What are fan-out queries?

Fan-out queries are the sub-questions an AI model generates internally while researching its answer to a user prompt. They represent the decomposition of a broad question into narrower information needs. If your content directly answers these sub-questions, you are more likely to be cited as a source.

How much does a request cost?

Each request costs approximately $0.10 via the DataForSEO LLM Mentions Search endpoint, regardless of whether you search by keyword or by domain.

What does the frequency ranking mean?

Fan-out queries are ranked by how often they appear across different parent questions. A higher frequency means the sub-question surfaces under multiple parent prompts, making it a higher-priority content target because answering it increases your citation chances across several queries.

What is the results limit slider for?

The slider (range 10 to 500, default 100) controls how many fan-out query results the API returns. A higher limit gives more comprehensive coverage but still counts as a single API call at the same cost.

Can I search by domain instead of keyword?

Yes. The tool supports both Keyword and Domain search modes. Domain mode returns the fan-out queries that led AI models to cite pages on that domain, which is useful for understanding why a competitor is being referenced.

How should I use the parent question mapping?

Each fan-out query maps back to the parent question that generated it. Use this mapping to build content clusters: group fan-out queries by their parent, then ensure your content answers the full set of sub-questions beneath each parent prompt.

Fan-Out Query Explorer: free AI Search tool

#about

Surfaces the fan-out queries (sub-questions) that ChatGPT generates when researching answers to queries in your topic space.

Queries the DataForSEO LLM Mentions Search endpoint by keyword or domain, deduplicates discovered fan-out queries, and ranks them by frequency.

Optionally clusters results by text similarity when scikit-learn is available.

Fan-out queries are only returned by the ChatGPT platform; Google AI Overviews do not provide them.

Platform: Python script (requires Python 3.x)
Input: DataForSEO API credentials (login and password)A keyword or domain to exploreLocation, language, and results limit settings
Output: Fan-out queries ranked by frequency with parent question mapping, plus a parent questions table with fan-out counts, AI search volume, and source counts.
Category: AI Search

Use cases

Planning content that answers the sub-questions AI uses to build answers
Discovering content gaps AI systems expose in your topic coverage
Understanding how AI breaks complex queries into research steps
Prioritising content creation by fan-out frequency

#features

Search by keyword topic or by domain mentions
ChatGPT platform (the only source that returns fan-out queries)
12 location and 8 language options
Fan-out query deduplication and frequency ranking
Optional TF-IDF clustering when scikit-learn is available (agglomerative, threshold 0.7)
Parent question mapping (which questions spawned each fan-out)
Summary metrics: parent questions, total fan-outs, unique fan-outs, average per question
CSV downloads for fan-out queries and parent questions

#how-to-use

Enter DataForSEO credentials in the sidebar
Select target type (Keyword or Domain)
Choose location and language
Enter your keyword or domain
Click Explore Fan-Out Queries
Review fan-out queries ranked by frequency
Download fan-out queries or parent questions CSV

#faq

What are fan-out queries?: Fan-out queries are the sub-questions an AI model generates internally while researching its answer to a user prompt. They represent the decomposition of a broad question into narrower information needs. If your content directly answers these sub-questions, you are more likely to be cited as a source.
How much does a request cost?: Each request costs approximately $0.10 via the DataForSEO LLM Mentions Search endpoint, regardless of whether you search by keyword or by domain.
What does the frequency ranking mean?: Fan-out queries are ranked by how often they appear across different parent questions. A higher frequency means the sub-question surfaces under multiple parent prompts, making it a higher-priority content target because answering it increases your citation chances across several queries.
What is the results limit slider for?: The slider (range 10 to 500, default 100) controls how many fan-out query results the API returns. A higher limit gives more comprehensive coverage but still counts as a single API call at the same cost.
Can I search by domain instead of keyword?: Yes. The tool supports both Keyword and Domain search modes. Domain mode returns the fan-out queries that led AI models to cite pages on that domain, which is useful for understanding why a competitor is being referenced.
How should I use the parent question mapping?: Each fan-out query maps back to the parent question that generated it. Use this mapping to build content clusters: group fan-out queries by their parent, then ensure your content answers the full set of sub-questions beneath each parent prompt.

/contact

Want me to run this for you? I run this tool as a managed service, or build something custom around your data. You get the insights without touching the code.

Send me a message →