Skip to main content
Use ChatGPT LLM Scraper when you want a workflow step to retrieve ChatGPT’s answer for a search query, including cited sources, and pass that output into later workflow steps.

​
Configuration

Add this step from the Research group in Search steps…. The Search Query field supports Insert Variable. The Language and Location controls can use the built-in lists or switch to Custom Value for manual values or workflow variables.

​
Output

Click Run in the step header to test the step. Fetch Hive shows the ChatGPT answer in Output after the run completes. Use the variable picker in a later step to insert the exact output path available for that run. The base reference is:
The output object includes the full answer as markdown, cited sources, retrieved search results, and structured answer blocks. To use the full answer text:
Use the variable picker after a test run to inspect nested fields such as sources and items.

​
Example

Add ChatGPT LLM Scraper from the Research group in Search steps…. Set Name to something like ChatGPT brand mention. Enter your query in Search Query. If the query should reuse data from earlier workflow steps, click Insert Variable and add that reference. Set Language and Location from the lists or switch either field to Custom Value. Location must be a numeric code (for example 2840) or a variable that resolves to one, not a country name. Click Run and review the returned ChatGPT answer in Output before using it in a later step.

​
Notes

  • This step uses ChatGPT-specific language and location lists.
  • Location must be a numeric location code (for example 2840) or a variable that resolves to one. The editor list shows country names and sends the matching code; custom values and variables cannot use a country name.
  • Hosted runs convert the recorded service cost plus a 6% service fee into task credits. See Task costs.
See also: Creating and Editing, Testing and Iteration, and Error Handling