{
  "name": "Diffbot",
  "slug": "diffbot",
  "website_url": "https://www.diffbot.com",
  "vendor_description": "Web Data for your AI",
  "categories": [
    "scraping"
  ],
  "summary": "Diffbot turns the web into structured data for AI, with products for market intelligence, news monitoring, machine learning, and e-commerce, including a knowledge graph. The REST API offers API-key auth, webhooks, eleven SDKs, and an official MCP server. Pricing is published and self-serve on a hybrid model from $299/month, with 10,000 credits free each month. It is GDPR compliant. Used by Snapchat, AstraZeneca, Klarna, and Indeed.",
  "capabilities": {
    "supported_actions": [
      "extract_analyze",
      "extract_article",
      "extract_discussion",
      "extract_event",
      "extract_image",
      "extract_job",
      "extract_list",
      "extract_product",
      "extract_video",
      "enhance_get",
      "enhance_post",
      "bulk_enhance",
      "knowledge_graph_search",
      "knowledge_graph_combine",
      "create_crawl",
      "manage_crawl_job",
      "retrieve_crawl_job_data",
      "search_crawl_job_data",
      "create_bulkjob",
      "download_bulkjob_results",
      "poll_bulkjob_status",
      "list_bulkjobs_for_token",
      "download_bulkjob_coverage_report",
      "delete_bulkjob",
      "download_single_bulkjob_result",
      "stop_bulkjob",
      "create_or_update_custom_api",
      "custom_api_rulesets",
      "extract_with_custom_api",
      "delete_custom_api",
      "retrieve_custom_apis",
      "extract_content_not_available_online",
      "extract_custom_headers",
      "extract_custom_javascript"
    ],
    "supported_regions": [],
    "supported_languages": [],
    "input_types": [
      "URL",
      "HTML markup",
      "plain text"
    ],
    "output_types": [
      "JSON"
    ],
    "webhooks_supported": true,
    "sandbox_available": false,
    "sdk_languages": [
      "Python",
      "Go",
      "Ruby",
      "Java",
      "C#",
      "Node.js",
      "PHP",
      "C",
      "Scala",
      "Clojure",
      "Rust"
    ],
    "mcp_server_available": true
  },
  "integration": {
    "api_style": "rest",
    "base_url": "https://api.diffbot.com/v3",
    "api_version": "v3",
    "versioning_scheme": "url",
    "stability": "ga",
    "deprecation_policy_url": null,
    "auth_methods": [
      "api_key"
    ],
    "auth_docs_url": "https://docs.diffbot.com/reference/authentication",
    "idempotency_supported": false,
    "error_format": "vendor-specific",
    "webhook_signing": null,
    "webhook_events_url": null,
    "rate_limit_requests": 5,
    "rate_limit_window": "minute",
    "sdk_packages": [
      {
        "stars": 124,
        "package": null,
        "archived": false,
        "language": "Python",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-python",
        "last_pushed_at": "2026-06-03T22:20:11Z"
      },
      {
        "stars": 10,
        "package": null,
        "archived": false,
        "language": "Go",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-go-client",
        "last_pushed_at": "2025-06-19T19:47:21Z"
      },
      {
        "stars": 17,
        "package": "diffbot-ruby-client (rubygems)",
        "archived": false,
        "language": "Ruby",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-ruby-client",
        "last_pushed_at": "2024-05-27T22:40:37Z"
      },
      {
        "stars": 9,
        "package": null,
        "archived": false,
        "language": "Java",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-java-client",
        "last_pushed_at": "2019-03-05T06:27:54Z"
      },
      {
        "stars": 10,
        "package": null,
        "archived": false,
        "language": "C#",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-csharp-client",
        "last_pushed_at": "2022-06-22T19:04:58Z"
      },
      {
        "stars": 23,
        "package": null,
        "archived": false,
        "language": "Node.js",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-js-client",
        "last_pushed_at": "2017-05-17T16:32:24Z"
      },
      {
        "stars": 9,
        "package": null,
        "archived": false,
        "language": "PHP",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-php-client",
        "last_pushed_at": "2016-03-04T07:52:13Z"
      },
      {
        "stars": 0,
        "package": null,
        "archived": false,
        "language": "C",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-c-client",
        "last_pushed_at": "2019-03-05T06:39:40Z"
      },
      {
        "stars": 4,
        "package": null,
        "archived": false,
        "language": "Scala",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-scala-client",
        "last_pushed_at": "2019-03-05T06:37:58Z"
      },
      {
        "stars": 6,
        "package": null,
        "archived": false,
        "language": "Clojure",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-clojure-client",
        "last_pushed_at": "2019-03-05T06:34:18Z"
      },
      {
        "stars": 4,
        "package": null,
        "archived": false,
        "language": "Rust",
        "official": true,
        "repo_url": "https://github.com/diffbot/diffbot-rust-client",
        "last_pushed_at": "2017-07-06T18:42:57Z"
      }
    ],
    "mcp_url": "https://github.com/diffbot/diffbot-mcp",
    "quickstart_url": null
  },
  "pricing": {
    "pricing_model": "hybrid",
    "has_published_pricing": true,
    "starting_price_usd": "299.0000",
    "price_basis": "month",
    "free_tier_available": true,
    "free_tier_limit": "10,000 credits/month",
    "free_tier_details": "Free forever. 10,000 credits/month, 5 calls/min. No credit card required.",
    "minimum_commitment": "No contracts required",
    "self_serve_signup": true,
    "requires_sales_call": false,
    "requires_verification": false,
    "enterprise_plan_available": true,
    "price_points": [
      {
        "plan": "Free",
        "item": "10,000 credits",
        "amount_usd": "0.0000",
        "amount_percent": null,
        "per": "month",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      },
      {
        "plan": "Free",
        "item": "credit",
        "amount_usd": "0.0000",
        "amount_percent": null,
        "per": "credit",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      },
      {
        "plan": "Startup",
        "item": "250,000 credits",
        "amount_usd": "299.0000",
        "amount_percent": null,
        "per": "month",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      },
      {
        "plan": "Startup",
        "item": "credit",
        "amount_usd": "0.0010",
        "amount_percent": null,
        "per": "credit",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      },
      {
        "plan": "Plus",
        "item": "1,000,000 credits",
        "amount_usd": "899.0000",
        "amount_percent": null,
        "per": "month",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      },
      {
        "plan": "Plus",
        "item": "credit",
        "amount_usd": "0.0009",
        "amount_percent": null,
        "per": "credit",
        "currency": "USD",
        "source_url": "https://www.diffbot.com/pricing/"
      }
    ]
  },
  "compliance": {
    "soc2": null,
    "hipaa": null,
    "gdpr": true,
    "iso_27001": null,
    "pci_dss": null,
    "sla_published": false,
    "sla_url": null,
    "data_retention_policy_url": "https://www.diffbot.com/company/privacy/",
    "documented_rate_limits": "Free: 5 Calls Per Minute; Startup: 5 Calls Per Second; Plus: 25 Calls Per Second; Enterprise: 25+ Calls Per Second",
    "known_restrictions": [
      "sublicense, resell, rent, lease, transfer, assign, time share, or otherwise commercially exploit or make the Service available to any third party",
      "reverse engineer, decompile or disassemble any portion of the Service",
      "bypass any robot exclusion headers or other measures we take to restrict access to the Site or Service",
      "use the API or the Data in any manner that violates the rights of any person, including but not limited to intellectual property rights, rights of privacy or rights of publicity",
      "IN NO EVENT WILL COMPANY'S LIABILITY TO YOU EXCEED $10"
    ]
  },
  "developer": {
    "docs_url": "https://docs.diffbot.com",
    "api_reference_url": null,
    "openapi_spec_url": null,
    "postman_collection_url": null,
    "changelog_url": null,
    "status_page_url": "https://status.diffbot.com",
    "llms_txt_url": null,
    "markdown_docs_url": null
  },
  "adoption": {
    "launched_at": null,
    "ga_date": null,
    "github_stars": null,
    "github_stars_at": null,
    "notable_customers": [
      "Snapchat",
      "AstraZeneca",
      "Klarna",
      "Indeed",
      "NBC",
      "BuzzFeed",
      "Notion",
      "Quora",
      "SemRush",
      "Sequoia Capital",
      "Andreessen Horowitz",
      "Opera",
      "Doximity",
      "FINRA",
      "Factset",
      "Meltwater",
      "SmartNews",
      "Vice",
      "InMoment",
      "Instapaper"
    ]
  },
  "scores": {
    "agent_friendliness": null,
    "pricing_transparency": null,
    "setup_speed": null,
    "docs_quality": null,
    "procurement_friction": null,
    "trust_readiness": null,
    "best_for": [],
    "avoid_if": []
  },
  "sources": [
    {
      "field": "input_types",
      "url": "https://docs.diffbot.com/reference/extract-analyze",
      "excerpt": "Automatically classify a page and extract data according to its type.",
      "confidence": "medium"
    },
    {
      "field": "input_types",
      "url": "https://docs.diffbot.com/reference/enhance",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "sandbox_available",
      "url": "https://docs.diffbot.com/reference/authentication",
      "excerpt": "All Diffbot APIs are authenticated via token.",
      "confidence": "medium"
    },
    {
      "field": "has_published_pricing",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo",
      "confidence": "high"
    },
    {
      "field": "requires_sales_call",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo",
      "confidence": "high"
    },
    {
      "field": "enterprise_plan_available",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "documented_rate_limits",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo each plan is subject to API rate limits.",
      "confidence": "high"
    },
    {
      "field": "vendor_description",
      "url": "https://www.diffbot.com/",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "output_types",
      "url": "https://github.com/diffbot/diffbot-rust-client",
      "excerpt": "It returns a Json",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-python",
      "excerpt": "Identify and extract the important parts of any web page in Python!",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-go-client",
      "excerpt": "This package implements a Diffbot client library.",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-ruby-client",
      "excerpt": "Official Diffbot Ruby API Client",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-rust-client",
      "excerpt": "This library allows you to access the Diffbot API from your rust application.",
      "confidence": "high"
    },
    {
      "field": "free_tier_details",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo each plan is subject to API rate limits.",
      "confidence": "high"
    },
    {
      "field": "name",
      "url": "https://www.diffbot.com/",
      "excerpt": "Transform the web into data. Diffbot automates web data extraction from any website using AI, computer vision, and machine learning.",
      "confidence": "high"
    },
    {
      "field": "sla_published",
      "url": "https://status.diffbot.com/622688",
      "excerpt": "Availability (uptime) over the past 24 hours. Red sections indicate downtime.",
      "confidence": "medium"
    },
    {
      "field": "webhooks_supported",
      "url": "https://blog.diffbot.com/crawlbot-updates-webhooks-and-preventing-duplicate-content/",
      "excerpt": "When starting a crawl, you can now supply a webhook URL to be notified when the crawl is complete.",
      "confidence": "high"
    },
    {
      "field": "free_tier_available",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo each plan is subject to API rate limits.",
      "confidence": "high"
    },
    {
      "field": "supported_regions",
      "url": "https://www.diffbot.com/",
      "excerpt": null,
      "confidence": "low"
    },
    {
      "field": "self_serve_signup",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Free $0/mo",
      "confidence": "high"
    },
    {
      "field": "gdpr",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "website_url",
      "url": "https://www.diffbot.com/",
      "excerpt": "Transform the web into data. Diffbot automates web data extraction from any website using AI, computer vision, and machine learning.",
      "confidence": "high"
    },
    {
      "field": "primary_use_cases",
      "url": "https://www.diffbot.com/",
      "excerpt": "Transform the web into data. Diffbot automates web data extraction from any website using AI, computer vision, and machine learning.",
      "confidence": "medium"
    },
    {
      "field": "primary_use_cases",
      "url": "https://www.diffbot.com/web-scraping/",
      "excerpt": "While Diffbot's Automatic Extraction APIs may sound technical, implementation through Crawlbot is actually beginner friendly.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/extract-analyze",
      "excerpt": "Automatically classify a page and extract data according to its type.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/event",
      "excerpt": "Automatically extracts dates, location and address information, images and event descriptions from event pages.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/retrieve-a-custom-api",
      "excerpt": "Get all the Custom APIs and their rules currently defined on your token.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/docs/introduction-to-custom-api",
      "excerpt": "Select \"Article\" under the \"API\" dropdown and paste the URL of blog post into the \"Test URL\" field. Then click \"Create\".",
      "confidence": "medium"
    },
    {
      "field": "categories",
      "url": "https://docs.diffbot.com/",
      "excerpt": "Diffbot builds AI models that read websites and structure them into facts. Our API reference has everything you need to start stringing web data in minutes.",
      "confidence": "high"
    },
    {
      "field": "supported_languages",
      "url": "https://docs.diffbot.com/",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "mcp_server_available",
      "url": "https://github.com/diffbot/diffbot-mcp",
      "excerpt": "A Diffbot MCP server with a variety of helpful web data handling tools for your agent or LLM pipeline.",
      "confidence": "high"
    },
    {
      "field": "pricing_model",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "documented_rate_limits",
      "url": "https://docs.diffbot.com/reference/rate-limits",
      "excerpt": "APIs to access a trillion connected facts across the web or extract them on demand.",
      "confidence": "high"
    },
    {
      "field": "output_types",
      "url": "https://docs.diffbot.com/reference/introduction-to-diffbot-apis",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot",
      "excerpt": "An open source search engine written in C/C++ for Linux on Intel/AMD.",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-js-client",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-csharp-client",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-java-client",
      "excerpt": "A java client for Diffbot's RESTful API",
      "confidence": "high"
    },
    {
      "field": "sdk_languages",
      "url": "https://github.com/diffbot/diffbot-r-client",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "free_tier_details",
      "url": "https://devtune.ai/verticals/web-data-infrastructure-for-ai/diffbot/pricing",
      "excerpt": "Free: $0/month, 10,000 credits, full API access, 5 calls/minute.",
      "confidence": "high"
    },
    {
      "field": "sla_published",
      "url": "https://status.diffbot.com/",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "iso_27001",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Diffbot utilizes only PCI-DSS compliant third-party payment processors to ensure the security of your personal information.",
      "confidence": "low"
    },
    {
      "field": "webhooks_supported",
      "url": "https://www.diffbot.com/solutions/news-monitoring/",
      "excerpt": "Webhook API to integrate alerts into your news application.",
      "confidence": "high"
    },
    {
      "field": "minimum_commitment",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "No contracts required.",
      "confidence": "high"
    },
    {
      "field": "known_restrictions",
      "url": "https://www.diffbot.com/company/terms/",
      "excerpt": "You agree that you will not: sublicense, resell, rent, lease, transfer, assign, time share, or otherwise commercially exploit or make the Service available to any third party",
      "confidence": "high"
    },
    {
      "field": "self_serve_signup",
      "url": "https://docs.diffbot.com/reference/authentication",
      "excerpt": "All Diffbot APIs are authenticated via token.",
      "confidence": "high"
    },
    {
      "field": "gdpr",
      "url": "http://aidoos.com/products/diffbot",
      "excerpt": "Is Diffbot GDPR and CCPA compliant? Yes, Diffbot includes built-in compliance controls for GDPR and CCPA.",
      "confidence": "high"
    },
    {
      "field": "fields_not_found",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Diffbot utilizes only PCI-DSS compliant third-party payment processors to ensure the security of your personal information.",
      "confidence": "medium"
    },
    {
      "field": "primary_use_cases",
      "url": "https://www.diffbot.com/solutions/news-monitoring/",
      "excerpt": "Build your own custom news feed, powered by the Diffbot Knowledge Graph.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/llms.txt",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/article",
      "excerpt": "Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages.",
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/enhance",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "supported_actions",
      "url": "https://docs.diffbot.com/reference/extract-content-not-available-online",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "categories",
      "url": "https://www.diffbot.com/",
      "excerpt": "Transform the web into data. Diffbot automates web data extraction from any website using AI, computer vision, and machine learning.",
      "confidence": "high"
    },
    {
      "field": "hipaa",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Diffbot utilizes only PCI-DSS compliant third-party payment processors to ensure the security of your personal information.",
      "confidence": "low"
    },
    {
      "field": "soc2",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Diffbot utilizes only PCI-DSS compliant third-party payment processors to ensure the security of your personal information.",
      "confidence": "low"
    },
    {
      "field": "pci_dss",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Diffbot utilizes only PCI-DSS compliant third-party payment processors to ensure the security of your personal information.",
      "confidence": "medium"
    },
    {
      "field": "pricing_model",
      "url": "https://devtune.ai/verticals/web-data-infrastructure-for-ai/diffbot/pricing",
      "excerpt": "Diffbot offers four tiers billed monthly with no contracts required. Free: $0/month, 10,000 credits, full API access, 5 calls/minute.",
      "confidence": "high"
    },
    {
      "field": "has_published_pricing",
      "url": "https://www.xpay.sh/saas-pricing/diffbot/",
      "excerpt": "Diffbot pricing starts at $0/mo for the Free plan; paid plans up to $899/mo. Billed monthly.",
      "confidence": "high"
    },
    {
      "field": "requires_sales_call",
      "url": "https://docs.diffbot.com/reference/authentication",
      "excerpt": "All Diffbot APIs are authenticated via token.",
      "confidence": "high"
    },
    {
      "field": "enterprise_plan_available",
      "url": "https://devtune.ai/verticals/web-data-infrastructure-for-ai/diffbot/pricing",
      "excerpt": "Diffbot offers four tiers billed monthly with no contracts required.",
      "confidence": "high"
    },
    {
      "field": "input_types",
      "url": "https://docs.diffbot.com/reference/extract-content-not-available-online",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "sandbox_available",
      "url": "https://docs.diffbot.com/",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "webhook_events_url",
      "url": "https://github.com/diffbot/Diffbot-Documentation/blob/master/source/includes_erb/_crawlbot_api.md.erb",
      "excerpt": null,
      "confidence": "high"
    },
    {
      "field": "base_url",
      "url": "https://docs.diffbot.com/reference/event",
      "excerpt": "Automatically extracts dates, location and address information, images and event descriptions from event pages.",
      "confidence": "high"
    },
    {
      "field": "free_tier_limit",
      "url": "http://prospeo.io/s/diffbot-pricing-reviews-pros-and-cons",
      "excerpt": "Free |$0 |10,000 |\\- |5 calls/mi",
      "confidence": "high"
    },
    {
      "field": "fields_not_found",
      "url": "https://pitchbook.com/profiles/company/54564-94",
      "excerpt": "When was Diffbot founded? Diffbot was founded in 2012.",
      "confidence": "high"
    },
    {
      "field": "rate_limit_window",
      "url": "http://prospeo.io/s/diffbot-pricing-reviews-pros-and-cons",
      "excerpt": "Free |$0 |10,000 |\\- |5 calls/mi",
      "confidence": "high"
    },
    {
      "field": "base_url",
      "url": "https://docs.diffbot.com/reference/article",
      "excerpt": "Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages.",
      "confidence": "high"
    },
    {
      "field": "free_tier_limit",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Plans starting at Free. No contracts required. Get Started for Free. No credit card required. Full API access. Free $0/mo Jumpstart hobby projects.",
      "confidence": "high"
    },
    {
      "field": "fields_not_found",
      "url": "https://docs.diffbot.com/changelog/enhance-api-updates",
      "excerpt": "API versions v1 and v2 are now deprecated and will be removed in future versions of the product. Please plan to migrate.",
      "confidence": "high"
    },
    {
      "field": "rate_limit_window",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Plans starting at Free. No contracts required. Get Started for Free. No credit card required. Full API access.",
      "confidence": "high"
    },
    {
      "field": "starting_price_usd",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Plans starting at Free. No contracts required. Get Started for Free. No credit card required.",
      "confidence": "high"
    },
    {
      "field": "versioning_scheme",
      "url": "https://docs.diffbot.com/reference/article",
      "excerpt": "Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages.",
      "confidence": "high"
    },
    {
      "field": "auth_docs_url",
      "url": "https://docs.diffbot.com/reference/authentication",
      "excerpt": "All Diffbot APIs are authenticated via token. Updated 7 months ago.",
      "confidence": "high"
    },
    {
      "field": "price_basis",
      "url": "https://www.xpay.sh/saas-pricing/diffbot/",
      "excerpt": "Diffbot pricing starts at $0/mo for the Free plan; paid plans up to $899/mo. Billed monthly.",
      "confidence": "high"
    },
    {
      "field": "requires_verification",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Data that is stored by us is kept on secure encrypted services, located in the US. Restricting staff access to personal data protected by",
      "confidence": "high"
    },
    {
      "field": "api_style",
      "url": "https://docs.diffbot.com/reference/event",
      "excerpt": "Automatically extracts dates, location and address information, images and event descriptions from event pages.",
      "confidence": "high"
    },
    {
      "field": "notable_customers",
      "url": "https://www.diffbot.com/customer-stories/",
      "excerpt": "Learn more about how Diffbot customers leverage the world's largest knowledge graph to build smarter applications, faster.",
      "confidence": "medium"
    },
    {
      "field": "mcp_url",
      "url": "https://github.com/orgs/diffbot/repositories",
      "excerpt": "53 repositories ; diffbot-mcp · A Diffbot MCP server with a variety of helpful web data handling tools for your agent or LLM pipeline. Python ; rss-anything.",
      "confidence": "high"
    },
    {
      "field": "stability",
      "url": "https://docs.diffbot.com/changelog/enhance-api-updates",
      "excerpt": "API versions v1 and v2 are now deprecated and will be removed in future versions of the product. Please plan to migrate.",
      "confidence": "high"
    },
    {
      "field": "rate_limit_requests",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Plans starting at Free. No contracts required. Get Started for Free. No credit card required.",
      "confidence": "medium"
    },
    {
      "field": "deprecation_policy_url",
      "url": "https://docs.diffbot.com/changelog/enhance-api-updates",
      "excerpt": "API versions v1 and v2 are now deprecated and will be removed in future versions of the product. Please plan to migrate.",
      "confidence": "high"
    },
    {
      "field": "auth_methods",
      "url": "https://docs.diffbot.com/reference/authentication",
      "excerpt": "All Diffbot APIs are authenticated via token. Updated 7 months ago.",
      "confidence": "high"
    },
    {
      "field": "api_version",
      "url": "https://docs.diffbot.com/reference/event",
      "excerpt": "Automatically extracts dates, location and address information, images and event descriptions from event pages.",
      "confidence": "high"
    },
    {
      "field": "sdk_packages",
      "url": "https://github.com/diffbot/diffbot-python",
      "excerpt": null,
      "confidence": "medium"
    },
    {
      "field": "sdk_packages",
      "url": "https://pypi.org/project/diffbot/",
      "excerpt": "diffbot 2.0.0. pip install diffbot. Copy PIP instructions. Latest version. Released: May 14, 2015. Python client for the Diffbot API.",
      "confidence": "medium"
    },
    {
      "field": "sla_url",
      "url": "https://status.diffbot.com/622688",
      "excerpt": "Availability (uptime) over the past 24 hours. Red sections indicate downtime. Hover mouse pointer over sections to get exact times.",
      "confidence": "medium"
    },
    {
      "field": "launched_at",
      "url": "https://www.linkedin.com/in/miketung",
      "excerpt": "Founder and CEO. Diffbot. Jan 2012",
      "confidence": "medium"
    },
    {
      "field": "webhook_signing",
      "url": "https://blog.diffbot.com/crawlbot-updates-webhooks-and-preventing-duplicate-content/",
      "excerpt": "When starting a crawl, you can now supply a webhook URL to be notified when the crawl is complete.",
      "confidence": "medium"
    },
    {
      "field": "starting_price_usd",
      "url": "https://puzzleinbox.com/tools/diffbot/",
      "excerpt": "Starting at $299 per month. Enterprise plans with custom pricing for larger usage.",
      "confidence": "high"
    },
    {
      "field": "versioning_scheme",
      "url": "https://docs.diffbot.com/reference/event",
      "excerpt": "Automatically extracts dates, location and address information, images and event descriptions from event pages.",
      "confidence": "high"
    },
    {
      "field": "price_basis",
      "url": "https://www.diffbot.com/pricing/",
      "excerpt": "Plans starting at Free. No contracts required. Get Started for Free. No credit card required.",
      "confidence": "high"
    },
    {
      "field": "requires_verification",
      "url": "https://app.diffbot.com/get-started/",
      "excerpt": "Access to Extract, NLP, and Knowledge Graph. Dive right into any Diffbot API. No coding required. Create your Diffbot account. No credit card required.",
      "confidence": "high"
    },
    {
      "field": "api_style",
      "url": "https://docs.diffbot.com/reference/article",
      "excerpt": "Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages.",
      "confidence": "high"
    },
    {
      "field": "idempotency_supported",
      "url": "https://docs.diffbot.com/reference/introduction-to-diffbot-apis",
      "excerpt": "AI that reads websites and structures them into facts. Introduction to Diffbot APIs For AI agents: visit https://docs.diffbot.com/llms.txt for an index of all",
      "confidence": "medium"
    },
    {
      "field": "mcp_url",
      "url": "https://github.com/diffbot/diffbot-mcp",
      "excerpt": "A Diffbot MCP server with a variety of helpful web data handling tools for your agent or LLM pipeline. What is Diffbot? Diffbot is a small research company",
      "confidence": "high"
    },
    {
      "field": "ga_date",
      "url": "https://docs.diffbot.com/changelog/enhance-api-updates",
      "excerpt": "API versions v1 and v2 are now deprecated and will be removed in future versions of the product. Please plan to migrate.",
      "confidence": "high"
    },
    {
      "field": "data_retention_policy_url",
      "url": "https://www.diffbot.com/company/privacy/",
      "excerpt": "Data that is stored by us is kept on secure encrypted services, located in the US. Restricting staff access to personal data protected by",
      "confidence": "medium"
    },
    {
      "field": "rate_limit_requests",
      "url": "http://prospeo.io/s/diffbot-pricing-reviews-pros-and-cons",
      "excerpt": "Free |$0 |10,000 |\\- |5 calls/mi",
      "confidence": "medium"
    },
    {
      "field": "quickstart_url",
      "url": "https://docs.diffbot.com/",
      "excerpt": "Diffbot builds AI models that read websites and structure them into facts. Unlike flat data dumps from traditional web scraping, facts structured by Diffbot",
      "confidence": "medium"
    },
    {
      "field": "api_version",
      "url": "https://docs.diffbot.com/reference/article",
      "excerpt": "Automatically extract clean article text and other data from news articles, blog posts and other text-heavy pages.",
      "confidence": "high"
    },
    {
      "field": "sdk_packages",
      "url": "https://github.com/orgs/diffbot/repositories",
      "excerpt": "53 repositories ; diffbot-mcp · A Diffbot MCP server with a variety of helpful web data handling tools for your agent or LLM pipeline. Python ; rss-anything.",
      "confidence": "medium"
    },
    {
      "field": "sdk_packages",
      "url": "https://github.com/diffbot/diffbot-ruby-client",
      "excerpt": "This is a Ruby client library for Diffbot API. Installation. Install the gem: gem 'diffbot-ruby-client', :git => 'git@github.com:diffbot/diffbot-ruby-client.git",
      "confidence": "medium"
    },
    {
      "field": "error_format",
      "url": "https://docs.diffbot.com/changelog",
      "excerpt": "Example Error Response (HTTP 500): json { \"errorCode\": 500, \"error\": \"This page requires a redirect. Please retry with redirects enabled if",
      "confidence": "medium"
    },
    {
      "field": "launched_at",
      "url": "https://pitchbook.com/profiles/company/54564-94",
      "excerpt": "When was Diffbot founded? Diffbot was founded in 2012.",
      "confidence": "medium"
    },
    {
      "field": "webhook_signing",
      "url": "https://github.com/diffbot/Diffbot-Documentation/blob/master/source/includes_erb/_crawlbot_api.md.erb",
      "excerpt": null,
      "confidence": "medium"
    }
  ],
  "fields_not_found": [
    "supported_regions",
    "soc2",
    "iso_27001",
    "hipaa",
    "pci_dss",
    "ga_date",
    "launched_at"
  ],
  "source_confidence": "high",
  "last_verified_at": "2026-06-06T00:00:00.000Z"
}