Supported collection target

ChatGPT collection API

chatgpt

Collected answer text and available sources.

What you receive

The chatgpt target collects responses through the web interface. Each successful run carries its run identity, capture time, text, markdown, pageUrl and sources. Text, markdown and pageUrl can be null; sources can be empty.

{
  "runNumber": 1,
  "runTaskId": "9a7536e7-b610-420a-a34c-5f829956f4d3",
  "status": "completed",
  "capturedAt": "2026-10-09T10:01:00.000Z",
  "text": "Illustrative captured answer text.",
  "markdown": null,
  "pageUrl": "https://chatgpt.com/",
  "sources": []
}

Illustrative successful run excerpt, not a production capture or full result file.

Collection behavior

Answers and sources vary by run. Country routing is a request option, not a guarantee of a particular language or provider location. Build your own analysis from the collected responses.

Submit an asynchronous crawl job, track its status, then download results with your account token. Inspect failedRuns even when the job is completed.

Request API access Read the docs

Our team arranges API access and follows up with next steps.