Provided by DataForSEO
Measure changes in a target's AI mentions over time with DataForSEO
Read how the mention count and AI search volume of one or more keywords or domains moved between consecutive periods in Google AI Overviews or ChatGPT answers, between a start date and an end date, grouped by day, week, month or year, in one location. One row per period with the difference in mentions and the difference in AI search volume against the previous period. One request per call, priced by the vendor's own rate card; an empty result set is reported as no result. Location defaults to the United States (location_code 2840); ChatGPT answers exist for the United States in English only, and a location outside DataForSEO's LLM Mentions location list is rejected.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the DataForSEO endpoint /v3/ai_optimization/llm_mentions/timeseries_delta/live on Glasser.glasser run -p dataforseo -e '/v3/ai_optimization/llm_mentions/timeseries_delta/live' -i '{"target":[{"keyword":"bmw","search_scope":["answer"]}],"date_to":"2026-06-01","date_from":"2026-01-01","group_range":"month","location_code":2840}' --endpoint-version 1Uses endpoint version 1. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"dataforseo","endpoint":"/v3/ai_optimization/llm_mentions/timeseries_delta/live","input":{"target":[{"keyword":"bmw","search_scope":["answer"]}],"date_to":"2026-06-01","date_from":"2026-01-01","group_range":"month","location_code":2840},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to report on brand visibility in AI responses, you might look for mentions of your brand in the available data and collect the supporting evidence.
Copy this prompt into your agent to review evidence for your AI visibility report.
Use dataforseo:/v3/ai_optimization/llm_mentions/timeseries_delta/live on Glasser.
Find evidence of my brand in the returned AI visibility data for my monitoring report.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"date_from",
"date_to",
"group_range",
"location_code",
"target"
],
"properties": {
"tag": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"target": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"pattern": "^(?!https?:\\/\\/)(?!www\\.)[a-z0-9.-]+$",
"maxLength": 63,
"minLength": 1
},
"search_scope": {
"type": "array",
"items": {
"enum": [
"any",
"sources",
"search_results"
],
"type": "string"
},
"maxItems": 3,
"minItems": 1
},
"search_filter": {
"enum": [
"include",
"exclude"
],
"type": "string"
},
"include_subdomains": {
"type": "boolean"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"keyword"
],
"properties": {
"keyword": {
"type": "string",
"maxLength": 250,
"minLength": 1
},
"match_type": {
"enum": [
"word_match",
"partial_match"
],
"type": "string"
},
"search_scope": {
"type": "array",
"items": {
"enum": [
"any",
"question",
"answer",
"brand_entities",
"fan_out_queries"
],
"type": "string"
},
"maxItems": 5,
"minItems": 1
},
"search_filter": {
"enum": [
"include",
"exclude"
],
"type": "string"
}
},
"additionalProperties": false
}
]
},
"maxItems": 10,
"minItems": 1
},
"date_to": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"platform": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"date_from": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"group_range": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"language_code": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"location_code": {
"type": "integer"
}
},
"additionalProperties": false
}{
"target": [
{
"keyword": "bmw",
"search_scope": [
"answer"
]
}
],
"date_to": "2026-06-01",
"date_from": "2026-01-01",
"group_range": "month",
"location_code": 2840
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Base fee | The same price with or without matching data. | $0.10 |
|---|---|---|
| Per row | For each row returned. | $0.001 |
| Maximum per Run | The total charge will not exceed this amount. | $0.194 |
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |