Google AI Overview API

Fetch Google AI Overviews for any query - get the AI-generated answer and its cited sources as structured JSON. Send one or many queries, target a country and language, and handle Google's deferred (page-token) generation automatically. Pay per retrieval. MCP-ready for Claude and AI agents.

MEDIAN LAGon demand
PARAMETERS5
TOTAL USERS126
MONTHLY ACTIVE82
TOTAL RUNS6,143
RUNS SUCCEEDED99.6%
RATING5.0 (4)

Input parameters

PARAMETERTYPEREQDEFAULTDESCRIPTION
query string no Enter a single search query to fetch the Google AI Overview for (e.g. 'what is the Siliconimist podcast?').
queries string[] no Provide a list of search queries to fetch AI Overviews for in one run.
gl string no us Set the two-letter country code for the search (ISO 3166-1, e.g. 'us', 'gb', 'ca').
hl string no en Set the two-letter interface language code (ISO 639-1, e.g. 'en').
location string no Optionally narrow results to a specific location by name (e.g. 'Austin, Texas, United States').

Worked examples

Basic — the required input, with the schema's own example values
{
  "query": "what is the Siliconimist podcast?",
  "queries": [
    "example"
  ]
}

Tasks

Saved runs with the inputs already filled in — each one a standalone page and a working configuration example.

Request a task →

Code

curl

curl -X POST "https://api.apify.com/v2/acts/johnvc~Google-AI-Overview-API/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "what is the Siliconimist podcast?", "queries": ["example"]}'

Python

from apify_client import ApifyClient

client = ApifyClient("APIFY_TOKEN")
run = client.actor("johnvc/Google-AI-Overview-API").call(
    run_input={'query': 'what is the Siliconimist podcast?', 'queries': ['example']}
)
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)