AI Responses
API + MCPRequests to this endpoint consume API units based on the
promptsparameter: requests returning only custom prompt data are free, while requests including Ahrefs prompt data follow standard API unit pricing.
Query parameters
A comma-separated list of fields to return.
The filter expression. The following column identifiers are recognized (this differs from the identifiers recognized by the select parameter).
The number of results to return.
The date to search for in YYYY-MM-DD format.
AI visibility reports are switching to AI adjusted volume. It better estimates demand for AI responses across chatbots and AI search surfaces. It is calculated by adjusting Google search volume for each AI platform’s estimated usage compared with Google. This param will be deprecated on August 31, 2026; all requests will use new AI adjusted volume.
A comma-separated list of two-letter country codes (ISO 3166-1 alpha-2).
A column to order the results by.
The ID of the report to use. If one is given, other parameters are taken from the report (brand, competitors, market, country, filters). If country or filters are provided, they override the ones in the report. You can find it in the URL of your Brand Radar report in Ahrefs: https://app.ahrefs.com/brand-radar/reports/#report_id#/...
The type of prompts to use. If not specified, both will be used. Custom prompts require a report_id to be provided.
A comma-separated list of chatbot models. All models can be combined with each other. claude module supports only custom prompts.
The google_ai_overviews_keywords and google_ai_mode_keywords models report AI Overviews / AI Mode visibility derived from Google search queries (keywords) rather than prompts.
A comma-separated list of the niche markets of your brands. Deprecated on 2026-05-18, this parameter will have no effect shortly after this date.
A comma-separated list of competitors of your brands.
A comma-separated list of brands to search for. At least one of brand, competitors, market or where should not be empty.
The output format.
Responses
The country of the question.
The chatbot model that generated the response.
The date when the data was last updated.
(10 units) The links used for the response.
The question asked by the user.
(10 units) The response from the model.
The search query used by the chatbot to find information for the response. Note: if data_source does not include chatgpt or perplexity, this field will always be empty.
Tags assigned to the query.
(10 units) Estimated monthly searches. This is based on our estimates for Google, combining the search volumes of related keywords where this question appears in People Also Ask section.