Skip to main content
GET
cURL
Web search always enabledEvery request runs in ChatGPT’s web search mode. All responses include live citations from the web.

Overview

Use this endpoint to monitor brand mentions, track AI-generated answers, and see which sources ChatGPT cites for any topic. The search_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

Pass search_queries results directly into your keyword research or content planning. Each string is a verbatim sub-question ChatGPT searched to build its answer.
The search_queries array for this prompt might look like:

Common questions

Can I retrieve the search queries ChatGPT used?

Yes. The search_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 in links 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

X-API-Key
string
header
required

Your ScrapeLLM API key passed in the request header.

Query Parameters

prompt
string
required

The prompt to send to ChatGPT. Maximum 4,000 characters.

Required string length: 1 - 4000
country
string
default:US

ISO 3166-1 alpha-2 country code. Routes the request through infrastructure in that region so you receive the localised ChatGPT response. Defaults to US.

Required string length: 2
markdown_json
boolean
default:false

Include the full markdown-it token tree in the response.

bypass_cache
boolean
default:false

Skip the response cache and always fetch a fresh result.

timeout
number<float>
default:300

Maximum seconds to wait for ChatGPT to respond. Must be between 10 and 600.

Required range: 10 <= x <= 600

Response

Scrape completed successfully.

scraper
string
required

Always "chatgpt".

Example:

"chatgpt"

status
string
required

"done" on success.

Example:

"done"

job_id
string
required

Unique identifier for this scrape job.

Example:

"job_abc123"

prompt
string
required

The prompt that was submitted.

Example:

"What brands do marketers recommend for email automation?"

country
string
required

The country the request was routed through.

Example:

"US"

result
string
required

Plain-text response from ChatGPT.

Example:

"Marketers commonly recommend Mailchimp, HubSpot, and Klaviyo..."

credits_used
integer
required

Credits consumed by this request. Always 3 for ChatGPT.

Example:

3

elapsed_ms
number<float>
required

Total end-to-end request duration in milliseconds.

Example:

8243.5

cached
boolean
required

true if this response was served from cache.

Example:

false

result_markdown
string | null

Markdown-formatted response from ChatGPT.

Example:

"Marketers commonly recommend **Mailchimp**, **HubSpot**, and **Klaviyo**..."

Cited web sources with their display text and URL.

search_queries
string[]

Internal search queries ChatGPT issued behind the scenes (query fan-out). These reveal what sub-questions ChatGPT searched to build its answer.

Example:
llm_model
string | null

ChatGPT model variant used (e.g. gpt-4o).

Example:

"gpt-4o"

markdown_url
string | null

Hosted .md URL for this response, suitable for sharing or linking. Expires after 24 hours.

Example:

"https://scrapellm.com/md/job_abc123.md"