Skip to main content
GET
cURL
AI answer + organic results togetherThis is the only scraper that returns both the AI-generated answer and the traditional organic search results shown on the same page - giving you a complete picture of Google Search visibility.

Overview

Use this endpoint to monitor your brand’s presence in Google’s AI Overviews, track which sources Google cites in its AI answers, and compare AI citation coverage against traditional organic rankings - all from a single request.

Unique features

  • Organic search results: Traditional Google search results returned alongside the AI answer
  • AI citations with thumbnails: Each cited source includes a thumbnail image URL and favicon
  • Raw URL capture: The underlying Google Search URL used to generate the response

Example request

Response schema

Includes common response fields plus:

Common questions

What is the difference between Google AI Mode and Gemini?

Google AI Mode is the AI answer panel shown within Google Search results on google.com. Gemini is Google’s standalone AI assistant at gemini.google.com. They use different models, different citation sources, and serve different user intents. Run both for full Google AI coverage.

Are organic search results always present?

No - organic results are only included when Google shows them on the same page as the AI answer. For some queries Google shows only the AI panel; for others it shows both. Check search_results.length before processing.

Can I use this for AI Overview monitoring?

Yes. Google AI Mode is the same surface as Google’s AI Overviews. This endpoint captures both the AI answer and the citations, making it the primary tool for AI Overview brand monitoring.

Authorizations

X-API-Key
string
header
required

Your ScrapeLLM API key passed in the request header.

Query Parameters

prompt
string
required

The query to send to Google AI Mode. 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 for localised responses. JP and TW are not supported. Defaults to US.

Required string length: 2
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 Google AI Mode to respond. Must be between 10 and 600.

Required range: 10 <= x <= 600

Response

Scrape completed successfully.

scraper
string
required

Always "google_ai_mode".

Example:

"google_ai_mode"

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 query 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 AI-generated answer from Google AI Mode.

Example:

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

credits_used
integer
required

Credits consumed by this request. Always 3 for Google AI Mode.

Example:

3

elapsed_ms
number<float>
required

Total end-to-end request duration in milliseconds.

Example:

7318.6

cached
boolean
required

true if this response was served from cache.

Example:

false

result_markdown
string | null

Markdown-formatted AI-generated answer.

Example:

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

citations
object[]

Sources directly referenced within the AI-generated answer. These are the pages that influenced what the AI said — distinct from search_results.

search_results
object[]

Traditional organic search results shown below the AI answer. Often different from citations — understanding that gap is a key AI SEO signal.

raw_url
string<uri> | null

The original Google search URL used to fetch this response.

Example:

"https://www.google.com/search?q=What+brands+do+marketers+recommend"

markdown_url
string | null

Hosted .md URL for this response. Expires after 24 hours.

Example:

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