get_trends_by_region
Google Trends interest for up to five keywords, state by state within a country. ₹0.33 per call; a result that finds nothing is ₹0.
What it does
Where in a country people search most for up to five keywords, from Google Trends: data.items[0].interests[] with, for each keyword, values[] of geo_name (a US state, an Indian state and so on) and value, the relative interest from 0 to 100 (100 is the region that searches most), over the date range you give or the last year.
Use it to pick the states to target for ads, events or a sales push, or to compare two terms region by region; keyword_data gives interest over time for the whole country, keyword_volume absolute monthly searches. Flat price per call for up to five keywords; a keyword nobody searches is free. Under three seconds.
India: location_name "India" gives the Indian states.
Inputs
Generated from the contract captured from staging on 2026-11-20.
| Field | Type | Required | Description |
|---|---|---|---|
date_to | string | no | Last day, yyyy-mm-dd. Default today. |
keywords | array of string | one of | One to five keywords, compared on one scale. |
date_from | string | no | First day, yyyy-mm-dd. Default a year ago. |
time_range | string | no | Instead of dates: past_30_days, past_90_days, past_12_months or past_5_years. |
location_name | string | no | The country by name ("United States", "India"). |
One of these sets must be complete (anything else is invalid_input, ₹0): keywords.
What drives the cost
Flat price per call. A keyword nobody searches for is free. A result that finds nothing is class: "ok_free", ₹0. The timeout is 30 seconds.
Price today
| Price today | ₹0.33 per call (cost_paise: 33) at ₹93.93 per US dollar on 17 November 2026 |
| Hold before the call | ₹0.50 (hold_paise: 50); when the call settles the real price is charged and the unused part is released |
| ₹0 when | it fails, or the provider answers but there is nothing in it (an empty list, no email, no page): class: "ok_free", ₹0 |
| Timeout | 30 s, then upstream_timeout (₹0, retryable) |
| Over MCP | run_tool with tool: "get_trends_by_region" |
| Over REST | POST https://api.parel.si/v1/run with "tool": "get_trends_by_region" |
| Confirmation | not needed (the estimate is under the ₹200 threshold) |
Request
curl https://api.parel.si/v1/run \
-H "Authorization: Bearer $PAREL_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"get_trends_by_region","input":{"keywords":["predictive maintenance","machine monitoring"],"time_range":"past_12_months","location_name":"United States"}}'
What comes back
data, as the live check of 2026-11-20 recorded it, trimmed:
{
"keywords": [
"predictive maintenance",
"machine monitoring"
],
"type": "trends",
"location_code": 2840,
"items_count": 1,
"items": [
{
"keywords": [
"predictive maintenance",
"machine monitoring"
],
"interests": [
{
"keyword": "predictive maintenance",
"values": [
{
"geo_name": "Alabama",
"value": 25
},
{
"geo_name": "Arizona",
"value": 15
},
{
"geo_name": "Arkansas",
"value": 30
}
]
},
{
"keyword": "machine monitoring",
"values": [
{
"geo_name": "Alabama",
"value": 25
},
{
"geo_name": "Arizona",
"value": 21
},
{
"geo_name": "Arkansas",
"value": 0
}
]
}
],
"interests_comparison": {
"items": [
{
"geo_id": null,
"geo_name": "Alabama",
"values": [
83,
17
]
},
{
"geo_id": null,
"geo_name": "Arizona",
"values": [
78,
22
]
},
{
"geo_id": null,
"geo_name": "Arkansas",
"values": [
100,
0
]
}
],
"absolute_items": [
{
"geo_id": null,
"geo_name": "Alabama",
"values": [
25,
5
]
},
{
"geo_id": null,
"geo_name": "Arizona",
"values": [
15,
4
]
},
{
"geo_id": null,
"geo_name": "Arkansas",
"values": [
30,
0
]
}
]
}
}
]
}
Notes
- Relative interest, not search counts: 100 is the region that searches most, others are scaled to it.
- Up to five keywords on one scale. Rare keywords cover only some regions.
- Flat price per call. A keyword nobody searches for is free.
Siblings
This page as Markdown: /docs/tools/get_trends_by_region.md. Something wrong or missing: hello@parel.si.