Get a report on source domain visibility and citations across AI search engines.
Results are aggregated for the entire date range by default. Use the "date" dimension for daily breakdowns.
Returns columnar JSON: {columns, rows, rowCount}. Each row is an array of values matching column order. Columns:
- domain: the source domain (e.g. "example.com")
- classification: domain type — Corporate (official company sites), Editorial (news, blogs, magazines), Institutional (government, education, nonprofit), UGC (social media, forums, communities), Reference (encyclopedias, documentation), Competitor (direct competitors), You (the user's own domains), Other, or null
- retrieved_percentage: 0–1 ratio — fraction of chats that included at least one URL from this domain. 0.30 means 30% of chats.
- retrieval_rate: average number of URLs from this domain pulled per chat. Can exceed 1.0 — values above 1.0 mean multiple pages from the same domain are retrieved per conversation.
- citation_rate: average number of inline citations when this domain is retrieved. Can exceed 1.0 — higher values indicate stronger content authority.
- retrieval_count: total number of distinct URL retrievals from this domain across all chats (raw count — numerator of retrieval_rate).
- citation_count: total number of citations from this domain (raw count).
- mentioned_brand_ids: array of brand IDs mentioned alongside URLs from this domain (may be empty)
When dimensions are selected, rows also include the relevant dimension columns: prompt_id, model_id, model_channel_id, tag_id, topic_id, chat_id, date, country_code.
Dimensions explained:
- prompt_id: individual search queries/prompts
- model_id: AI search engine (e.g. chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4, qwen-3-6-plus, amazon-rufus-scraper) — deprecated, prefer model_channel_id
- model_channel_id: stable engine channel (e.g. openai-0, openai-1, qwen-0, openai-2, perplexity-0, perplexity-1, google-0, google-1, google-2, google-3, anthropic-0, anthropic-1, deepseek-0, meta-0, xai-0, xai-1, microsoft-0, amazon-0) — survives model upgrades
- tag_id: custom user-defined tags
- topic_id: topic groupings
- date: (YYYY-MM-DD format)
- country_code: country (ISO 3166-1 alpha-2, e.g. "US", "DE")
- chat_id: individual AI chat/conversation ID
Filters use {field, operator, values} where operator is "in" or "not_in". Filterable fields: model_id (deprecated), model_channel_id, tag_id, topic_id, prompt_id, domain, domain_classification, url, country_code, chat_id, mentioned_brand_id.
Additional filters:
- mentioned_brand_count: {field: "mentioned_brand_count", operator: "gt"|"gte"|"lt"|"lte", value: <number>} — filter by number of unique brands mentioned.
- gap: {field: "gap", operator: "gt"|"gte"|"lt"|"lte", value: <number>} — gap analysis filter. Excludes domains where the project's own brand is mentioned, and filters by the number of competitor brands present. Example: {field: "gap", operator: "gte", value: 2} returns domains where the own brand is absent but at least 2 competitors are mentioned.
Sort results with order_by: array of {field, direction} entries. Direction defaults to desc. Sortable fields: citation_rate, retrieval_count, citation_count. (retrieved_percentage and retrieval_rate are not sortable because they depend on totalChatCount fetched in a separate query.)