ChatGPT
Monitor what ChatGPT says about any brand, product, or topic. Get cited sources, internal search queries, and clean structured JSON from the real ChatGPT web interface.
Overview
Use this endpoint to monitor brand mentions, track AI-generated answers, and see which sources ChatGPT cites for any topic. Thesearch_queries field reveals ChatGPT’s internal query fan-out - the sub-questions it searched to build its answer - making it a powerful tool for keyword research and AI SEO.
Unique features
- Sources: Web citations with URL and link text for every source referenced in the response
- Search queries: The internal fan-out queries ChatGPT used to gather information before answering
- Markdown response: Full response formatted as markdown via
result_markdown
Example request
Example response
Response schema
Includes common response fields plus:Using search queries
Passsearch_queries results directly into your keyword research or content planning. Each string is a verbatim sub-question ChatGPT searched to build its answer.
search_queries array for this prompt might look like:
Common questions
Can I retrieve the search queries ChatGPT used?
Yes. Thesearch_queries field is included in every response and contains the internal fan-out queries ChatGPT issued to gather information before composing its answer.
Why do search queries look like long natural-language strings?
ChatGPT’s search model decides the shape of each query and often emits a single long natural-language string rather than comma-separated keywords. The length and structure vary between runs, even for the same prompt. ScrapeLLM returns them exactly as ChatGPT generates them.Does this hit the ChatGPT API or the web interface?
The web interface. ScrapeLLM captures what a real user sees in the ChatGPT chat UI - not the direct OpenAI API response. This means you get live web search results, citations, and UI-specific features unavailable through the raw API.How do I calculate AI visibility for my brand?
Run the same set of industry prompts repeatedly and check whether your brand appears inlinks or result. Divide the number of responses that mention your brand by the total runs to get a reliable AI visibility %.
Why does bypass_cache matter for brand monitoring?
Without bypass_cache: true, consecutive identical prompts may return a cached result. For accurate visibility tracking across multiple runs, set bypass_cache: true so each request fetches a fresh response from ChatGPT.Authorizations
Your ScrapeLLM API key passed in the request header.
Query Parameters
The prompt to send to ChatGPT. Maximum 4,000 characters.
1 - 4000ISO 3166-1 alpha-2 country code. Routes the request through infrastructure in
that region so you receive the localised ChatGPT response. Defaults to US.
2Include the full markdown-it token tree in the response.
Skip the response cache and always fetch a fresh result.
Maximum seconds to wait for ChatGPT to respond. Must be between 10 and 600.
10 <= x <= 600Response
Scrape completed successfully.
Always "chatgpt".
"chatgpt"
"done" on success.
"done"
Unique identifier for this scrape job.
"job_abc123"
The prompt that was submitted.
"What brands do marketers recommend for email automation?"
The country the request was routed through.
"US"
Plain-text response from ChatGPT.
"Marketers commonly recommend Mailchimp, HubSpot, and Klaviyo..."
Credits consumed by this request. Always 3 for ChatGPT.
3
Total end-to-end request duration in milliseconds.
8243.5
true if this response was served from cache.
false
Markdown-formatted response from ChatGPT.
"Marketers commonly recommend **Mailchimp**, **HubSpot**, and **Klaviyo**..."
Cited web sources with their display text and URL.
Internal search queries ChatGPT issued behind the scenes (query fan-out). These reveal what sub-questions ChatGPT searched to build its answer.
ChatGPT model variant used (e.g. gpt-4o).
"gpt-4o"
Hosted .md URL for this response, suitable for sharing or linking.
Expires after 24 hours.
"https://scrapellm.com/md/job_abc123.md"