Multi-AI Answer Snapshot
Pricing
from $25.00 / 1,000 prompt answereds
Go to Apify Store
Multi-AI Answer Snapshot
Pricing
from $25.00 / 1,000 prompt answereds
The questions people ask AI assistants, one per line, for example 'best project management software for a small team'. Each prompt is sent to every chosen assistant and charged once when at least one answers. Or use a dataset or file below.
Which assistants to ask, each with its own live web search. OpenAI's cost is included in the price. Perplexity, Gemini, Claude and Grok run through Apify's official OpenRouter proxy, and their model cost is billed to your Apify account at OpenRouter's rate (about $0.005 Perplexity, $0.013 Claude, $0.04 Gemini, $0.04 Grok per answer; 10x on Apify's free plan). Copilot and Meta AI have no public API.
[ "openai", "perplexity", "claude"]Your brand, product or website and your competitors', for example 'Asana' or 'monday.com'. Each answer reports whether each name is mentioned, in what order, and whether its site is cited. Optional.
An Apify dataset with one prompt per row, for example a keyword list. Every original column is kept and the AI shopping results are added alongside. Use the picker rather than typing an ID.
A public link to a CSV, TSV, Excel, JSON or JSON Lines file with one prompt per row. A normal Google Sheets link works: share it as 'Anyone with the link can view'. Used when no dataset is given.
Leave on 'Detect automatically' unless the link has no file extension and the server reports the wrong content type.
Which sheet to read from an Excel workbook. Defaults to the first sheet.
Rows as inline JSON, an alternative to a dataset or file. Each object needs a field holding the prompt.
The column that holds the prompt. Leave empty to detect it (prompt, query, question, keyword and similar names).
Optional column holding brands or websites to look for on that row only (comma separated), added to the list above.
Optional two-letter country code (US, GB, DE...) so answers and sources fit that country. A row's own 'country' column overrides it.
Keep the full written answer on each row.
Remember each prompt's result and report what changed since the last run, per assistant (your brand newly mentioned or dropped, moved in order, newly cited or no longer cited, new cited sites). Run it on a schedule. The first run records the starting point. Off by default.
Names the saved memory for monitor mode, so different watchlists do not mix. Use the same name on every scheduled run of one watchlist. Default: 'default'.
Filtering happens after each prompt is answered and charged.
Keep every column from the input row next to the results, so they line up with your own data.
How many prompts are asked in parallel (each goes to every chosen assistant at once).
A hard ceiling on how many rows are read from the input, as a safety net on a large dataset.
Also write the results as a downloadable CSV or Excel file, linked from the run's output. $0.01 per file, charged only when the run answered at least one prompt.
[]Also append every kept row to a named dataset that persists across runs, for example a history of checks. Not charged again.