Sign in

v4

Swagger 2.0Proprietary2026-08-0173264.4 KB
Metrics

Per-prompt metrics summary

Paginated per-prompt aggregated metrics with optional breakdown=model. Citations and citation rate include visible citations and background source references; avg_position uses visible citations only.

get/metrics/prompt_summary

Query parameters

project_idinteger required

Project ID

rangeinteger

Number of days to look back

fromstring date-time
tostring date-time
breakdown'model'
model'chatgpt' | 'perplexity' | 'gemini' | 'ai_overview' | 'ai_mode' | 'copilot' | 'claude' | 'grok' | 'deepseek' | 'meta_ai' | 'amazon_rufus'

Filter by AI model. Models the API key's user has not enabled are silently dropped.

collection_idinteger
country_codestring
language_codestring
promptinteger
prompt_type'informational' | 'navigational' | 'commercial' | 'transactional'

Filter by prompt type (search intent).

brand_kind'brand' | 'brand_other' | 'non_brand'

Filter by brand kind: brand (own brand/products), brand_other (competitors/other brands), non_brand (generic, no brand named). For fair 1:1 brand-vs-competitor comparisons (visibility, share of voice), use non_brand: brand-focused prompts skew results toward the brand they name. The in-app Overview page applies non_brand by default.

sort'responses' | 'mentions' | 'citations' | 'mention_rate' | 'visibility' | 'citation_rate' | 'avg_mention_position' | 'avg_position'
sort_dir'asc' | 'desc'
pageinteger
per_pageinteger
output'flat' | 'csv'

Rectangular output for BI tools (Tableau, Excel, Sheets, ELT). Omit for the default nested JSON. 'flat' returns the same metadata plus 'columns' and 'rows'; 'csv' returns those rows as text/csv. Errors are always returned as JSON.

Response

Per-prompt metrics