Agentic Platform
Documentation API reference Tools Skills

Tools

Google Search

google_search Keywords Web search Google

Ask a question about Google Search results

Get feature snippets (e.g., Google shopping, images, video, people also search/ask), blue links, and knowledge graphs from real-time Google results.

Playground

POST
item
query required

The search query to analyze

question required

What do you want to know about the search results?

config
location_request required

Location request (ex: Paris, FR), will translate to location ID

device

Device to use for search

Credits

Fixed cost per question asked, plus one set of search results per query and the model that reads them to answer you. The model usage follows the results page and the length of your answer, and neither is capped.

These usage SKUs can be charged on a call, including SKUs from tools this one may call.

SKU Credits Description Used by
Tool call 1 per request Charged once per successful item, on top of any usage below.
  • This tool
Gemini 3 Flash (flex), input 250 per million tokens Tokens the model reads from the prompt you send.
  • This tool
Gemini 3 Flash (flex), output 1,500 per million tokens Tokens the model writes in its answer.
  • This tool
Gemini 3 Flash (flex), read from cache 50 per million tokens Tokens the model reads from a cached prompt. Cheaper than a fresh read.
  • This tool
Gemini 3 Flash (standard), input 500 per million tokens Tokens the model reads from the prompt you send.
  • This tool
Gemini 3 Flash (standard), output 3,000 per million tokens Tokens the model writes in its answer.
  • This tool
Gemini 3 Flash (standard), read from cache 50 per million tokens Tokens the model reads from a cached prompt. Cheaper than a fresh read.
  • This tool
Search results (live) 2 per query One organic search-results page for one query, fetched while you wait.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
query string required

The search query to analyze

question string required

What do you want to know about the search results?

Example
{
  "query": "string",
  "question": "string"
}

Configuration

object
Properties
location_request string required

Location request (ex: Paris, FR), will translate to location ID

device string

Device to use for search

Values: mobile desktop

Default: "mobile"

Example
{
  "location_request": "string",
  "device": "mobile"
}

Response

object
Properties
answer string required

The answer to the question

results GoogleSearchRawResults required

The SERP results used to generate the answer

Type: GoogleSearchRawResults

Example
{
  "answer": "string",
  "results": {
    "keyword": "string",
    "type": "string",
    "se_domain": "string",
    "location_code": 0,
    "language_code": "string",
    "check_url": "string",
    "datetime": "string",
    "spell": "string",
    "item_types": [
      "string"
    ],
    "se_results_count": 0,
    "items_count": 0,
    "items": [
      {}
    ]
  }
}

Type Definitions

1 type

These are the available sub-object types that can be used in the properties above.

GoogleSearchRawResults object
#
keyword string required
type string required
se_domain string required
location_code integer required
language_code string required
check_url string required
datetime string required
spell string | null required
item_types array required
se_results_count integer required
items_count integer required
items array required

Endpoints

POST http://agents.botify.com/{organization}/{project}/google_search/process
POST http://agents.botify.com/{organization}/{project}/google_search/batch_process
POST http://agents.botify.com/{organization}/{project}/google_search/async_process
POST http://agents.botify.com/{organization}/{project}/google_search/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/google_search/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "query": "<query>",
    "question": "<question>"
  },
  "config": {
    "location_request": "<location_request>"
  }
}'

Raw metadata