Is this the OpenAI API?

No. The OpenAI API answers from a model you pick, without ChatGPT's search, product cards or citations. This endpoint returns what ChatGPT itself shows a person on chatgpt.com, which is what matters when you want to know how ChatGPT presents your brand or category.

How much does it cost?

4 credits per answer, $4.00 → $2.40 per 1,000 answers depending on the pack. A cached answer (max_age) costs half. Failed, refused and empty answers are free.

How long does an answer take?

Usually 10 to 30 seconds (about 17 at the median), rarely up to 90. Keep the HTTP timeout at 120 s or more (the SDKs do), or use batches and monitors so nothing waits on the call.

The free model ChatGPT gives logged-out visitors; the response names it in model. Signed-in and paid plans can use other models, which we can't ask since we never log in.

Do you log in to the assistant?

No. Every prompt is asked the way a logged-out visitor asks it, in a standard browser, and we never use accounts or anything behind a login. Assistants that ask every logged-out visitor to sign in are not offered.

Why does the answer change between runs?

Assistants don't give the same answer twice: wording, sources and products vary from run to run and by country. For tracking, ask each prompt several times (a batch or a monitor) and count how often you're named or cited, rather than reading one answer.

How do I track my brand in the answer?

Pass track with up to 20 brands and domains. Each comes back in mentions: whether the text names it, whether a cited source is on it, which sources and products match, and how early the text first names it (text_position, 0 to 1).

Can I run hundreds of prompts?

Yes. Send up to 100 prompts per call to POST /v1/batches with endpoint: "chatgpt" and collect the answers from a signed webhook. AI answers cost the same in the batch lane (no 0.5× discount), because each one holds a browser for 10–30 s.

POST /v1/chatgpt

ChatGPT Scraper API

See what ChatGPT tells people. Send a prompt and get the answer ChatGPT gives a logged-out visitor on chatgpt.com, with the sources it cited, the products and local places it showed, and whether it named or cited the brands you track.

Updated Oct 28, 2026

Get a free API key Try it in the dashboard

4 credits per answer (10–30 s), the same in batches 2,500 free credits, no card Failed calls are free

Overview

What the ChatGPT Scraper API does

POST /v1/chatgpt opens chatgpt.com as a logged-out visitor in a standard browser, sends your prompt and waits for the full answer. You get it as plain text and as markdown whose [n](link) citations match sources[].position, plus the products cards and places (local businesses) ChatGPT showed, and model, the free model ChatGPT gives guests.

web_search is on by default, so ChatGPT searches the web the way the ChatGPT search results page does; set it to false to let ChatGPT decide, as a casual user would (it then searches for about two thirds of shopping and local prompts). ChatGPT localises prices, shops and places to where the visitor is: country asks as a visitor in that country, and without it the visitor is usually in the US or EU.

Add track (up to 20 brands or domains) and the response carries mentions: for each term, whether the text names it, whether a cited source is on it, and which sources and products match. That is the building block for AI visibility (GEO) tracking: run a prompt set through POST /v1/batches, or let a monitor ask on a schedule.

What you get

request object: The normalised request: endpoint, prompt, country, language (not chatgpt), web_search (chatgpt), include_html.
text string: The answer as plain text.
markdown string: The answer as Markdown. Citations are n, where n is the position of a source in sources.
html string: The answer's HTML, only with include_html: true.
model string: The model the assistant reports to logged-out visitors, when it reports one.
sources[] array: position (the n in the citations), title, link, domain, snippet, date, cited (true: cited inline in the answer; false: only listed beside it).
search_queries[] array: The searches the assistant ran to answer (its fan-out), where it shows them.
products[] array: Product cards shown with the answer: position, title, brand, price (as shown), extracted_price, currency (ISO 4217 when unambiguous), rating, reviews, merchant, link, image, description.
places[] array: Local businesses the answer showed, same shape as /v1/maps results.
related_questions[] array: Follow-up questions the assistant suggested.
mentions[] array: Only with track, one per term: term, mentioned (the answer text names it), cited (a cited source matches it), sources (positions of matching sources, cited or listed), products (positions of matching products), text_position (where the text first names it, 0 = start to 1 = end; -1 when it doesn't). See AI visibility tracking.
meta object: request_id, credits_used, cached, cached_at, engine (the assistant), latency_ms, parse_quality.

Request

POST /v1/chatgpt

cURL

Python

TypeScript

fetch

PHP

curl https://api.serpkite.com/v1/chatgpt \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"What are the best CRMs for a 10-person startup?","track":["hubspot.com","Pipedrive"]}'

Response (illustrative; answers vary from run to run)

200 OK · application/json

{
  "request": {
    "endpoint": "chatgpt",
    "prompt": "What are the best CRMs for a 10-person startup?",
    "country": "us",
    "web_search": true
  },
  "text": "For a 10-person startup, HubSpot CRM and Pipedrive are the usual shortlist. HubSpot's free plan covers contacts, deals and email tracking, and paid tiers add automation as you grow. Pipedrive is built around a visual sales pipeline and is quick to set up. Zoho CRM is the budget pick with a free plan for up to three users.",
  "markdown": "For a 10-person startup, **HubSpot CRM** and **Pipedrive** are the usual shortlist [1](https://www.example.com/best-crm-for-startups).\n\n- **HubSpot CRM**: the free plan covers contacts, deals and email tracking; paid tiers add automation [2](https://www.hubspot.com/products/crm).\n- **Pipedrive**: built around a visual sales pipeline, quick to set up [1](https://www.example.com/best-crm-for-startups).\n- **Zoho CRM**: the budget pick, free for up to three users [3](https://www.example.org/crm-pricing-2026).",
  "model": "instant",
  "sources": [
    {
      "position": 1,
      "title": "The best CRM software for startups in 2026",
      "link": "https://www.example.com/best-crm-for-startups",
      "domain": "example.com",
      "snippet": "We tested 14 CRMs with small sales teams…",
      "cited": true
    },
    {
      "position": 2,
      "title": "Free CRM software | HubSpot",
      "link": "https://www.hubspot.com/products/crm",
      "domain": "hubspot.com",
      "cited": true
    },
    {
      "position": 3,
      "title": "CRM pricing compared (2026)",
      "link": "https://www.example.org/crm-pricing-2026",
      "domain": "example.org",
      "date": "2026-09-14",
      "cited": true
    }
  ],
  "search_queries": [],
  "products": [],
  "mentions": [
    {
      "term": "hubspot.com",
      "mentioned": false,
      "cited": true,
      "sources": [
        2
      ],
      "text_position": -1
    },
    {
      "term": "Pipedrive",
      "mentioned": true,
      "cited": false,
      "sources": [],
      "text_position": 0.071
    }
  ],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 5,
    "cached": false,
    "engine": "chatgpt",
    "latency_ms": 31840,
    "parse_quality": "ok"
  }
}

Every response also carries X-Credits-Used, X-Credits-Remaining, X-Cache and X-Tokens-Estimate headers. Full endpoint reference

Measured Oct 28, 2026

How ChatGPT Scraper API behaves on this endpoint

About 20 logged-out ChatGPT prompts (shopping, local and how-to), each asked as a new visitor.

Answered: Every prompt in the test; no sign-in wall for logged-out visitors
Time to full answer: Median about 17 s; most within 10–30 s
Web search: With web_search (default): every prompt searched. Without it: about two thirds of shopping and local prompts
Localisation: Prices and shops follow the country it is asked from (euros from Finland, pounds from the UK)
Search queries: ChatGPT doesn't show guests the searches it ran: search_queries is empty

Filters and limits

prompt up to 4,000 characters; one turn per request (no conversation history).
country asks as a visitor in that country; language is not accepted, the answer follows the prompt's language.
Answers are cached for at most an hour and read only with max_age (half price).
include_html adds the answer's HTML; format: "markdown" returns the answer with a Sources list and, with track, a Mentions section.

AI visibility

Is your brand in the answer?

track takes up to 20 brands ("Pipedrive") and domains ("hubspot.com", subdomains match).
Each comes back in mentions: named in the text, cited, the matching sources and products, and how early it's named (text_position, 0 to 1).
A monitor asks the prompt hourly, daily or weekly and reports every answer with its mentions and new_sources, to a signed webhook. Each run costs 4 credits.
Answers vary between runs: ask each prompt several times and track how often you're named. AI visibility guide

mentions (illustrative)

{
  "mentions": [
    {"term": "hubspot.com", "mentioned": true, "cited": true, "sources": [2,5], "products": [], "text_position": 0.08},
    {"term": "Pipedrive", "mentioned": true, "cited": false, "sources": [], "products": [], "text_position": 0.41},
    {"term": "Acme CRM", "mentioned": false, "cited": false, "sources": [], "products": [], "text_position": -1}
  ]
}

POST /v1/monitors

cURL

Python

TypeScript

fetch

PHP

curl https://api.serpkite.com/v1/monitors \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpoint":"chatgpt","prompt":"What are the best CRMs for a 10-person startup?","track":["hubspot.com","Pipedrive","Acme CRM"],"interval":"daily","webhook_url":"https://example.com/hooks/serpkite"}'

Reference

Parameters

The fields /v1/chatgpt accepts in its JSON body.

ChatGPT Scraper API parameters
Name	Type	Default	Description
`prompt` required	string	–	The message to the assistant, up to 4,000 characters. Required. (q is not accepted here.)
`web_search`	boolean	true	Make ChatGPT search the web before answering. false lets it decide (it then searches for about two thirds of shopping and local prompts).
`country`	string	–	Ask as a visitor in this country (ISO 3166-1 alpha-2). ChatGPT localises prices, shops and places to where the visitor is. Without it the visitor is usually in the US or EU, and request.country shows the default us.
`track`	string[]	–	Up to 20 brands ("Acme") or domains ("acme.com", subdomains match), 100 characters each, to check the answer for. Each comes back in mentions. A term with a dot is a domain: it matches sources and product links on that domain; other terms match whole words, case-insensitively.
`include_html`	boolean	false	Also return the answer's HTML in html.
`format`	string	json	markdown returns the answer, its sources, searches, products and a Mentions section as one Markdown document; compact keeps text, sources (n, title, link), search_queries, products and places. Values: json, markdown, compact.
`fields`	string	–	Comma-separated projection, e.g. results.title,results.link,knowledge_graph. Cuts tokens.
`max_age`	integer	–	Accept a cached answer up to this many seconds old, at half price. Answers are cached for at most 1 hour, and only a request with max_age reads the cache.

Full reference, error codes and headers are in the /v1/chatgpt reference. Queue up to 100 prompts with POST /v1/batches, at the same price per answer.

Use cases

What people build with the ChatGPT Scraper API

AI visibility (GEO) tracking

Ask the prompts your buyers ask and see whether the answer names you, cites your domain or lists your product.

Share of answer over time

A monitor asks the same prompt hourly, daily or weekly and reports every answer with its mentions and new sources.

Citation research

Find which pages and domains the assistant cites for your category, then fix or pitch the ones that matter.

Agent tool

Give an agent a second opinion from a public assistant through the MCP tool or one SDK call.

Pricing