ChatGPT Answers API: Perplexity, AI Overviews, AI Mode, Copilot
Pricing
from $3.20 / 1,000 ai answers
ChatGPT Answers API: Perplexity, AI Overviews, AI Mode, Copilot
One row per answer: the full answer, every cited source (URL, domain, title, position), engine, model, country and time, from ChatGPT, Perplexity, Gemini, Claude, Grok, Google AI Overviews, Google AI Mode and Copilot. Live search by country, bulk questions, consensus, clean JSON.
Pricing
from $3.20 / 1,000 ai answers
Rating
0.0
(0)
Developer
Zaiq
Maintained by CommunityActor stats
0
Bookmarked
16
Total users
15
Monthly active users
8 days ago
Last modified
Categories
Features
Share
AI Answers API: ChatGPT, Perplexity, Gemini, Claude, Grok, Google AI Overviews, AI Mode and Copilot, with sources

Ask ChatGPT, Perplexity, Gemini, Claude, Grok, Google AI Overviews, Google AI Mode and Microsoft Copilot your questions in one run and get every answer with the sources it cites, searched live from the country you pick. Every engine returns the same row: the answer, its sources (position, URL, domain, title), the engine and model, country, language and time, as clean JSON for your app, sheet or agent.
Google AI Overviews, AI Mode and Copilot are read from Google's and Bing's own search pages, so they have no AI usage to pay. When Google shows no AI Overview or AI Mode answer for a search, the row says so (answer: null and a status saying why) and costs nothing. The AI assistants answer through their official APIs with their own web search, on fast low-cost models or each company's flagship.
Each question also gets a consensus report: the answer most engines support, what they agree and disagree on, claims only one makes, an agreement score and the sites more than one cited.
What you get
| Field | What it holds |
|---|---|
| Answer rows (every engine) | prompt, engine, model, surface, country, language, answer, citations (position, url, domain, title, site, kind), citationCount, citedDomains, searchUrl, seconds, answeredAt, status, charged, note |
| AI assistants | modelTier, webSearch, finishReason, aiCostUsd (the AI usage the gateway reported for that answer) |
| Pages read | pagesRead: pages Perplexity, Grok and Copilot read beyond the ones they cite, each with cited. Grok doesn't say which it used, so its citations stay empty unless it writes a link into its answer, with citationsUnknown: true |
| Google AI Mode | products: the product cards in the answer (product, price, currency, seller, rating, reviews, url) |
| No-answer rows (free) | answer: null, status no-ai-overview, ai-overview-loads-later, no-ai-mode or no-copilot-answer, and a note saying why; never charged |
| Consensus rows | consensus, agreeOn, disagreeOn (each engine's position), uniqueClaims, mostComplete, agreementScore, domainsCitedByMoreThanOne, enginesAnswered |
| SUMMARY | the models used, answers, no-answer searches and failures per engine, consensus reports, the AI usage reported |
What people use it for
- Track Google's AI answers: what Google's AI Overview and AI Mode say for your searches, and which sites they cite, country by country
- Compare the AIs: how ChatGPT, Gemini, Copilot and Google answer the questions your customers ask, and which sites each trusts
- Research with sources: answers to many questions at once, each with links to check
- Fact-checking: where eight engines agree, and where one stands alone
- Apps and agents: multi-engine answers through one API, without eight API keys or a SERP account
How to use it
- Add your questions, one per line.
- Pick the engines (AI assistants and AI search), the country to search from and the model tier.
- Click Start and open the Answers table: one row per question and engine, one consensus row per question.
Input
| Field | Example | Notes |
|---|---|---|
| Questions | What are the best project management tools for a small team in 2026, and what does each cost? | Each goes to every engine |
| AI assistants and AI search | ChatGPT, Perplexity, Gemini, Claude | Also Grok, google-ai-overview, google-ai-mode, copilot |
| Models | fast | flagship: what each assistant's app runs |
| Live web search | on | Off: the assistants answer from what they know |
| Country | US | Gemini takes no location; Google and Copilot search from the US when empty |
| Search language | de | Google and Copilot; empty: the country's own language |
| Consensus report | on | Two or more engines |
| Instructions | Answer in under 100 words | Sent to the assistants, not to Google or Copilot |
| Fixed models | {"chatgpt": "openai/gpt-6.1-sol"} | Any OpenRouter model |
Output
Each result is one row in the run's dataset (download it as JSON, CSV, Excel, XML or HTML, or read it through the API). An example row (values shortened):
{"prompt": "what is a heat pump","engine": "Google AI Mode","model": "google-ai-mode","modelTier": null,"surface": "google-ai-mode","webSearch": true,"country": "US","language": "en","answer": "A **heat pump** is a single, energy-efficient system that provides **both heating and cooling** for your home.[[1]](https://energy-agency.example/heat-pumps) Instead of burning fuel or using electricity to *generate* heat (like a gas furnace or an electric baseboard heater), a heat pump **moves heat** from one place to another… #### Main Types of Heat Pumps 1. **Air-Source Heat Pumps** … 2. **Geothermal (Ground-Source) Heat Pumps** …","citations": [{"position": 1,"url": "https://energy-agency.example/heat-pumps","domain": "energy-agency.example","title": "Pump Up Your Savings with Heat Pumps","site": "Energy agency","kind": "other"}],"citationCount": 1,"citedDomains": ["energy-agency.example"],"pagesRead": null,"citationsUnknown": false,"products": [],"searchUrl": "https://www.google.com/search?q=what%20is%20a%20heat%20pump&hl=en&gl=US&udm=50","finishReason": null,"aiCostUsd": null,"seconds": 24.9,"status": "ok","charged": true,"note": null,"answeredAt": "2026-11-12T14:32:10Z"}
A real Google AI Mode row from a cloud run on 12 November 2026, shortened, with the cited site's address replaced. Every engine returns this same row; the AI assistants also fill modelTier, finishReason and aiCostUsd. In that day's cloud runs (US, eight everyday questions): Google AI Mode answered 4 of 4 in 12 to 31 seconds, Copilot 4 of 4 in 18 to 38 seconds with 3 to 4 sources and the 6 to 11 pages it read, and Google showed an AI Overview for 6 of 8 searches with 3 to 6 sources each (the other two came back free with answer: null). Asked from Germany, AI Mode and Copilot answered in German with German sources. On 17 October, one pricing question to the five assistants on fast models gave 0 to 20 sources each and a consensus agreement score of 75 out of 100. A record named SUMMARY in the run's key-value store lists the models used, the answers and no-answer searches per engine, and what was charged.
Pricing
- $0.004 per answer: one engine's answer to one question, with its sources (ChatGPT, Perplexity, Gemini, Claude, Grok, Google AI Overview, Google AI Mode or Copilot)
- $0.004 per consensus report (one per question when two or more engines answered; switch it off to skip it)
- Free: failed answers and reports, and searches where Google or Copilot shows no answer (
answer: null) - The AI assistants' usage is billed by Apify's AI gateway at OpenRouter's rates. Measured 17 October 2026 on a hard pricing question, fast models: Perplexity Sonar $0.006, GPT-5.4 mini $0.02-0.03, Claude Haiku 5.5 $0.023, Grok 4.3 $0.049, Gemini 3.8 Flash $0.061 (Google charges per search, and it ran about four); the consensus report about $0.005. Flagship: GPT-6.1 Sol about $0.09 and Grok 4.7 $0.15-0.23 an answer (12 October); Apify charges free-plan accounts 10 times the AI usage. Google AI Overview, AI Mode and Copilot have no AI usage
What typical jobs cost at the list price:
| Job | Cost |
|---|---|
| 1 question to 4 assistants with a consensus (fast) | $0.02 + about $0.12 AI |
| 100 questions to Google AI Overview, AI Mode and Copilot | up to $1.20, no AI usage (searches with no answer are free) |
| 100 questions to Perplexity only | $0.40 + about $0.60 AI |
| 10 questions to all eight with a consensus (fast) | $0.36 + about $1.70 AI |
On Apify's Scale and Business plans the per-event prices are lower (Store discounts). Set Maximum cost per run and the Actor stops cleanly when it is reached: you never pay more than that.
Tips
- Google AI Overview, AI Mode and Copilot alone have no AI usage: the cheapest way to see what Google's and Bing's AI answer for your searches.
- Perplexity alone is the cheapest assistant for web answers with many sources.
- Use the flagship tier when you need the answers your customers see in each assistant's app.
- Shape the assistants' answers with Instructions: a length, a format (a table, a numbered list) or a role.
- Tracking whether the AIs name your brand? The AI Answer Tracker counts mentions and citations per brand.
Use it through the API
Python
from apify_client import ApifyClientclient = ApifyClient("<YOUR_APIFY_TOKEN>")run = client.actor("zaiq/ai-answers-api").call(run_input={"prompts": ["What are the best project management tools for a small team in 2026?"], "engines": ["chatgpt", "perplexity", "google-ai-overview", "google-ai-mode", "copilot"], "country": "US"})for row in client.dataset(run.default_dataset_id).iterate_items():print(row)
JavaScript
import { ApifyClient } from 'apify-client';const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });const run = await client.actor('zaiq/ai-answers-api').call({"prompts": ["What are the best project management tools for a small team in 2026?"], "engines": ["chatgpt", "perplexity", "google-ai-overview", "google-ai-mode", "copilot"], "country": "US"});const { items } = await client.dataset(run.defaultDatasetId).listItems();
HTTP (one call, results back)
curl -X POST 'https://api.apify.com/v2/acts/zaiq~ai-answers-api/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>' \-H 'Content-Type: application/json' \-d '{"prompts": ["What are the best project management tools for a small team in 2026?"], "engines": ["chatgpt", "perplexity", "google-ai-overview", "google-ai-mode", "copilot"], "country": "US"}'
Integrations and schedules
- Schedules: run it every hour, day or week from the Apify Console (Schedules) and keep a history of results.
- Make, Zapier, n8n, Google Sheets, Slack, Airtable: connect it through Apify's integrations, or send each finished run to a webhook.
- Datasets: results stay in the run's dataset; export them or read them by API whenever you need them.
Use it with AI agents (MCP)
Add Apify's MCP server with this Actor already pinned (https://mcp.apify.com?tools=zaiq/ai-answers-api) to Claude, ChatGPT, Cursor, VS Code or any MCP client. The agent can find this Actor and run it for you: ask it for "ask ChatGPT, Google AI Mode and Copilot this question and show me where they disagree". AI agents can also pay for runs directly through Apify's agentic payments.
Limits
- The assistants are their official APIs with their own web search, not the consumer apps: the apps add memory, personalisation and their own instructions, so their answers can differ.
- Google AI Overview, AI Mode and Copilot are read signed out, as a new visitor from the chosen country; a signed-in user's answer can differ.
- Google loads some AI Overviews only after its page has opened; those come back free with status
ai-overview-loads-later. - Copilot sometimes refuses a search on every route; that row fails free. If Microsoft asks for a human check, Copilot is not asked again in that run.
- On Apify's free plan, Google AI Overview, AI Mode and Copilot each answer the first 5 questions of a run.
- Answers change from run to run and as the models are updated.
- An assistant's answer can hold at most 2,048 tokens (about 1,500 words), the limit of Apify's AI gateway.
- Gemini does not take a location; Perplexity always searches the web.
FAQ
Do I need API keys for OpenAI, Anthropic, Google, xAI or a SERP service?
No. Apify's AI gateway runs every assistant and bills its exact usage to your Apify account; Google and Copilot need nothing.
Is it the real Google AI Overview and AI Mode?
Yes: the AI Overview from Google's own results page, and Google's own AI Mode answer, for the search as a signed-out visitor from the country you pick, with their sources (AI Mode also with its product cards).
What happens when Google shows no AI Overview?
The row comes back with answer: null, a status saying why (no-ai-overview, ai-overview-loads-later, no-ai-mode, no-copilot-answer) and a note, and it is not charged.
Is it the real ChatGPT?
It is OpenAI's model through OpenAI's API with OpenAI's own web search: the same model family as ChatGPT, not the chatgpt.com app.
Which models are used?
Each company's newest model in the tier you pick, chosen at the start of every run; the model is in every row. Fixed models pins any OpenRouter model.
Can I switch off web search?
Yes, and the assistants answer from what they know (Perplexity always searches). Google and Copilot always search.
Related Actors from Zaiq
- ai-answer-tracker: whether the AIs name and cite your brand
- google-ai-mode-tracker: Google AI Mode answers with brand mentions and citation share
- bulk-ai-runner: one prompt on every row of your data
- ai-web-scraper: any page to JSON with a prompt
- llm-website-crawler: sites as Markdown for your own AI
Support
Questions, a site that changed, or a field you need? Open an issue on this Actor's Issues tab: we answer there, usually within a day.
Also found as: chatgpt api, perplexity api, google ai overviews api, google ai mode api, ai overview scraper, ai mode scraper, copilot api, ai answers api, compare ai answers, gemini api, claude api, grok api, ai search api, multi llm api.