API

AI Search

AI Search API provides programmatic access to a domain’s performance in Large Language Model (LLM) results. Data is refreshed on a monthly basis.

Using the API, you can:

get an AI search overview with metrics like link presence, average position, AI traffic, and historical trends
compare a primary domain against competitors across multiple LLM engines and retrieve a share of voice leaderboard
discover the brand associated with a domain or URL
retrieve prompts by target, showing where a domain or URL appears in LLM responses
retrieve prompts by brand, showing where a brand is mentioned in LLM results

Get AI search overview

GET https://api.seranking.com/v1/ai-search/overview/by-engine/time-series
Cost: 800 credits per request

Retrieves a high-level overview of a domain’s brand presence in an LLM, including historical trends over time and other metrics like link presence, average position, and AI traffic.

Request parameters

Parameter	Type	Required	Default	Description
engine	String	Yes	N/A	LLM to query (e.g., `ai-overview`, `chatgpt`, `perplexity`, `gemini`, `ai-mode`).
target	String	Yes	N/A	Target to analyze for LLM performance. Can be a root domain, subdomain, or a specific URL (e.g., `seranking.com`).
source	string	Yes	N/A	Country code for the regional prompt database (e.g., `us` for the United States results). For acceptable values, see Regional database codes.
scope	String	No	`base_domain`	Scope of analysis: • `base_domain` – aggregate by registrable domain, includes all subdomains. • `domain` – exact host only, no subdomain aggregation. • `url` – exact URL including path and query.
brand	String	No	N/A	Brand to filter the brand presence analysis (e.g., `SE Ranking`).

Request example

Copy

curl --location 'https://api.seranking.com/v1/ai-search/overview/by-engine/time-series?target=seranking.com&source=us&engine=ai-overview' \

--header 'Authorization: Token YOUR_API_KEY'

Response parameters

If successful, the server returns a JSON object containing aggregated metrics, changes from the previous period, and time-series data for generating charts.

Parameter	Type	Description
summary	Object	Object containing key performance metrics like `brand_presence`, `link_presence`, `average_position`, and `ai_opportunity_traffic`.
time_series	Object	Object containing historical data arrays for `overall_traffic`, `organic_traffic`, `ai_traffic`, `link_presence`, and `average_position`.

Each object within the summary object has the following structure:

Parameter	Type	Description
current	Float	Value for the current period.
previous	Float	Value for the previous period.
change_absolute	Float	Absolute difference between the current and previous periods.
change_percent	Float	Percentage change between the current and previous periods.

Each array within the time_series object contains a series of objects with the following structure:

Parameter	Type	Description
date	String	Month and year of the data point in `YYYY-MM` format.
value	Float	Metric’s value for that month.

Response example

Copy

{

  "summary": {

    "brand_presence": {

      "current": 50,

      "previous": 45,

      "change_absolute": 5,

      "change_percent": 11.1

    },

    "link_presence": {

      "current": 120,

      "previous": 110,

      "change_absolute": 10,

      "change_percent": 9.1

    },

    "average_position": {

      "current": 8.5,

      "previous": 9.2,

      "change_absolute": 0.7,

      "change_percent": 7.6

    },

    "ai_opportunity_traffic": {

      "current": 2000,

      "previous": 1800,

      "change_absolute": 200,

      "change_percent": 11.1

    }

  },

  "time_series": {

    "overall_traffic": [

      { "date": "2025-08", "value": 43000 },

      { "date": "2025-09", "value": 45000 }

    ],

    "organic_traffic": [

      { "date": "2025-08", "value": 40000 },

      { "date": "2025-09", "value": 42000 }

    ],

    "ai_traffic": [

      { "date": "2025-08", "value": 3000 },

      { "date": "2025-09", "value": 3000 }

    ],

    "link_presence": [

      { "date": "2025-08", "value": 110 },

      { "date": "2025-09", "value": 120 }

    ],

    "average_position": [

      { "date": "2025-08", "value": 9.2 },

      { "date": "2025-09", "value": 8.5 }

    ]

  }

}

Get AI search leaderboard

POST https://api.seranking.com/v1/ai-search/overview/leaderboard
Cost: 7,500 credits per request (flat)

Compares a primary domain against up to 10 competitors across multiple LLM engines and returns a share of voice leaderboard showing which domains have the highest AI search visibility. The leaderboard is calculated based on both brand and link presence across the selected engines.

Request parameters

Parameter	Type	Required	Default	Description
primary	Object	Yes	N/A	Primary domain and brand information.
competitors	Array	Yes	N/A	List of competitors to compare (1–10 items).
scope	String	No	`base_domain`	Scope of the analysis: • `base_domain` – aggregate by registrable domain, includes all subdomains. • `domain` – exact host only, no subdomain aggregation. • `url` – exact URL including path and query.
source	String	Yes	N/A	Country code for the regional database (e.g., `us` for United States results). For acceptable values, see Regional database codes.
engines	Array	Yes	N/A	LLM engines to query (`ai-overview`, `chatgpt`, `perplexity`, `gemini`, `ai-mode`).

Each object within the primary parameter has the following structure:

Parameter	Type	Required	Description
target	String	Yes	Target to analyze for LLM performance. Can be a root domain, subdomain, or a specific URL (e.g., `seranking.com`).
brand	String	No	Brand name (e.g., `SE Ranking`).

Each object within the competitors parameter has the following structure:

Parameter	Type	Required	Description
target	String	Yes	Competitor to analyze for LLM performance. Can be a root domain, subdomain, or a specific URL (e.g., `semrush.com`).
brand	String	No	Competitor brand name (e.g., `Semrush`).

Request example

Copy

curl --location 'https://api.seranking.com/v1/ai-search/overview/leaderboard' \

--header 'Authorization: Token YOUR_API_KEY' \

--header 'Content-Type: application/json' \

--data '{

  "primary": {

    "target": "example.com",

    "brand": "Example"

  },

  "competitors": [

    { "target": "example1.com", "brand": "Example 1" },

    { "target": "example2.com", "brand": "Example 2" }

  ],

  "scope": "base_domain",

  "source": "us",

  "engines": ["ai-overview", "chatgpt", "perplexity"]

}'

Response parameters

If successful, the server returns a JSON object containing leaderboard and per-domain, per-engine metrics.

Parameter	Type	Description
request_metadata	Object	Metadata describing the request.
leaderboard	Array	Leaderboard of domains sorted by share of voice.
results	Object	Detailed per-domain, per-engine metrics.

Each object in request_metadata has the following structure:

Parameter	Type	Description
primary	String	Primary target domain.
competitors	Array	Competitor domains included in the request.
engines	Array	Engines used for the comparison.
source	String	Country code for the regional database.

Each object in leaderboard array has the following structure:

Parameter	Type	Description
rank	Integer	Position in the leaderboard (1 = highest share of voice).
domain	String	Domain name.
share_of_voice	Float	Calculated share of voice.
brand_presence	Integer	Total brand mentions across selected engines.
link_presence	Integer	Total link citations across selected engines.
is_primary_target	Boolean	Indicates whether this is the primary domain.

Each object in results has the following structure:

Each domain object (results.{domain}) contains:

Parameter	Type	Description
{engine}	Object	Metrics for a specific engine.

Each engine object (results.{domain}.{engine}) contains:

Parameter	Type	Description
brand_presence	Integer	Brand presence for this domain on this engine.
link_presence	Integer	Link presence for this domain on this engine.

Response example

Copy

{

    "results": {

        "example.com": {

            "chatgpt": {

                "brand_presence": 5,

                "link_presence": 18

            },

            "ai-overview": {

                "brand_presence": 4798,

                "link_presence": 9245

            },

            "perplexity": {

                "brand_presence": 162,

                "link_presence": 416

            }

        },

        "example1.com": {

            "chatgpt": {

                "brand_presence": 3042,

                "link_presence": 287

            },

            "ai-overview": {

                "brand_presence": 13688,

                "link_presence": 10083

            },

            "perplexity": {

                "brand_presence": 737,

                "link_presence": 730

            }

        },

        "example2.com": {

            "chatgpt": {

                "brand_presence": 55,

                "link_presence": 324

            },

            "ai-overview": {

                "brand_presence": 20161,

                "link_presence": 37952

            },

            "perplexity": {

                "brand_presence": 466,

                "link_presence": 2816

            }

        }

    },

    "request_metadata": {

        "engines": [

            "ai-overview",

            "chatgpt",

            "perplexity"

        ],

        "competitors": [

            "example1.com",

            "example2.com"

        ],

        "source": "us",

        "primary": "example.com"

    },

    "leaderboard": [

        {

            "rank": 1,

            "link_presence": 41092,

            "share_of_voice": 0.5719,

            "is_primary_target": false,

            "brand_presence": 20682,

            "domain": "example2.com"

        },

        {

            "rank": 2,

            "link_presence": 11100,

            "share_of_voice": 0.2923,

            "is_primary_target": false,

            "brand_presence": 17467,

            "domain": "example1.com"

        },

        {

            "rank": 3,

            "link_presence": 9679,

            "share_of_voice": 0.1358,

            "is_primary_target": true,

            "brand_presence": 4965,

            "domain": "example.com"

        }

    ]

}

Discover brand by URL

GET https://api.seranking.com/v1/ai-search/discover-brand
Cost: 100 credits per request

Identifies the brand name associated with the specified target domain. This utility endpoint is useful for programmatically finding a brand before using it in other queries.

Request parameters

Parameter	Type	Required	Default	Description
target	String	Yes	N/A	Target to analyze for LLM performance. Can be a root domain, subdomain, or a specific URL (e.g., `seranking.com`).
source	String	Yes	N/A	Country code for the regional prompt database (e.g., `us` for United States results). For acceptable values, see Regional database codes.
scope	String	Yes	`base_domain`	Scope of analysis: • `base_domain` – aggregate by registrable domain, includes all subdomains. • `domain` – exact host only, no subdomain aggregation. • `url` – exact URL including path and query.

Request example

Copy

curl --location 'https://api.seranking.com/v1/ai-search/discover-brand?target=microsoft.com&scope=domain&source=us' \

--header 'Authorization: Token YOUR_API_KEY'

Response parameters

If successful, the server returns a JSON object containing an array of discovered brand names.

Parameter	Type	Description
brands	Array	Array of strings, each a potential brand name.

Response example

Copy

{

    "brands": [

        "Microsoft"

    ]

}

Get prompts by target

GET https://api.seranking.com/v1/ai-search/prompts-by-target
Cost: 200 credits per returned prompt

Retrieves a paginated list of prompts where the specified domain, subdomain, or URL appears in LLM results.

Request parameters

Parameter	Type	Required	Default	Description
engine	String	Yes	N/A	LLM to query (e.g., `ai-overview`, `chatgpt`, `perplexity`, `gemini`, `ai-mode`).
target	String	Yes	N/A	Target to analyze for LLM performance. Can be a root domain, subdomain, or a specific URL.
source	String	Yes	N/A	Country code for the regional prompt database (e.g., `us` for United States results). For acceptable values, see Regional database codes.
scope	String	Yes	`base_domain`	Scope of the analysis: • `base_domain` – aggregate by registrable domain, includes all subdomains. • `domain` – exact host only, no subdomain aggregation. • `url` – exact URL including path and query.
sort	String	No	`volume`	Field to sort the results by: `volume`, `type`, `snippet_length`.
sort_order	String	No	`desc`	Sort order for the results: • `asc` – for ascending • `desc` – for descending
limit	Integer	No	`100`	Maximum number of prompts to return per page (max 1000).
offset	Integer	No	`0`	Starting position for the paginated list.
filter	Object	No	N/A	Object for filtering results. See the Filtering results section for details.

Request example

Copy

curl --location --globoff 'https://api.seranking.com/v1/ai-search/prompts-by-target?target=seranking.com&scope=domain&source=us&engine=ai-mode&limit=1' \

--header 'Authorization: Token YOUR_API_KEY'

Response parameters

If successful, the server returns a JSON object containing a list of prompts and metadata.

Parameter	Type	Description
total	Integer	Total number of prompts found for the target.
date	String	Date of the data snapshot in `YYYY-MM-DD` format.
prompts	Array	Array of objects, each representing a found prompt.

Each object in the prompts array has the following structure:

Parameter	Type	Description
prompt	String	User query or prompt text that triggered the LLM response.
volume	Integer	Estimated monthly search volume for the prompt.
type	String	Type of appearance for the target in the LLM result (e.g., `Link`, `Brand`).
answer	Object	Object containing the detailed response from the LLM.

The answer object contains the following fields:

Parameter	Type	Description
text	String	Full text of the snippet generated by the LLM.
links	Array	Array of URL strings that were included as links within the LLM’s answer.

Response example

Copy

{

    "total": 5448,

    "date": "2025-09-01",

    "prompts": [

        {

            "prompt": "peliculas en netflix",

            "volume": 14800,

            "type": "Link",

            "answer": {

                "text": "Hay una gran variedad de peliculas disponibles en Netflix...",

                "links": [ "[https://movies.sitioficial.netflix.com/browse/genre/34399](https://movies.sitioficial.netflix.com/browse/genre/34399)" ]

            }

        }

    ]

}

Get prompts by brand

GET https://api.seranking.com/v1/ai-search/prompts-by-brand
Cost: 200 credits per returned prompt

Retrieves a paginated list of prompts where the specified brand name is mentioned in LLM results.

Request parameters

Parameter	Type	Required	Default	Description
engine	String	Yes	N/A	LLM to query (e.g., `ai-overview`, `chatgpt`, `perplexity`, `gemini`, `ai-mode`).
brand	String	Yes	N/A	Brand name to search for in LLM snippets.
source	String	Yes	N/A	Country code for the regional prompt database (e.g., `us` for United States results). For acceptable values, see Regional database codes.
sort	String	No	`volume`	Field to sort the results by: `volume`, `type`, `snippet_length`.
sort_order	String	No	`desc`	Sort order for the results: • `asc` – for ascending • `desc` – for descending
limit	Integer	No	`100`	Maximum number of prompts to return per page (max 1000).
offset	Integer	No	`0`	Starting position for the paginated list.
filter	Object	No	N/A	Object for filtering results. See the Filtering results section for details.

Request example

Copy

curl --location 'https://api.seranking.com/v1/ai-search/prompts-by-brand?brand=Netflix&source=us&engine=perplexity&sort=volume&sort_order=desc&offset=0&limit=10' \

--header 'Authorization: Token YOUR_API_KEY'

Response parameters

If successful, the server returns a JSON object containing a list of prompts that mention the specified brand.

Parameter	Type	Description
total	Integer	Total number of times the brand has been mentioned in the specified LLM for the current month.
date	String	Date of the data snapshot in `YYYY-MM-DD` format.
prompts	Array	Array of objects, each representing a found prompt. See the structure below for details.

Each object in the prompts array has the following structure:

Parameter	Type	Description
prompt	String	User query or prompt text that triggered the LLM response.
volume	Integer	Estimated monthly search volume for the prompt.
type	String	Type of appearance for the target in the LLM result (e.g., `Link`, `Brand`).
answer	Object	Object containing the detailed response from the LLM.

The answer object contains the following fields:

Parameter	Type	Description
text	String	Full text of the snippet generated by the LLM.
links	Array	Array of URL strings that were included as links within the LLM’s answer.

Response example

Copy

{

    "total": 5448,

    "date": "2025-09-01",

    "prompts": [

        {

            "prompt": "peliculas en netflix",

            "volume": 14800,

            "type": "Link",

            "answer": {

                "text": "Hay una gran variedad de peliculas disponibles en Netflix...",

                "links": [ "[https://movies.sitioficial.netflix.com/browse/genre/34399](https://movies.sitioficial.netflix.com/browse/genre/34399)" ]

            }

        }

    ]

}

Filtering results

The Get prompts by target and Get prompts by brand endpoints support advanced filtering to refine your search results. The filter parameter is passed as an object in the query string.

Range filters (`volume`, `keyword_count`, `characters_count`)

These filters allow you to specify a numeric range for your results. Both from and to values are inclusive. You can use one or both to define the range.

To get values greater than or equal to a number: Use filter[<parameter>][from]=<value>.
- Example: filter[volume][from]=100 returns prompts with a search volume of 100 or more.
To get values less than or equal to a number: Use filter[<parameter>][to]=<value>.
- Example: filter[keyword_count][to]=5 returns prompts with 5 or fewer words.
To get values within a specific range: Use both from and to.
- Example: filter[characters_count][from]=10&filter[characters_count][to]=50 returns prompts that are between 10 and 50 characters long.

Text search filters (`multi_keyword_included`, `multi_keyword_excluded`)

These filters allow you to include or exclude specific keywords from the prompt text.

multi_keyword_included: A URL-encoded JSON string specifying keywords that must be present in the prompt.
multi_keyword_excluded: A URL-encoded JSON string specifying keywords that must not be present in the prompt.

For details on how to structure the JSON for these filters, please refer to the Text search JSON structure documentation.

AI Search

You are reading the Data API docs

Get AI search overview

Request parameters

Request example

Response parameters

Response example

Get AI search leaderboard

Request parameters

Request example

Response parameters

Response example

Discover brand by URL

Request parameters

Request example

Response parameters

Response example

Get prompts by target

Request parameters

Request example

Response parameters

Response example

Get prompts by brand

Request parameters

Request example

Response parameters

Response example

Filtering results

Range filters (volume, keyword_count, characters_count)

Text search filters (multi_keyword_included, multi_keyword_excluded)

Learn how SE Ranking’s API can boost your SEO!

Request a free demo to see our tools and integrations in action

Range filters (`volume`, `keyword_count`, `characters_count`)

Text search filters (`multi_keyword_included`, `multi_keyword_excluded`)