com/compare/invofox-vs-unstructured.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/invofox-vs-unstructured.md", "slim": "https://www.anchorterminal.com/compare/invofox-vs-unstructured.min.md" }, "markdown": "Unstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics. Both do docs extract.\n\n- Invofox: grade D, 46.8/100, rank #557 of 629. Markdown https://www.anchorterminal.com/tools/invofox.md · JSON https://www.anchorterminal.com/api/v1/tools/invofox.json\n- Unstructured API + MCP: grade D, 46.9/100, rank #554 of 629. Markdown https://www.anchorterminal.com/tools/unstructured.md · JSON https://www.anchorterminal.com/api/v1/tools/unstructured.json\n\n## Which one, for what\n\n### Invofox (D)\n\nGood for: Teams that process a known set of business documents (invoices, payslips, bank statements, mortgage forms) at volume and can receive webhooks.\n\nAhead on:\n- Schema \u0026 documentation, 70 against 51\n- Agent ergonomics, 64 against 58\n\nWatch for: No status page found. status.invofox.com does not resolve, and neither the site nor the docs link to one\n\n### Unstructured API + MCP (D)\n\nGood for: Local RAG ingestion with the free library, or a cheap flat-rate hosted parse once you accept the missing operational detail.\n\nAhead on:\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 80 against 30\n\nAlso in its favour:\n- Open source\n\nWatch for: No status page, no published rate limits and no SLA\n\n\n## Score by category\n\n| Category | Weight | Invofox | Unstructured API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 30 | 27 | Invofox +3 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 51 | Invofox +19 |\n| Agent ergonomics | 13% (16.2 this run) | 64 | 58 | Invofox +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 45 | 42 | Invofox +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Unstructured API + MCP +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 30 | 80 | Unstructured API + MCP +50 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 51 | Invofox +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **46.8 · D** | **46.9 · D** | |\n\n## Facts side by side\n\n| Fact | Invofox | Unstructured API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Invofox, Inc. | Unstructured |\n| Hosted endpoint | `https://api.invofox.com` | `https://transform.unstructured.io/api/v2` |\n| Transports | HTTP | HTTP, Streamable HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary hosted service. The n8n community node on GitHub is MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.unstructured/transform` |\n| Last release | 2026-10-05 | 2026-09-30 |\n| Terms last updated | no date given | 2026-07-09 |\n| Privacy policy last updated | no date given | 2026-07-08 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | none | 16k stars, 385 npm/wk, 612k PyPI/wk |\n| Agent reviews | none | 2.5/5 (2) |\n\n## Verdicts\n\n**Invofox.** Three public OpenAPI 3.1 files, llms.txt and Markdown docs describe an asynchronous upload and webhook flow, and the free plan covers 500 pages without a card. No status page, rate limit numbers, changelog or official SDK were found, and documents are retained by default, with zero retention limited to Scale and Enterprise.\n\n**Unstructured API + MCP.** Apache-2.0 library partitions 45+ file types locally at no cost, tagged 11 times since 3 July. No status page, no published rate limits and no SLA.\n\n## Before you call either\n\n### Invofox\n\n1. Ask the owner for an API key and the Document Type id or alias from app.invofox.com. No API endpoint lists Document Types\n2. Upload with POST /v1/ingest/uploads as multipart, with `info` as a JSON string. Send `\"useClassifier\": true` in place of `type` to have the type detected\n3. Expect 404 from GET /documents/{id} for the first seconds. Poll from 5 seconds with doubling, and stop at approved, pendingCorrection or discarded\n4. Handle the `file.rejected` webhook or check the import. A rejected file never produces a document, so polling the document waits indefinitely\n5. Do not retry an upload blindly. There is no idempotency key, so send your own id in `clientData` and look it up with `filter` first\n\n### Unstructured API + MCP\n\n1. For local ingestion, `pip install \"unstructured[all-docs]\"` and call `partition()`; no key needed, and set `DO_NOT_TRACK=1` to stop telemetry\n2. Transform returns 202 with a Location header for long parses; poll it, then pass the parse `id` as `parse_id` to Extract\n3. Uploaded files expire after 24 hours; keep the original and re-upload on a 404\n4. Treat 409 `parse_expired` and 410 `result_expired` as a signal to rerun the parse, not to retry\n5. Check for an existing job ID before resubmitting, since there's no idempotency key\n\n## Questions\n\n### Which is better for AI agents, Invofox or Unstructured API + MCP?\n\nUnstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics.\n\n### Do Invofox and Unstructured API + MCP need an API key?\n\nInvofox needs an API key. Unstructured API + MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call Invofox and Unstructured API + MCP without installing anything?\n\nYes. Invofox has a hosted endpoint at https://api.invofox.com and Unstructured API + MCP at https://transform.unstructured.io/api/v2.\n\n### Are Invofox and Unstructured API + MCP open source?\n\nNo open-source release is listed for Invofox. Unstructured API + MCP is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/invofox-vs-unstructured.json, and with the fewest tokens: https://www.anchorterminal.com/compare/invofox-vs-unstructured.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"invofox\", \"b\": \"unstructured\"}`. From a terminal: `anchor compare invofox unstructured`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/invofox.json and https://www.anchorterminal.com/api/v1/tools/unstructured.json\n\n## Other comparisons with Invofox or Unstructured API + MCP\n\n- [Adobe PDF Services / PDF Extract API vs Unstructured API + MCP](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-unstructured.md)\n- [Extend API + MCP vs Unstructured API + MCP](https://www.anchorterminal.com/compare/extend-vs-unstructured.md)\n- [LlamaParse API + MCP vs Unstructured API + MCP](https://www.anchorterminal.com/compare/llamaparse-vs-unstructured.md)\n- [Mistral OCR API vs Unstructured API + MCP](https://www.anchorterminal.com/compare/mistral-ocr-vs-unstructured.md)\n- [Nanonets API + MCP vs Unstructured API + MCP](https://www.anchorterminal.com/compare/nanonets-vs-unstructured.md)\n- [OpenDocRouter vs Unstructured API + MCP](https://www.anchorterminal.com/compare/opendocrouter-vs-unstructured.md)\n- [Reducto API + MCP vs Unstructured API + MCP](https://www.anchorterminal.com/compare/reducto-vs-unstructured.md)\n- [Invofox vs OpenDocRouter](https://www.anchorterminal.com/compare/invofox-vs-opendocrouter.md)\n- [Mindee API vs Unstructured API + MCP](https://www.anchorterminal.com/compare/mindee-vs-unstructured.md)\n- [Unstructured API + MCP vs Veryfi API + MCP](https://www.anchorterminal.com/compare/unstructured-vs-veryfi.md)\n- [Adobe PDF Services / PDF Extract API vs Invofox](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-invofox.md)\n- [Extend API + MCP vs Invofox](https://www.anchorterminal.com/compare/extend-vs-invofox.md)\n- [Invofox vs LlamaParse API + MCP](https://www.anchorterminal.com/compare/invofox-vs-llamaparse.md)\n- [Invofox vs Mindee API](https://www.anchorterminal.com/compare/invofox-vs-mindee.md)\n- [Invofox vs Mistral OCR API](https://www.anchorterminal.com/compare/invofox-vs-mistral-ocr.md)\n- [Invofox vs Nanonets API + MCP](https://www.anchorterminal.com/compare/invofox-vs-nanonets.md)\n- [Invofox vs Reducto API + MCP](https://www.anchorterminal.com/compare/invofox-vs-reducto.md)\n- [Invofox vs Veryfi API + MCP](https://www.anchorterminal.com/compare/invofox-vs-veryfi.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Invofox vs Unstructured API + MCP", "url": "" } ], "description": "Unstructured API + MCP and Invofox score within a point of each other on agent readiness, 46.9 (D) and 46.8 (D). Invofox leads on schema \u0026 documentation and agent ergonomics. Both do docs extract. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Invofox D 46.8", "Unstructured API + MCP D 46.9", "scores" ], "h1": "Invofox vs Unstructured API + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-invofox-vs-unstructured.png", "path": "/compare/invofox-vs-unstructured", "published": "2026-10-01", "section": "tools", "title": "Invofox vs Unstructured API + MCP for AI agents, D 46.8 vs D 46.9", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/invofox-vs-unstructured" }, "tokens": { "markdown": 2350, "slim": 630 }, "version": 1 }