# AI Answer Scraper - ChatGPT, Perplexity, Gemini & AI Mode

> Answers and cited sources from ChatGPT, Perplexity, Gemini, Google AI Mode, Google AI Overviews and Claude for your prompts. Same input as Apify's AI scrapers (queries, countryCode). Licensed data, no logins, no browser. $0.015 per answer. Built for GEO / AI search tracking and AI agents.

- Category: AI search visibility
- Price: $15 per 1,000 × ai answer, billed per result by Apify (no subscription); any other billed events are listed on the Store page. Cap any run with `maxTotalChargeUsd`.
- Store page: https://apify.com/wrenfield-data/ai-answer-scraper
- Human page: https://wrenfielddata.com/tools/ai-answer-scraper/
- OpenAPI 3 spec: https://api.apify.com/v2/acts/wrenfield-data~ai-answer-scraper/builds/default/openapi.json
- MCP tool: https://mcp.apify.com?tools=wrenfield-data/ai-answer-scraper (appears as `wrenfield-data--ai-answer-scraper`)

## Call it

Synchronous run that returns the dataset rows as JSON (use `/runs` for long jobs and poll; see the OpenAPI spec):

```bash
curl -X POST \
  "https://api.apify.com/v2/acts/wrenfield-data~ai-answer-scraper/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompts": ["What is the best CRM for a small business?"], "engines": ["chatgpt", "perplexity"], "country": "United States", "language": "English"}'
```

## Input

| Field | Type | Required | Default | Description |
|---|---|---|---|---|
| `prompts` | array |  |  | Questions to ask, one per line (up to 500 characters each, up to 500 prompts). Each prompt is sent to every selected engine. Coming from Apify's ChatGPT / Perplexity / Gemini / AI Mode scrapers? You can send your existing queries input unchanged instead. |
| `engines` | array |  | `["chatgpt", "perplexity"]` | Engines to ask. One answer row per prompt and engine. Default: ChatGPT + Perplexity. |
| `country` | string |  |  | Country the answers are localized to (web search location): name, 2-letter code or location code. Default: United States. |
| `language` | string |  | `"English"` | Language name or code (English, de). |
| `chatgptWebSearch` | boolean |  | `true` | Make ChatGPT search the web, so the answer has cited sources (what most users see for buying questions). |
| `includeAnswerText` | boolean |  | `true` | Turn off to get only citations, cited domains and brands (smaller output for agents). |
| `maxAnswerChars` | integer |  | `20000` | Answer text is cut to this length. |
| `queries` | string |  |  | Same as queries in Apify's AI scrapers: one query per line. Added to Prompts. When used, each row also gets Apify-style fields (query, text, sources, citationUrls). |
| `countryCode` | string |  |  | Lowercase 2-letter country code as in Apify's AI scrapers (e.g. us, gb). Used when Country is empty. |
| `perplexitySearch` | object |  |  | Accepted for compatibility with apify/perplexity-search-scraper. Images, related questions and search recency are not supported and are ignored (noted in the run summary). |
| `apifyCompatibleFields` | boolean |  |  | Add query, text, sources, citationUrls, relatedQuestions and images to every row, matching Apify's AI scrapers. Default: on when you use queries, off otherwise. |

## Example input

```json
{
  "prompts": [
    "What is the best CRM for a small business?"
  ],
  "engines": [
    "chatgpt",
    "perplexity"
  ],
  "country": "United States",
  "language": "English"
}
```

## Output fields

One flat row per result:

| Field | Type | Description |
|---|---|---|
| `prompt` | string | Prompt that was asked |
| `engine` | string | Engine key |
| `engine_name` | string | Engine name, e.g. ChatGPT |
| `model` | string | Model that answered, when reported (e.g. sonar, gpt-..., google-ai-mode) |
| `status` | string | ok = answer returned; no_answer = the engine showed no AI answer (e.g. no AI Overview for the query); error = the engine did not respond (not charged); incomplete = the engine returned a cut-off answer twice (not charged) |
| `answer_markdown` | string | Answer as markdown (images removed) |
| `answer_text` | string | Answer as plain text |
| `answer_word_count` | integer | Words in the answer |
| `citations` | array | Sources the answer cites: url, domain, title |
| `citation_count` | integer | Number of cited sources |
| `cited_domains` | array | Unique cited domains in order of first citation |
| `brands` | array | Brands and products the answer recommends, in the order they first appear (all engines). Each: name, rank, mentions, cited (the answer cites a domain of that brand), cited_domain, confidence (high/low), source (answer, provider or answer+provider). |
| `brands_mentioned` | array | Names of high-confidence brands, in answer order (ready for share-of-voice counts) |
| `first_brand` | string | First high-confidence brand the answer names (the "top pick") |
| `brand_entities` | array | Brands / products the engine highlighted (ChatGPT, Gemini) |
| `fan_out_queries` | array | Web searches the engine ran to answer (ChatGPT, Perplexity when reported) |
| `organic_results` | array | Google AI Overviews only: top organic results on the same page (rank, domain, url) |
| `country` | string | Country used |
| `language` | string | Language used |
| `response_time_secs` | number | Seconds the engine took to answer |
| `note` | string | Explanation when there is no answer |
| `scraped_at` | string | When the answer was retrieved (ISO 8601, UTC) |
| `query` | string | Apify-compatible alias of prompt (only with Apify-style input or apifyCompatibleFields) |
| `text` | string | Apify-compatible alias of answer_markdown |
| `sources` | array | Apify-compatible list of cited sources: id, title, url, section |
| `citationUrls` | array | Apify-compatible list of cited URLs |
| `relatedQuestions` | array | Apify-compatible field; always empty |
| `images` | array | Apify-compatible field; always empty |

## Notes

- Auth: an Apify API token as `Authorization: Bearer <token>`; the MCP server also supports OAuth sign-in.
- Failed or empty results are not charged on most tools; check the pricing on the Store page.
- Questions: hello@wrenfielddata.com