{
 "name": "Training data for sale and the prices sellers publish",
 "title": "Training data for sale and the prices sellers publish",
 "kind": "terms-board",
 "url": "https://buyaitrainingdata.com/datasets/datasets-for-sale-listed-prices/",
 "csv": "https://buyaitrainingdata.com/datasets/datasets-for-sale-listed-prices.csv",
 "markdown": "https://buyaitrainingdata.com/datasets/datasets-for-sale-listed-prices/index.md",
 "computed_at": "2026-10-08",
 "license": "https://buyaitrainingdata.com/terms",
 "headline": "8 of 24 companies that sell AI training data or buy company data publish a price on the pages we read, read 8 October 2026.",
 "quotes": [
  "8 of 24 companies that sell AI training data or buy company data publish a price on the pages we read, read 8 October 2026.",
  "Sells training data or buys company data, by company: sells training data 13 of 24, buys or licenses company data 11 of 24 (24 companies, read 8 October 2026).",
  "Publishes a price for data, by company: price on a quote only 9 of 24, publishes a price 8 of 24, not stated 6 of 24, varies 1 of 24 (24 companies, read 8 October 2026).",
  "Listed price, by company: not stated 15 of 24, stated 9 of 24 (24 companies, read 8 October 2026).",
  "Unit of the price, by company: not stated 18 of 24, per dataset purchase 4 of 24, per hour of audio or video 1 of 24, subscription 1 of 24 (24 companies, read 8 October 2026).",
  "Modalities on sale, by company: stated 21 of 24, not stated 3 of 24 (24 companies, read 8 October 2026).",
  "Licence offered, by company: not stated 16 of 24, subscription or access plan 4 of 24, non-exclusive licence 3 of 24, one-off purchase 1 of 24 (24 companies, read 8 October 2026)."
 ],
 "citation": "\"Training data for sale and the prices sellers publish\", updated 2026-10-08, https://buyaitrainingdata.com/datasets/datasets-for-sale-listed-prices/.",
 "national": {
  "n": 24,
  "unit": "companies",
  "documents": 34,
  "published_sources": 24,
  "named_sources": 41
 },
 "board": {
  "type": "clauses",
  "noun": {
   "one": "company",
   "many": "companies"
  },
  "document": {
   "one": "page",
   "many": "pages"
  },
  "fields": [
   {
    "id": "side",
    "label": "Sells training data or buys company data",
    "counts": {
     "buys": 11,
     "sells": 13
    },
    "values": [
     {
      "value": "sells",
      "text": "sells training data"
     },
     {
      "value": "buys",
      "text": "buys or licenses company data"
     }
    ]
   },
   {
    "id": "publishes_price",
    "label": "Publishes a price for data",
    "counts": {
     "quote-only": 9,
     "not-stated": 6,
     "varies": 1,
     "published": 8
    },
    "values": [
     {
      "value": "published",
      "text": "publishes a price"
     },
     {
      "value": "quote-only",
      "text": "price on a quote only"
     }
    ]
   },
   {
    "id": "price",
    "label": "Listed price",
    "counts": {
     "not-stated": 15,
     "stated": 9
    },
    "values": [
     {
      "value": "stated",
      "text": "stated"
     }
    ],
    "clause": true
   },
   {
    "id": "unit",
    "label": "Unit of the price",
    "counts": {
     "not-stated": 18,
     "subscription": 1,
     "per-hour": 1,
     "per-dataset": 4
    },
    "values": [
     {
      "value": "per-hour",
      "text": "per hour of audio or video"
     },
     {
      "value": "per-minute",
      "text": "per minute"
     },
     {
      "value": "per-record",
      "text": "per record or item"
     },
     {
      "value": "per-dataset",
      "text": "per dataset purchase"
     },
     {
      "value": "subscription",
      "text": "subscription"
     }
    ]
   },
   {
    "id": "modality",
    "label": "Modalities on sale",
    "counts": {
     "stated": 21,
     "not-stated": 3
    },
    "values": [
     {
      "value": "stated",
      "text": "stated"
     }
    ],
    "clause": true
   },
   {
    "id": "licence",
    "label": "Licence offered",
    "counts": {
     "non-exclusive": 3,
     "subscription": 4,
     "not-stated": 16,
     "one-off": 1
    },
    "values": [
     {
      "value": "one-off",
      "text": "one-off purchase"
     },
     {
      "value": "subscription",
      "text": "subscription or access plan"
     },
     {
      "value": "exclusive",
      "text": "exclusive licence available"
     },
     {
      "value": "non-exclusive",
      "text": "non-exclusive licence"
     }
    ]
   }
  ],
  "lead": {
   "type": "share",
   "field": "publishes_price",
   "value": "published",
   "n": 8,
   "of": 24,
   "label": "Companies that publish a price"
  },
  "vendors": [
   {
    "name": "aitrainer.work",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "buys",
        "quote": "Sell private code, data or a closed company's records to AI labs"
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "buys",
        "quote": "AI labs pay to license how companies work: support tickets, CRM history, chat, email and code."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "quote-only",
        "quote": "It depends on the buyer and the asset."
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold…",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "stated",
        "quote": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold non-exclusively."
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "stated",
        "quote": "AI labs pay to license how companies work: support tickets, CRM history, chat, email and code."
       }
      ]
     },
     "licence": {
      "value": "non-exclusive",
      "text": "non-exclusive licence",
      "documents": [
       {
        "document": "aitrainer.work sell to AI labs page",
        "url": "https://aitrainer.work/sell",
        "value": "non-exclusive",
        "quote": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold non-exclusively."
       },
       {
        "document": "aitrainer.work enterprise page",
        "url": "https://aitrainer.work/enterprise/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Appen",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "sells",
        "quote": "Off-the-shelf (OTS) AI training datasets are pre-collected, pre-licensed datasets that teams can license and use immediately for model training"
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "597 datasets across nine categories, from reinforcement learning (RL) tasks and verifiers…",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "stated",
        "quote": "597 datasets across nine categories, from reinforcement learning (RL) tasks and verifiers to speech, code, and enterprise data."
       }
      ]
     },
     "licence": {
      "value": "non-exclusive",
      "text": "non-exclusive licence",
      "documents": [
       {
        "document": "Appen off-the-shelf dataset catalog",
        "url": "https://www.appen.com/off-the-shelf-datasets",
        "value": "non-exclusive",
        "quote": "Contributor consent and documented licensing. Perpetual, non-exclusive commercial training rights."
       }
      ]
     }
    }
   },
   {
    "name": "AWS Data Exchange",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "sells",
        "quote": "Discover and subscribe to over 3,500 third-party data sets."
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "subscription",
      "text": "subscription",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "subscription",
        "quote": "Subscription-based products: For products that support subscription pricing, you can see a list of prices varying by subscription durations that are set by the data provider on the product’s detail page."
       }
      ]
     },
     "modality": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "licence": {
      "value": "subscription",
      "text": "subscription or access plan",
      "documents": [
       {
        "document": "AWS Data Exchange pricing page",
        "url": "https://aws.amazon.com/data-exchange/pricing/",
        "value": "subscription",
        "quote": "Subscription-based products: For products that support subscription pricing, you can see a list of prices varying by subscription durations that are set by the data provider on the product’s detail page."
       }
      ]
     }
    }
   },
   {
    "name": "Created by Humans",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "sells",
        "quote": "License premium content that's legally sound and author-approved."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "quote-only",
        "quote": "We negotiate agreements for your approval, and you track payments in your dashboard."
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "A single source for premium books",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "stated",
        "quote": "A single source for premium books"
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Created by Humans home page",
        "url": "https://www.createdbyhumans.ai/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Defined.ai",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "sells",
        "quote": "Defined.ai, the leading marketplace for high-quality AI training data, announced today the launch of its Data Access Plan (DAP)"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "sells",
        "quote": "Showing 10 of 819 datasets"
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "sells",
        "quote": "Access off-the-shelf ethically sourced and high-quality datasets across audio, image, video, text, and multimodal formats—delivered via API for speed and scale."
       }
      ]
     },
     "publishes_price": {
      "value": "varies",
      "text": "varies by document",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "published",
        "quote": "Standard Plan: 315 hours of speech data for €50,000 (30% discount)"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "quote-only",
        "quote": "request free samples and quotes to start training faster"
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "Elite Plan: 3,125 hours for €500,000 (55% discount)",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "stated",
        "quote": "Elite Plan: 3,125 hours for €500,000 (55% discount)"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "per-hour",
      "text": "per hour of audio or video",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "per-hour",
        "quote": "Premium Plan: 625 hours of speech data for €100,000 (40% discount)"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "per-hour",
        "quote": "99,500 hours of meeting recordings in English with video, audio, transcripts, metadata, action items, and recaps across industries."
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "a flexible and scalable plan that provides businesses with affordable access to…",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "stated",
        "quote": "a flexible and scalable plan that provides businesses with affordable access to off-the-shelf (OTS) speech datasets"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "stated",
        "quote": "99,500 hours of meeting recordings in English with video, audio, transcripts, metadata, action items, and recaps across industries."
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "stated",
        "quote": "Access off-the-shelf ethically sourced and high-quality datasets across audio, image, video, text, and multimodal formats—delivered via API for speed and scale."
       }
      ]
     },
     "licence": {
      "value": "subscription",
      "text": "subscription or access plan",
      "documents": [
       {
        "document": "Defined.ai Data Access Plan press release",
        "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
        "value": "subscription",
        "quote": "The four available plans—Standard, Premium, Ultimate, and Elite—offer discounted rates on high-quality speech datasets"
       },
       {
        "document": "Defined.ai dataset marketplace",
        "url": "https://defined.ai/datasets",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "Defined.ai home page",
        "url": "https://www.defined.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Grepped",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "buys",
        "quote": "Monetize the data supply only you have"
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "published",
        "quote": "Your company’s data could be worth $20K–$5M."
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "Your company’s data could be worth $20K–$5M.",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "stated",
        "quote": "Your company’s data could be worth $20K–$5M."
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Your team’s tools, connected read-only. Messages, docs, tickets, code, and records.",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "stated",
        "quote": "Your team’s tools, connected read-only. Messages, docs, tickets, code, and records."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Grepped home page",
        "url": "https://grepped.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Grepsr",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "sells",
        "quote": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web Data"
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "quote-only",
        "quote": "Usage-based Available Request detailed pricing"
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web…",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "stated",
        "quote": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web Data"
       }
      ]
     },
     "licence": {
      "value": "subscription",
      "text": "subscription or access plan",
      "documents": [
       {
        "document": "Datarade listing: Grepsr tailored web data",
        "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
        "value": "subscription",
        "quote": "Monthly License Available Yearly License Available"
       }
      ]
     }
    }
   },
   {
    "name": "Innodata",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "sells",
        "quote": "providing the data, evaluation frameworks, and human expertise required to build AI systems that can be trusted at scale"
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Innodata home page",
        "url": "https://www.innodata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "License My Data",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "buys",
        "quote": "License your business, clinical or video data for AI training."
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "published",
        "quote": "Placements in this category have reached six and seven figures"
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "Placements in this category have reached six and seven figures",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "stated",
        "quote": "Placements in this category have reached six and seven figures"
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "License your business, clinical or video data for AI training.",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "stated",
        "quote": "License your business, clinical or video data for AI training."
       }
      ]
     },
     "licence": {
      "value": "non-exclusive",
      "text": "non-exclusive licence",
      "documents": [
       {
        "document": "License My Data home page",
        "url": "https://licensemydata.com/",
        "value": "non-exclusive",
        "quote": "Depending on the buyer, that is a non-exclusive licence you can place again and again, or a one-time exclusive buyout."
       }
      ]
     }
    }
   },
   {
    "name": "Maryah",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "buys",
        "quote": "Turn your existing business data into a new source of revenue."
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "published",
        "quote": "LOWER RANGE $800K TO UPPER RANGE $1M"
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "LOWER RANGE $800K TO UPPER RANGE $1M",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "stated",
        "quote": "LOWER RANGE $800K TO UPPER RANGE $1M"
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Maryah licenses the emails, sales records and support tickets you choose to share, with…",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "stated",
        "quote": "Maryah licenses the emails, sales records and support tickets you choose to share, with identifying details removed and terms you approve."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Maryah business data licensing page",
        "url": "https://maryah.ai/business-data",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Mercor",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "buys",
        "quote": "The data your business generates every day is exactly what frontier labs need. We license it, package it, and pay you for it."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "quote-only",
        "quote": "Compensation is based on data volume, the tools you connect, and the depth of your data."
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Repositories, commits, PRs, and issues",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "stated",
        "quote": "Repositories, commits, PRs, and issues"
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Mercor Data page",
        "url": "https://mercor.com/data",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "micro1",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "buys",
        "quote": "micro1 helps companies turn their operational data into new revenue while advancing frontier AI"
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "buys",
        "quote": "Help companies monetize their operational data and get paid for every successful introduction."
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "published",
        "quote": "$100k+ Qualified Enterprise Data Partnerships"
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "published",
        "quote": "$100K-$2M+ for approved data packages"
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "$1M+ Highly unique, proprietary operational data with significant value for frontier AI…",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "stated",
        "quote": "$1M+ Highly unique, proprietary operational data with significant value for frontier AI development"
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "stated",
        "quote": "$100K-$2M+ for approved data packages"
       }
      ]
     },
     "unit": {
      "value": "per-dataset",
      "text": "per dataset purchase",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "per-dataset",
        "quote": "$100K-$2M+ for approved data packages"
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "SOPs, knowledge bases, internal documentation, CRM data, project histories, and QA…",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "stated",
        "quote": "SOPs, knowledge bases, internal documentation, CRM data, project histories, and QA processes"
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "stated",
        "quote": "Operational data partnership using existing business documentation and operational datasets."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "micro1 data estimate page",
        "url": "https://micro1.ai/data-estimate",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "micro1 company referral page",
        "url": "https://www.micro1.ai/company-referral",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Nexdata",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "sells",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "sells",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "sells",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "sells",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "sells",
        "quote": "Explore Nexdata’s datasets, databases, and data feeds."
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "sells",
        "quote": "French Natural Conversational Speech Synthesis Corpus."
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "published",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "published",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "published",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "published",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "published",
        "quote": "Starts at $100,000 / purchase View Product"
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "License Starts at One-off purchase $20,000 / purchase",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "stated",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "stated",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "stated",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "stated",
        "quote": "License Starts at One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "stated",
        "quote": "Starts at $100,000 / purchase View Product"
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "per-dataset",
      "text": "per dataset purchase",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "per-dataset",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "per-dataset",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "per-dataset",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "per-dataset",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "per-dataset",
        "quote": "Starts at $100,000 / purchase View Product"
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Scripted Monologues Speech Data | 65,000 Hours | GenAI Audio Data| Text-to-Speech Data|…",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "stated",
        "quote": "Scripted Monologues Speech Data | 65,000 Hours | GenAI Audio Data| Text-to-Speech Data| Multilingual Language Data"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "stated",
        "quote": "Unscripted Call Center Telephony Speech Data | 20,000 Hours |Speech"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "stated",
        "quote": "Speech Synthesis Data | 400 Hours |Text-to-Speech(TTS) Data | Audio Data | AI Training Data| Speech Data"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "stated",
        "quote": "Mixed Speech Data |5,000 Hours |Code-switching|Audio Data| Speech R"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "stated",
        "quote": "8kHz Conversational Speech Data | 15,000 Hours | Audio Data | Speech Recognition Data| Conversation Audio Data"
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "stated",
        "quote": "The total duration is approximately 11 hours, with audio specifications of 48 kHz sampling rate, 24‑bit depth, WAV format, mono channel."
       }
      ]
     },
     "licence": {
      "value": "one-off",
      "text": "one-off purchase",
      "documents": [
       {
        "document": "Datarade listing: multilingual read speech, 65,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
        "value": "one-off",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
        "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
        "value": "one-off",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: speech synthesis, 400 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
        "value": "one-off",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade listing: code-switching speech, 5,000 hours",
        "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
        "value": "one-off",
        "quote": "One-off purchase $20,000 / purchase"
       },
       {
        "document": "Datarade: Nexdata data products profile",
        "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "Nexdata off-the-shelf datasets page",
        "url": "https://www.nexdata.ai/datasets",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Nyne",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "buys",
        "quote": "We partner with you to license your company's data."
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "published",
        "quote": "ESTIMATED PAYOUT RANGE $383,083 - $896,969"
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "ESTIMATED PAYOUT RANGE $383,083 - $896,969",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "stated",
        "quote": "ESTIMATED PAYOUT RANGE $383,083 - $896,969"
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "File contents plus their metadata, authorship, timestamps, and access permissions.",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "stated",
        "quote": "File contents plus their metadata, authorship, timestamps, and access permissions."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Nyne data partnerships page",
        "url": "https://nyne.ai/data-partnerships",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "OpenAI",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "buys",
        "quote": "This is a form to express your interest so that we can get in contact and explore a partnership."
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "E.g. number of words, hours of content. Please specify units",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "stated",
        "quote": "E.g. number of words, hours of content. Please specify units"
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "OpenAI data partnerships interest form",
        "url": "https://openai.com/form/data-partnerships/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Opendatabay",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "sells",
        "quote": "Data Marketplace for AI Training and LLM Fine-Tuning"
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "published",
        "quote": "From 1 October 2026, all marketplace prices are denominated in USD."
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "Number of records 10M Size 500.0 GB 267 $102,900 Buy Now",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "stated",
        "quote": "Number of records 10M Size 500.0 GB 267 $102,900 Buy Now"
       }
      ]
     },
     "unit": {
      "value": "per-dataset",
      "text": "per dataset purchase",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "per-dataset",
        "quote": "Number of records 20K Size 6.8 TB 84 $227,800 Buy Now"
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Long-term Malware Detonation EDR Telemetry Feed Annual License",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "stated",
        "quote": "Long-term Malware Detonation EDR Telemetry Feed Annual License"
       }
      ]
     },
     "licence": {
      "value": "subscription",
      "text": "subscription or access plan",
      "documents": [
       {
        "document": "Opendatabay marketplace home page",
        "url": "https://www.opendatabay.com",
        "value": "subscription",
        "quote": "Long-term Malware Detonation EDR Telemetry Feed Annual License"
       }
      ]
     }
    }
   },
   {
    "name": "Protege",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "buys",
        "quote": "Unlock New Revenue Through Data Licensing for AI"
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Protege works with data and content providers across domains. Select an industry below to…",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "stated",
        "quote": "Protege works with data and content providers across domains. Select an industry below to learn more."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Protege for data providers page",
        "url": "https://withprotege.ai/data-provider",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Shaip",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "sells",
        "quote": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages — ready for ASR, TTS and voice AI."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "quote-only",
        "quote": "Licensing: Get a license tailored to your needs."
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages…",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "stated",
        "quote": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages — ready for ASR, TTS and voice AI."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shaip speech data catalogue",
        "url": "https://www.shaip.com/offerings/speech-data-catalog/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Shutterstock",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "sells",
        "quote": "Access licensable multimodal data for training, fine-tuning, evaluation, inference, and specialized AI applications."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "quote-only",
        "quote": "Tell us about your data needs"
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Access hundreds of millions of images, videos, audio files, 3D assets, and other content…",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "stated",
        "quote": "Access hundreds of millions of images, videos, audio files, 3D assets, and other content from Shutterstock’s global collection."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Shutterstock data licensing page",
        "url": "https://www.shutterstock.com/data-licensing",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "SimpleClosure AssetHub",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "buys",
        "quote": "AssetHub helps startups monetize their assets, like SourceCode or WorkspaceData to vetted AI buyers looking for real-world work product."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "quote-only",
        "quote": "We review your assets to determine what can be purchased and what they're worth."
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "That can include connected information across tools like Slack, Google Drive, Email…",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "stated",
        "quote": "That can include connected information across tools like Slack, Google Drive, Email, Notion, Figma, and more"
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "AssetHub product page",
        "url": "https://simpleclosure.com/product/asset-hub/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Snowflake Marketplace",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "sells",
        "quote": "Daily quantitative sentiment signals for DJ30: 30-day free Snowflake trial"
       }
      ]
     },
     "publishes_price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Snowflake Marketplace listing page",
        "url": "https://app.snowflake.com/marketplace",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "StageZero",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "sells",
        "quote": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not available anymore."
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "quote-only",
        "quote": "StageZero has not published pricing information for their data services."
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not…",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "stated",
        "quote": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not available anymore."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Datarade: StageZero (listing no longer available)",
        "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Troveo",
    "answers": {
     "side": {
      "value": "buys",
      "text": "buys or licenses company data",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "buys",
        "quote": "Thousands of companies trust Troveo to license their data, protect their rights, and pay them on time."
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "buys",
        "quote": "Turn your company's data into recurring revenue"
       }
      ]
     },
     "publishes_price": {
      "value": "published",
      "text": "publishes a price",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "published",
        "quote": "AI labs and startups are actively paying six figures for company data exports."
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "price": {
      "value": "stated",
      "text": "AI labs and startups are actively paying six figures for company data exports.",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "stated",
        "quote": "AI labs and startups are actively paying six figures for company data exports."
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "per-dataset",
      "text": "per dataset purchase",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "per-dataset",
        "quote": "AI labs and startups are actively paying six figures for company data exports."
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Buyers pay a premium for work they can follow across communication channels, knowledge…",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "stated",
        "quote": "Buyers pay a premium for work they can follow across communication channels, knowledge and code repositories, and operational tools."
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "stated",
        "quote": "Curate from millions of hours of content and 100+ video, audio, and gaming datasets."
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Troveo business data page",
        "url": "https://www.troveo.ai/business-data",
        "value": "not-stated",
        "quote": ""
       },
       {
        "document": "Troveo home page",
        "url": "https://www.troveo.ai",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   },
   {
    "name": "Unidata",
    "answers": {
     "side": {
      "value": "sells",
      "text": "sells training data",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "sells",
        "quote": "High-quality curated datasets for model training and testing"
       }
      ]
     },
     "publishes_price": {
      "value": "quote-only",
      "text": "price on a quote only",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "quote-only",
        "quote": "Tell us what you need — we’ll reply within 24h with a free estimate"
       }
      ]
     },
     "price": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "unit": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     },
     "modality": {
      "value": "stated",
      "text": "Egocentric Video Dataset 4,050 Hours 13 Scenarios",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "stated",
        "quote": "Egocentric Video Dataset 4,050 Hours 13 Scenarios"
       }
      ]
     },
     "licence": {
      "value": "not-stated",
      "text": "not stated",
      "documents": [
       {
        "document": "Unidata ready-made datasets",
        "url": "https://unidata.pro/datasets/",
        "value": "not-stated",
        "quote": ""
       }
      ]
     }
    }
   }
  ]
 },
 "subject_kind": "company",
 "rows": [
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AI labs pay to license how companies work: support tickets, CRM history, chat, email and code.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,924 characters) is silent on this.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,924 characters) is silent on this.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,924 characters) is silent on this.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "AI labs pay to license how companies work: support tickets, CRM history, chat, email and…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AI labs pay to license how companies work: support tickets, CRM history, chat, email and code.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/enterprise/",
   "document": "aitrainer.work enterprise page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,924 characters) is silent on this.",
   "text_sha256": "9f0ebeef6fa9a48d9d6696690d575e8f205747c44b33bd24e67ea7c0661dee85"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Sell private code, data or a closed company's records to AI labs",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "It depends on the buyer and the asset.",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,280 characters) is silent on this.",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,280 characters) is silent on this.",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold non-exclusively.",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "aitrainer.work",
   "url": "https://aitrainer.work/sell",
   "document": "aitrainer.work sell to AI labs page",
   "question": "licence",
   "answer": "non-exclusive",
   "answer_text": "non-exclusive licence",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Labeled data, logs and corpora you built, with rights you can prove. Mostly sold non-exclusively.",
   "text_sha256": "bd79c043d85302bbbbe9d04ef342ae798b170c802c79fc5b87c0a380d9429093"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Off-the-shelf (OTS) AI training datasets are pre-collected, pre-licensed datasets that teams can license and use immediately for model training",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,844 characters) is silent on this.",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,844 characters) is silent on this.",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,844 characters) is silent on this.",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "modality",
   "answer": "stated",
   "answer_text": "597 datasets across nine categories, from reinforcement learning (RL) tasks and verifiers…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "597 datasets across nine categories, from reinforcement learning (RL) tasks and verifiers to speech, code, and enterprise data.",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "Appen",
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "document": "Appen off-the-shelf dataset catalog",
   "question": "licence",
   "answer": "non-exclusive",
   "answer_text": "non-exclusive licence",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Contributor consent and documented licensing. Perpetual, non-exclusive commercial training rights.",
   "text_sha256": "e1ae7133950b6742b8dba346853a59eacdc3f1adcee3c0f39aec1f71de3eb1ce"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Discover and subscribe to over 3,500 third-party data sets.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (7,716 characters) is silent on this.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (7,716 characters) is silent on this.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "unit",
   "answer": "subscription",
   "answer_text": "subscription",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Subscription-based products: For products that support subscription pricing, you can see a list of prices varying by subscription durations that are set by the data provider on the product’s detail page.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "modality",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (7,716 characters) is silent on this.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "AWS Data Exchange",
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "document": "AWS Data Exchange pricing page",
   "question": "licence",
   "answer": "subscription",
   "answer_text": "subscription or access plan",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Subscription-based products: For products that support subscription pricing, you can see a list of prices varying by subscription durations that are set by the data provider on the product’s detail page.",
   "text_sha256": "cff54bd67bdddf79da5b068190e9b17884cb4304bad5012ea21c6e1252ac2fd8"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License premium content that's legally sound and author-approved.",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "We negotiate agreements for your approval, and you track payments in your dashboard.",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,758 characters) is silent on this.",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,758 characters) is silent on this.",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "A single source for premium books",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "A single source for premium books",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Created by Humans",
   "url": "https://www.createdbyhumans.ai/",
   "document": "Created by Humans home page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,758 characters) is silent on this.",
   "text_sha256": "c682c485ba085cb7de0c0df69d85da3716f330245ae19d1acec8ac9500d86453"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Showing 10 of 819 datasets",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,418 characters) is silent on this.",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,418 characters) is silent on this.",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "unit",
   "answer": "per-hour",
   "answer_text": "per hour of audio or video",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "99,500 hours of meeting recordings in English with video, audio, transcripts, metadata, action items, and recaps across industries.",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "modality",
   "answer": "stated",
   "answer_text": "99,500 hours of meeting recordings in English with video, audio, transcripts, metadata…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "99,500 hours of meeting recordings in English with video, audio, transcripts, metadata, action items, and recaps across industries.",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/datasets",
   "document": "Defined.ai dataset marketplace",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,418 characters) is silent on this.",
   "text_sha256": "c9d9f57e4c5d6e863ed759fd9fb324cd27e69330ae22e131b5fff6da97aa949a"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Defined.ai, the leading marketplace for high-quality AI training data, announced today the launch of its Data Access Plan (DAP)",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Standard Plan: 315 hours of speech data for €50,000 (30% discount)",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "price",
   "answer": "stated",
   "answer_text": "Elite Plan: 3,125 hours for €500,000 (55% discount)",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Elite Plan: 3,125 hours for €500,000 (55% discount)",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "unit",
   "answer": "per-hour",
   "answer_text": "per hour of audio or video",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Premium Plan: 625 hours of speech data for €100,000 (40% discount)",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "modality",
   "answer": "stated",
   "answer_text": "a flexible and scalable plan that provides businesses with affordable access to…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "a flexible and scalable plan that provides businesses with affordable access to off-the-shelf (OTS) speech datasets",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "document": "Defined.ai Data Access Plan press release",
   "question": "licence",
   "answer": "subscription",
   "answer_text": "subscription or access plan",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "The four available plans—Standard, Premium, Ultimate, and Elite—offer discounted rates on high-quality speech datasets",
   "text_sha256": "9257cb52fd4325be94c2aa7502525b4272810b0d257a0058cabf8c6ba5c45410"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Access off-the-shelf ethically sourced and high-quality datasets across audio, image, video, text, and multimodal formats—delivered via API for speed and scale.",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "request free samples and quotes to start training faster",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,139 characters) is silent on this.",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,139 characters) is silent on this.",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Access off-the-shelf ethically sourced and high-quality datasets across audio, image……",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Access off-the-shelf ethically sourced and high-quality datasets across audio, image, video, text, and multimodal formats—delivered via API for speed and scale.",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Defined.ai",
   "url": "https://www.defined.ai",
   "document": "Defined.ai home page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,139 characters) is silent on this.",
   "text_sha256": "93546a85c9b9cc85ab39b57a1e239a258055af7fbf31c959f6f5188140c652ed"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Monetize the data supply only you have",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Your company’s data could be worth $20K–$5M.",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "price",
   "answer": "stated",
   "answer_text": "Your company’s data could be worth $20K–$5M.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Your company’s data could be worth $20K–$5M.",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,047 characters) is silent on this.",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Your team’s tools, connected read-only. Messages, docs, tickets, code, and records.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Your team’s tools, connected read-only. Messages, docs, tickets, code, and records.",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepped",
   "url": "https://grepped.ai",
   "document": "Grepped home page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,047 characters) is silent on this.",
   "text_sha256": "0a6842509519ab5ec2822d6c9f738847d5f109c3185ac29cc1d4447b7edf93f2"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web Data",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Usage-based Available Request detailed pricing",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (10,500 characters) is silent on this.",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (10,500 characters) is silent on this.",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Global Tailored Web Data | AI Training Data | Machine Learning (ML) Data | Tailored Web Data",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Grepsr",
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "document": "Datarade listing: Grepsr tailored web data",
   "question": "licence",
   "answer": "subscription",
   "answer_text": "subscription or access plan",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Monthly License Available Yearly License Available",
   "text_sha256": "b26ed0ba7ce914716c1510291c7814d45fe3826ec2cee90e12a8339433909942"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "providing the data, evaluation frameworks, and human expertise required to build AI systems that can be trusted at scale",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,593 characters) is silent on this.",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,593 characters) is silent on this.",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,593 characters) is silent on this.",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "modality",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,593 characters) is silent on this.",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "Innodata",
   "url": "https://www.innodata.com/",
   "document": "Innodata home page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,593 characters) is silent on this.",
   "text_sha256": "7d8b973f815ace3104f458d8979c9ef4f5965f8dcd13d8376fe8b34fe4021e32"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License your business, clinical or video data for AI training.",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Placements in this category have reached six and seven figures",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "price",
   "answer": "stated",
   "answer_text": "Placements in this category have reached six and seven figures",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Placements in this category have reached six and seven figures",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (13,970 characters) is silent on this.",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "License your business, clinical or video data for AI training.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License your business, clinical or video data for AI training.",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "License My Data",
   "url": "https://licensemydata.com/",
   "document": "License My Data home page",
   "question": "licence",
   "answer": "non-exclusive",
   "answer_text": "non-exclusive licence",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Depending on the buyer, that is a non-exclusive licence you can place again and again, or a one-time exclusive buyout.",
   "text_sha256": "51674be4e6ecc02ec4cd523469c714f4617655a7c86be82c0b70d0a17030e171"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Turn your existing business data into a new source of revenue.",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "LOWER RANGE $800K TO UPPER RANGE $1M",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "price",
   "answer": "stated",
   "answer_text": "LOWER RANGE $800K TO UPPER RANGE $1M",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "LOWER RANGE $800K TO UPPER RANGE $1M",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (7,326 characters) is silent on this.",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Maryah licenses the emails, sales records and support tickets you choose to share, with…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Maryah licenses the emails, sales records and support tickets you choose to share, with identifying details removed and terms you approve.",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Maryah",
   "url": "https://maryah.ai/business-data",
   "document": "Maryah business data licensing page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (7,326 characters) is silent on this.",
   "text_sha256": "71d488fa186a5922f6596599b8d5fc7a49a33b23f18b8f3cf32deeed082647e4"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "The data your business generates every day is exactly what frontier labs need. We license it, package it, and pay you for it.",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Compensation is based on data volume, the tools you connect, and the depth of your data.",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,081 characters) is silent on this.",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,081 characters) is silent on this.",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Repositories, commits, PRs, and issues",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Repositories, commits, PRs, and issues",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "Mercor",
   "url": "https://mercor.com/data",
   "document": "Mercor Data page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,081 characters) is silent on this.",
   "text_sha256": "16f75bb0e09ac28c32da9cadf42e30bca9a2bcea0bd3a6a67103537cb888de62"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "micro1 helps companies turn their operational data into new revenue while advancing frontier AI",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "$100k+ Qualified Enterprise Data Partnerships",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "price",
   "answer": "stated",
   "answer_text": "$1M+ Highly unique, proprietary operational data with significant value for frontier AI…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "$1M+ Highly unique, proprietary operational data with significant value for frontier AI development",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (8,917 characters) is silent on this.",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "SOPs, knowledge bases, internal documentation, CRM data, project histories, and QA…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "SOPs, knowledge bases, internal documentation, CRM data, project histories, and QA processes",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://micro1.ai/data-estimate",
   "document": "micro1 data estimate page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (8,917 characters) is silent on this.",
   "text_sha256": "2a6c4cfba9e6518ed2fbe0e093ce95fa5d10508cf4f285da0b45d5b9329d2cff"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Help companies monetize their operational data and get paid for every successful introduction.",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "$100K-$2M+ for approved data packages",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "price",
   "answer": "stated",
   "answer_text": "$100K-$2M+ for approved data packages",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "$100K-$2M+ for approved data packages",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "$100K-$2M+ for approved data packages",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Operational data partnership using existing business documentation and operational…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Operational data partnership using existing business documentation and operational datasets.",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "micro1",
   "url": "https://www.micro1.ai/company-referral",
   "document": "micro1 company referral page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,561 characters) is silent on this.",
   "text_sha256": "2c27fcf1c7aeb693d96dd83a5ab929e780c9d5f959430b99d93570fd03e2b300"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Explore Nexdata’s datasets, databases, and data feeds.",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Starts at $100,000 / purchase View Product",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "price",
   "answer": "stated",
   "answer_text": "Starts at $100,000 / purchase View Product",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Starts at $100,000 / purchase View Product",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Starts at $100,000 / purchase View Product",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "modality",
   "answer": "stated",
   "answer_text": "8kHz Conversational Speech Data | 15,000 Hours | Audio Data | Speech Recognition Data|…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "8kHz Conversational Speech Data | 15,000 Hours | Audio Data | Speech Recognition Data| Conversation Audio Data",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "document": "Datarade: Nexdata data products profile",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (13,208 characters) is silent on this.",
   "text_sha256": "17b02d00e2767c1429b4466657ad687126883d3876e3b77d266919bad69d9770"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "price",
   "answer": "stated",
   "answer_text": "License Starts at One-off purchase $20,000 / purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Mixed Speech Data |5,000 Hours |Code-switching|Audio Data| Speech R",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Mixed Speech Data |5,000 Hours |Code-switching|Audio Data| Speech R",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "document": "Datarade listing: code-switching speech, 5,000 hours",
   "question": "licence",
   "answer": "one-off",
   "answer_text": "one-off purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "9a01dea57cea00be3bb1821ab550af6f0a70b8a9b2fdee3cbf6c71f6c44fd74b"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "price",
   "answer": "stated",
   "answer_text": "License Starts at One-off purchase $20,000 / purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Scripted Monologues Speech Data | 65,000 Hours | GenAI Audio Data| Text-to-Speech Data|…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Scripted Monologues Speech Data | 65,000 Hours | GenAI Audio Data| Text-to-Speech Data| Multilingual Language Data",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "document": "Datarade listing: multilingual read speech, 65,000 hours",
   "question": "licence",
   "answer": "one-off",
   "answer_text": "one-off purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "91bf524509fd250bbfff3b913a544034be76437a7edbe96fd0c383e13204b02e"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "price",
   "answer": "stated",
   "answer_text": "License Starts at One-off purchase $20,000 / purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Speech Synthesis Data | 400 Hours |Text-to-Speech(TTS) Data | Audio Data | AI Training…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Speech Synthesis Data | 400 Hours |Text-to-Speech(TTS) Data | Audio Data | AI Training Data| Speech Data",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "document": "Datarade listing: speech synthesis, 400 hours",
   "question": "licence",
   "answer": "one-off",
   "answer_text": "one-off purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "d8e32f207c24038d69fcbcbe7aed07b749eb7ff505e7854e5c97ed3619013e94"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "price",
   "answer": "stated",
   "answer_text": "License Starts at One-off purchase $20,000 / purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "License Starts at One-off purchase $20,000 / purchase",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Unscripted Call Center Telephony Speech Data | 20,000 Hours |Speech",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Unscripted Call Center Telephony Speech Data | 20,000 Hours |Speech",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "document": "Datarade listing: call-centre telephony speech, 20,000 hours",
   "question": "licence",
   "answer": "one-off",
   "answer_text": "one-off purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "One-off purchase $20,000 / purchase",
   "text_sha256": "fc08d287e6b0a6053cff7ae34032647559a6f8d35eb743d86c05a135ffb12b3c"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "French Natural Conversational Speech Synthesis Corpus.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (12,649 characters) is silent on this.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (12,649 characters) is silent on this.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (12,649 characters) is silent on this.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "The total duration is approximately 11 hours, with audio specifications of 48 kHz…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "The total duration is approximately 11 hours, with audio specifications of 48 kHz sampling rate, 24‑bit depth, WAV format, mono channel.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nexdata",
   "url": "https://www.nexdata.ai/datasets",
   "document": "Nexdata off-the-shelf datasets page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (12,649 characters) is silent on this.",
   "text_sha256": "629748137b945ca4daddc77744c092016d6b0aeda2a4bf77867bdf42818c06d9"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "We partner with you to license your company's data.",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "ESTIMATED PAYOUT RANGE $383,083 - $896,969",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "price",
   "answer": "stated",
   "answer_text": "ESTIMATED PAYOUT RANGE $383,083 - $896,969",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "ESTIMATED PAYOUT RANGE $383,083 - $896,969",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,973 characters) is silent on this.",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "File contents plus their metadata, authorship, timestamps, and access permissions.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "File contents plus their metadata, authorship, timestamps, and access permissions.",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "Nyne",
   "url": "https://nyne.ai/data-partnerships",
   "document": "Nyne data partnerships page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,973 characters) is silent on this.",
   "text_sha256": "4bd6ce7f2a4b099258349d6fb17c71461163fb8b22644aa3919116811fd05ee0"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "This is a form to express your interest so that we can get in contact and explore a partnership.",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,029 characters) is silent on this.",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,029 characters) is silent on this.",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,029 characters) is silent on this.",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "modality",
   "answer": "stated",
   "answer_text": "E.g. number of words, hours of content. Please specify units",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "E.g. number of words, hours of content. Please specify units",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "OpenAI",
   "url": "https://openai.com/form/data-partnerships/",
   "document": "OpenAI data partnerships interest form",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,029 characters) is silent on this.",
   "text_sha256": "bf82703e03b14d8ead972b6a9f04660ec3c07cae135d52b5d209c7bc65072a0a"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Data Marketplace for AI Training and LLM Fine-Tuning",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "From 1 October 2026, all marketplace prices are denominated in USD.",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "price",
   "answer": "stated",
   "answer_text": "Number of records 10M Size 500.0 GB 267 $102,900 Buy Now",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Number of records 10M Size 500.0 GB 267 $102,900 Buy Now",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Number of records 20K Size 6.8 TB 84 $227,800 Buy Now",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Long-term Malware Detonation EDR Telemetry Feed Annual License",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Long-term Malware Detonation EDR Telemetry Feed Annual License",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Opendatabay",
   "url": "https://www.opendatabay.com",
   "document": "Opendatabay marketplace home page",
   "question": "licence",
   "answer": "subscription",
   "answer_text": "subscription or access plan",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Long-term Malware Detonation EDR Telemetry Feed Annual License",
   "text_sha256": "bdd9d3c1bddf52865383543e40aada4e6f329caad9860358f5f21b8ca37725cd"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Unlock New Revenue Through Data Licensing for AI",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,626 characters) is silent on this.",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,626 characters) is silent on this.",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,626 characters) is silent on this.",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Protege works with data and content providers across domains. Select an industry below to…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Protege works with data and content providers across domains. Select an industry below to learn more.",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Protege",
   "url": "https://withprotege.ai/data-provider",
   "document": "Protege for data providers page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (1,626 characters) is silent on this.",
   "text_sha256": "a3aabbfedfc151f5d56968d04458ecbfb5553f35ad1889cc81c8935095a5d9e6"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages — ready for ASR, TTS and voice AI.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Licensing: Get a license tailored to your needs.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (10,135 characters) is silent on this.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (10,135 characters) is silent on this.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Off-the-shelf Voice Dataset / Speech Dataset / Audio Datasets in multiple languages — ready for ASR, TTS and voice AI.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shaip",
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "document": "Shaip speech data catalogue",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (10,135 characters) is silent on this.",
   "text_sha256": "f15da6b1b125ad8beb5f7f302359e27c876406086f82d23e2b291d2b6c236df9"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Access licensable multimodal data for training, fine-tuning, evaluation, inference, and specialized AI applications.",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Tell us about your data needs",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (8,297 characters) is silent on this.",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (8,297 characters) is silent on this.",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Access hundreds of millions of images, videos, audio files, 3D assets, and other content…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Access hundreds of millions of images, videos, audio files, 3D assets, and other content from Shutterstock’s global collection.",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "Shutterstock",
   "url": "https://www.shutterstock.com/data-licensing",
   "document": "Shutterstock data licensing page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (8,297 characters) is silent on this.",
   "text_sha256": "8fb3e6e4d233ef7b3e356a23be19388ad4e406b18d0a3927b4d2f9e6e7a175e0"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AssetHub helps startups monetize their assets, like SourceCode or WorkspaceData to vetted AI buyers looking for real-world work product.",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "We review your assets to determine what can be purchased and what they're worth.",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,730 characters) is silent on this.",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,730 characters) is silent on this.",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "That can include connected information across tools like Slack, Google Drive, Email…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "That can include connected information across tools like Slack, Google Drive, Email, Notion, Figma, and more",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "SimpleClosure AssetHub",
   "url": "https://simpleclosure.com/product/asset-hub/",
   "document": "AssetHub product page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,730 characters) is silent on this.",
   "text_sha256": "59168d3509aacbdafcab238235de21bc3dad73bd91c8e5461391e7e26c5d3c4b"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Daily quantitative sentiment signals for DJ30: 30-day free Snowflake trial",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,638 characters) is silent on this.",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,638 characters) is silent on this.",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,638 characters) is silent on this.",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "modality",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,638 characters) is silent on this.",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "Snowflake Marketplace",
   "url": "https://app.snowflake.com/marketplace",
   "document": "Snowflake Marketplace listing page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (3,638 characters) is silent on this.",
   "text_sha256": "0b5a0b26550c328751d773d6c26260fb2774b5616cda35cc4c739bcc3a21e5bf"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not available anymore.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "StageZero has not published pricing information for their data services.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,703 characters) is silent on this.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,703 characters) is silent on this.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "modality",
   "answer": "stated",
   "answer_text": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "The product Lithuanian audio dataset for speech recognition 20 hours (4/5) is not available anymore.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "StageZero",
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "document": "Datarade: StageZero (listing no longer available)",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (6,703 characters) is silent on this.",
   "text_sha256": "047e2e944d731708b8180ccf3a03f94348fdf4b712bd992e0392ade9c4243489"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Turn your company's data into recurring revenue",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "publishes_price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (14,071 characters) is silent on this.",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (14,071 characters) is silent on this.",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (14,071 characters) is silent on this.",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Curate from millions of hours of content and 100+ video, audio, and gaming datasets.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Curate from millions of hours of content and 100+ video, audio, and gaming datasets.",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai",
   "document": "Troveo home page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (14,071 characters) is silent on this.",
   "text_sha256": "fb51c0553573fed203dcbf01dfb0a053ee314711df955e346d6d3a6e3ebcaead"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "side",
   "answer": "buys",
   "answer_text": "buys or licenses company data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Thousands of companies trust Troveo to license their data, protect their rights, and pay them on time.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "publishes_price",
   "answer": "published",
   "answer_text": "publishes a price",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AI labs and startups are actively paying six figures for company data exports.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "price",
   "answer": "stated",
   "answer_text": "AI labs and startups are actively paying six figures for company data exports.",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AI labs and startups are actively paying six figures for company data exports.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "unit",
   "answer": "per-dataset",
   "answer_text": "per dataset purchase",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "AI labs and startups are actively paying six figures for company data exports.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Buyers pay a premium for work they can follow across communication channels, knowledge…",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Buyers pay a premium for work they can follow across communication channels, knowledge and code repositories, and operational tools.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Troveo",
   "url": "https://www.troveo.ai/business-data",
   "document": "Troveo business data page",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (4,973 characters) is silent on this.",
   "text_sha256": "c4fbcd6f4518fe5bbb2b4c13d1aa9b277f026b5c3818ec640ecd62d05ad72055"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "side",
   "answer": "sells",
   "answer_text": "sells training data",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "High-quality curated datasets for model training and testing",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "publishes_price",
   "answer": "quote-only",
   "answer_text": "price on a quote only",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Tell us what you need — we’ll reply within 24h with a free estimate",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "price",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,641 characters) is silent on this.",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "unit",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,641 characters) is silent on this.",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "modality",
   "answer": "stated",
   "answer_text": "Egocentric Video Dataset 4,050 Hours 13 Scenarios",
   "status": "stated",
   "retrieved_at": "2026-10-08",
   "quote": "Egocentric Video Dataset 4,050 Hours 13 Scenarios",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  },
  {
   "subject": "Unidata",
   "url": "https://unidata.pro/datasets/",
   "document": "Unidata ready-made datasets",
   "question": "licence",
   "answer": "not-stated",
   "answer_text": "not stated",
   "status": "not-stated",
   "retrieved_at": "2026-10-08",
   "quote": "Not addressed: the page read on 2026-10-08 (5,641 characters) is silent on this.",
   "text_sha256": "09e0f0aaf833e58714e19c117da24f2ece0dc07d25cfea5583cc41e806e8d008"
  }
 ],
 "sources": [
  {
   "url": "https://datarade.ai/data-products/nexdata-multilingual-read-speech-data-65-000-hours-aud-nexdata",
   "label": "Datarade: Nexdata multilingual read speech 65,000 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/unscripted-call-center-telephony-speech-data-20-000-hours-nexdata",
   "label": "Datarade: Nexdata call-centre telephony speech 20,000 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/nexdata-multilingual-speech-synthesis-data-400-hours-a-nexdata",
   "label": "Datarade: Nexdata speech synthesis 400 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/nexdata-multilingual-code-switching-speech-data-5-000-hou-nexdata",
   "label": "Datarade: Nexdata code-switching speech 5,000 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/nexdata-in-car-speech-data-15-000-hours-audio-ai-ml-t-nexdata",
   "label": "Datarade: Nexdata in-car speech 15,000 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/lithuanian-audio-dataset-for-speech-recognition-20-hours-4-5-stagezero",
   "label": "Datarade: StageZero Lithuanian speech 20 hours",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-products/grepsr-ai-ml-training-data-machine-learning-data-tail-grepsr",
   "label": "Datarade: Grepsr tailored web data",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datarade.ai/data-categories/audio-data/datasets",
   "label": "Datarade: audio datasets category",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "not-terms",
   "why": "a marketplace category index listing other sellers' products, each priced by its own seller (the $250 an audio hour is Spire Light's custom collection listing), not a document of Datarade's own"
  },
  {
   "url": "https://defined.ai/press-room/defined-ai-launches-data-access-plan-dap-allowing-access-to-speech-datasets-at-affordable-prices",
   "label": "Defined.ai: Data Access Plan",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://defined.ai/datasets",
   "label": "Defined.ai datasets marketplace",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.defined.ai",
   "label": "Defined.ai",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.nexdata.ai/datasets",
   "label": "Nexdata off-the-shelf datasets",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.shaip.com/offerings/speech-data-catalog/",
   "label": "Shaip speech data catalogue",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.appen.com/off-the-shelf-datasets",
   "label": "Appen off-the-shelf datasets",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://unidata.pro/datasets/",
   "label": "Unidata datasets",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.opendatabay.com",
   "label": "Opendatabay",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://aws.amazon.com/data-exchange/pricing/",
   "label": "AWS Data Exchange pricing",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://app.snowflake.com/marketplace",
   "label": "Snowflake Marketplace",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://huggingface.co/pricing",
   "label": "Hugging Face pricing",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "not-terms",
   "why": "Hugging Face's pricing page prices its hosting, compute and storage plans; it sells no training data"
  },
  {
   "url": "https://www.kaggle.com/datasets",
   "label": "Kaggle datasets",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "not-terms",
   "why": "Kaggle's dataset index lists free community datasets; nothing on it is offered for sale"
  },
  {
   "url": "https://www.shutterstock.com/data-licensing",
   "label": "Shutterstock data licensing",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.innodata.com/",
   "label": "Innodata",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://withprotege.ai/data-provider",
   "label": "Protege for data providers",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.troveo.ai/business-data",
   "label": "Troveo business data",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.troveo.ai",
   "label": "Troveo",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.createdbyhumans.ai/",
   "label": "Created by Humans",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://licensemydata.com/",
   "label": "licensemydata.com",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://grepped.ai",
   "label": "Grepped",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://maryah.ai/business-data",
   "label": "Maryah business data",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://micro1.ai/data-estimate",
   "label": "micro1 data estimate",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://www.micro1.ai/company-referral",
   "label": "micro1 company referral",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://mercor.com/data",
   "label": "Mercor Data",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://nyne.ai/data-partnerships",
   "label": "Nyne data partnerships",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://datavendor.ai/",
   "label": "DataVendor",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "unread"
  },
  {
   "url": "https://simpleclosure.com/product/asset-hub/",
   "label": "SimpleClosure Asset Hub",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://aitrainer.work/sell",
   "label": "aitrainer.work sell",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://aitrainer.work/enterprise/",
   "label": "aitrainer.work enterprise",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://openai.com/form/data-partnerships/",
   "label": "OpenAI data partnerships",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "read"
  },
  {
   "url": "https://fileyield.com/data-buyers",
   "label": "FileYield data buyers",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "secondary",
   "status": "not-terms",
   "why": "the charter admits it for: the roster of labs and buyers named as purchasing training data; never a buyer's price"
  },
  {
   "url": "https://monda.ai/data-valuation/calculator",
   "label": "Monda/Gulp data valuation calculator",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "secondary",
   "status": "not-terms",
   "why": "the charter admits it for: an adjacent valuation method for comparison; not a listed price"
  },
  {
   "url": "https://fileyield.com/how-it-works",
   "label": "FileYield, How it works (own terms and fees)",
   "license": "cited for reporting; the publisher's own marketplace, broker and vendor pages",
   "class": "primary-provider-own-site",
   "status": "unread"
  }
 ],
 "methodology": "Each company's own marketplace, broker and vendor pages were read through estate-fetch and stored whole (sha256 on every row). For every page, six questions were answered from its own words: sells training data or buys company data, publishes a price for data, listed price, unit of the price, modalities on sale, licence offered. Every stated answer carries the sentence it rests on, checked against the stored text; 'not stated' means the page read does not address the question. A company with several pages reads 'varies' where they disagree. 24 companies, 34 pages.",
 "embed": "<figure style=\"margin:0;padding:16px;border:1px solid #d0d0d0;background:#ffffff\"><blockquote style=\"margin:0 0 8px;background:#ffffff\">8 of 24 companies that sell AI training data or buy company data publish a price on the pages we read, read 8 October 2026.</blockquote><figcaption style=\"background:#ffffff\"><a href=\"https://buyaitrainingdata.com/datasets/datasets-for-sale-listed-prices/\" style=\"background:#ffffff\">Training data for sale and the prices sellers publish, buyaitrainingdata.com</a></figcaption></figure>"
}