> ## Documentation Index > Fetch the complete documentation index at: https://docs.markifact.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Llm Mentions > Search the DataForSEO database of AI answers (Google AI Overviews and AI Mode, plus ChatGPT for the United States in English) for answers that mention a brand, keyword or domain, and return the pro... Search the DataForSEO database of AI answers (Google AI Overviews and AI Mode, plus ChatGPT for the United States in English) for answers that mention a brand, keyword or domain, and return the prompts, answers, cited sources and AI search volume. Core AI visibility data for AEO and GEO; needs the DataForSEO LLM Mentions subscription. | | | | -------------------- | ----------------------------- | | **App** | DataForSEO | | **Operation ID** | `dataforseo_get_llm_mentions` | | **Type** | Action | | **Connection** | `dataforseo` (required) | | **Credits per run** | Free | | **Agent / MCP tool** | Yes | ## Inputs | Field | Type | Required | Default | Description | | -------------------- | -------------------------- | -------- | ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `domains` | string or array of string | No | - | Domains that must appear in the AI answer, as a list or newline/comma-separated text (bare domains such as ahrefs.com). Use this to track a brand's website being cited or linked. At least one domain or keyword is required; up to 10 targets in total. | | `keywords` | string or array of string | No | - | Words or phrases that must appear in the AI answer, question or named brands, e.g. a brand name or a product category. List or newline/comma-separated text. All included domains and keywords must match together (AND). | | `excluded_domains` | string or array of string | No | - | Domains that must NOT appear in the matched answers, e.g. wikipedia.org. | | `excluded_keywords` | string or array of string | No | - | Words or phrases that must NOT appear in the matched answers. | | `domain_scope` | string or SelectableOption | No | `any` | Where a domain has to appear: 'any' (default), 'sources' (cited in the answer) or 'search\_results' (retrieved by the web search behind the answer; ChatGPT only). | | `keyword_scope` | string or SelectableOption | No | `any` | Where a keyword has to appear: 'any' (default), 'question' (the user prompt), 'answer' (the AI answer text), 'brand\_entities' (brands named in the answer) or 'fan\_out\_queries' (the follow-up searches the model ran). | | `keyword_match_type` | string or SelectableOption | No | `word_match` | 'word\_match' (default) matches whole words, so 'light' also matches 'light bulb'; 'partial\_match' matches substrings, so 'light' also matches 'lighting'. | | `include_subdomains` | boolean | No | `True` | Also match subdomains of the target domains, which includes the [www](http://www). host most sites are cited under. Defaults to true; turn it off to count only the bare domain. | | `platform` | string or SelectableOption | No | `all` | AI platform: 'all' (default), 'google' (Google AI Overviews and AI Mode) or 'chat\_gpt'. ChatGPT data exists for the United States in English only; every other location and language is Google only. | | `location` | string or SelectableOption | No | `2840` | Country or location: a two-letter country code (us, gb, de...), a DataForSEO location code (2840 = United States) or a full location name. Defaults to the United States. Only locations listed by DataForSEO for LLM Mentions have data. | | `language` | string or SelectableOption | No | `en` | Language code of the AI answers, e.g. en, de, es, fr, nl. Defaults to en. | | `filters` | array of FilterItem | No | - | Up to 8 filters on ai\_search\_volume, model\_name, platform, location\_code, language\_code, is\_web\_search\_based, first\_response\_at or last\_response\_at, e.g. ai\_search\_volume GREATER\_THAN 100. | | `orders` | array of OrderItem | No | - | Sort by up to 3 of the filterable fields, e.g. ai\_search\_volume DESC or last\_response\_at DESC. | | `limit` | integer | No | `20` | Maximum number of AI answers to return (1 to 1000). Defaults to 20. Each answer is a full markdown response with its sources, so keep this small; DataForSEO also bills per row on top of the request fee. | | `offset` | integer | No | - | Number of answers to skip, for paging. | | `fields` | string or array of string | No | - | Result columns to keep: platform, model\_name, question, answer, ai\_search\_volume, monthly\_searches, sources, search\_results, brand\_entities, fan\_out\_queries, is\_web\_search\_based, first\_response\_at, last\_response\_at, location\_code, language\_code. Leave empty for the default set listed in the output description. | ### FilterItem | Field | Type | Required | Default | Description | | ---------- | -------------------------- | -------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `field` | string or SelectableOption | Yes | - | The field to filter on, must be one of the current selected metrics or dimensions. | | `operator` | string | Yes | - | The operator to use for filtering. Must be one of the supported values. Use REGEXP\_MATCH to search/filter by multiple OR values like '.*(summer\|holiday).*' | | `value` | string | Yes | - | The value to filter by, always as a string: text, a number, or a regex. For IN\_LIST and NOT\_IN\_LIST, pass the values as one comma-separated string such as 'a,b,c', not as an array. For regex values, escape backslashes once in the JSON string: write \b for a word boundary, not \b. | ### OrderItem | Field | Type | Required | Default | Description | | ----------- | -------------------------- | -------- | ------- | -------------------------------------------------------------------------------- | | `field` | string or SelectableOption | Yes | - | The field to sort by. must be one of the current selected metrics or dimensions. | | `direction` | string | Yes | - | The order to sort by, must be one of 'ASC', 'DESC' | ### SelectableOption | Field | Type | Required | Default | Description | | ------- | ------ | -------- | ------- | ----------- | | `value` | string | Yes | - | | | `label` | string | Yes | - | | ## Output **Type**: `List[Dict]` Returns one row per AI answer with DataForSEO's fields flattened to dotted columns. Default columns: platform, model\_name, question, answer (markdown), ai\_search\_volume, sources (list of title, domain, url, snippet...), brand\_entities (list of title, category), is\_web\_search\_based, last\_response\_at. Other columns available through fields: monthly\_searches, search\_results, fan\_out\_queries, first\_response\_at, location\_code, language\_code. **Fields**: `platform`, `model_name`, `question`, `answer`, `ai_search_volume`, `sources`, `brand_entities`, `is_web_search_based`, `last_response_at` **Example**: ```json theme={"dark"} [ { "platform": "google", "question": "best backlink checker", "answer": "Popular backlink checkers include Ahrefs and Semrush...", "ai_search_volume": 1300 } ] ```