Search LLM mentions of a domain or keyword

Search an indexed corpus of ChatGPT or Google AI Overview answers. This does not execute a custom prompt. Includes answer text, sources and estimated AI search volume. Costs 10 credits per returned record, minimum 1,000 credits ($1). Reserves credits for limit (default 100) before collection and releases unused credits; no balance truncation. Failed requests are not charged.

Pricing — $$$ · min $1.00

Minimum 1000 credits ($1.00) per call. Records returned above the minimum bill 10 credit ($0.001) each.

Authorization

bearerAuth

AuthorizationBearer <token>

UnifAPI API key. Provider credentials are managed by UnifAPI.

In: header

Header Parameters

X-Unifapi-Max-Credits?string

Optional maximum credit budget for this request. The gateway validates the required reservation before collection and rejects a lower cap without charging. Unused reserved credits are released after settlement. Omit to use your available balance.

Match^\d+$

Unifapi-Version?"2026-07-01"

Pin the API version an integration was built against (date-based, e.g. 2026-07-01). Omit to use the current version. Public URL paths stay stable and unversioned; breaking changes ship under a new dated version and are announced with Deprecation and Sunset response headers. The served version is echoed in every response's Unifapi-Version header. Policy: https://unifapi.com/versioning.md

Default"2026-07-01"

Value in

"2026-07-01"

Idempotency-Key?string

Client-supplied unique key that makes a write request safe to retry. If a request with the same key was already processed, the original response is replayed (with Idempotency-Replayed: true) instead of executing — and billing — again. Send a fresh UUID per logical operation. Best-effort with a 24h window.

Lengthlength <= 255

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

target*array<>

Up to 10 target entities, each a domain or a keyword.

Items1 <= items <= 10

engine?string

Value in

"chatgpt"
"google"

location?|

Search location as a country code/name, DataForSEO location code, full location name, or latitude,longitude,radius coordinate string. Defaults to us.

language?string

Search language as an ISO code or full language name. Defaults to en.

Length2 <= length <= 80

filters?||

Filter the matched mentions. Provide a single condition {"field","op","value"} or an {"and":[…]} / {"or":[…]} group of conditions (nest groups for mixed logic), up to 8 conditions. Operators: =, <>, <, <=, >, >=, in, not_in, like, not_like, ilike, not_ilike, match, not_match (use an array value with in / not_in). Filterable fields: ai_search_volume (monthly AI search volume); platform (LLM engine, e.g. chat_gpt, google, perplexity); model (model name that produced the answer). Example: {"and":[{"field":"ai_search_volume","op":">","value":1000},{"field":"platform","op":"=","value":"chat_gpt"}]}

order_by?array<>

Sort the matched mentions. Each rule is {"field","dir"} with dir asc or desc; up to 3 rules, applied in order. Sortable fields: ai_search_volume, platform, model.

Items1 <= items <= 3

limit?integer

Max mentions to return. Default 100.

Range1 <= value <= 1000

offset?integer

Mentions to skip. Use cursor beyond 9000.

Range0 <= value <= 9000

cursor?string

search_after_token from a previous response, for deep pagination.

view?GeoView

Response size. full keeps answers, sources, and raw search results; standard drops raw search results; summary keeps only the question, volume, and cited sources. Defaults to standard.

Value in

"summary"
"standard"
"full"

Response Body

`application/json`

curl -X POST "https://example.com/geo/mentions/search" \  -H "Content-Type: application/json" \  -d '{    "target": [      {}    ]  }'

{  "request_id": "string",  "data": {    "engine": "chatgpt",    "location": "string",    "language": "string",    "total_count": 0,    "returned_count": 0,    "cursor": "string",    "results": [      {        "engine": "chatgpt",        "model": "string",        "question": "string",        "answer": "string",        "ai_search_volume": 0,        "monthly_searches": [          {            "year": 0,            "month": 0,            "ai_search_volume": 0          }        ],        "sources": [          {            "title": "string",            "url": "string",            "domain": "string",            "snippet": "string",            "source_name": "string",            "position": 0,            "publication_date": "string"          }        ],        "search_results": [          {            "title": "string",            "url": "string",            "domain": "string",            "description": "string",            "position": 0,            "publication_date": "string"          }        ],        "brand_entities": [          {            "title": "string",            "category": "string",            "position": 0          }        ],        "fan_out_queries": [          "string"        ],        "first_response_at": "string",        "last_response_at": "string"      }    ]  },  "billing": {    "credits_charged": 0,    "records_charged": 0,    "balance_remaining": 0,    "truncated_due_to_balance": true  }}

Search LLM mentions of a domain or keyword

Authorization

Header Parameters

Request Body

Response Body

200application/json

400application/json

401application/json

402application/json

404application/json

429application/json

500application/json

502application/json

503application/json

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`