ChatGPT scraper API

Request

curl -X POST "https://api.answerline.dev/v1/monitor/chatgpt" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"What are the best running shoes for flat feet?","country":"US","include":{"markdown":true}}'

import { Client } from "@answerline/sdk";

const client = new Client({ apiKey: process.env.API_KEY! });
const answer = await client.monitor.chatgpt({
  "prompt": "What are the best running shoes for flat feet?",
  "country": "US",
  "include": {
    "markdown": true
  }
});

import os
from answerline import Client

with Client(os.environ["API_KEY"]) as client:
    answer = client.monitor.chatgpt(
        prompt="What are the best running shoes for flat feet?",
        country="US",
        include={
            "markdown": True
        },
    )

Every request option is on the ChatGPT reference page.

What you get back

Full field definitions are on the ChatGPT reference page.

Answers from inside any US state

Send state with a two-letter code and ChatGPT and Gemini answer from inside that state, as a person there sees it. All 50 states and DC are covered; GET /v1/states?country=US lists the codes.

{ "prompt": "best pizza near me", "state": "TX" }

A state implies country "US"; with any other country the request is refused with a 400. The price is the same with or without a state. result.provenance.requestedState echoes the state. On 2026-11-09, “best pizza near me” with TX was answered for San Antonio; without a state, for New York. Every other engine accepts state and answers for the whole US (coverage).

ChatGPT state targeting covers who uses it and a 51-state batch in Python and TypeScript.

The app answer versus OpenAI’s developer API

This endpoint returns the answer a ChatGPT user sees. OpenAI’s developer API returns a completion you generate yourself, and the two answer different questions.

The developer API has a web search tool. Its guide (checked 2026-09-17, developers.openai.com) says the response carries url_citation annotations with the URL, title and location of each cited source, a separate sources list of every URL retrieved, the search actions the model took, and an optional user location (country, city, region, timezone). The guide does not describe shopping cards or ads. You also choose the model, system prompt and tool settings, so the output reflects your configuration.

When a brand manager asks whether ChatGPT recommends them, they mean the app. A completion with your own settings is a proxy you would have to validate against the app anyway.

The app also shows products from its shopping search, which the developer API does not describe. They are returned here as inlineProducts. For e-commerce brands those products decide visibility.

Citation fields here describe presentation. citationPills records which sources were grouped into each inline chip. sources[].footnote would mark a source listed but cited by no chip; it is false on every answer served today, since every listed source is cited by a chip. That is closer to what a reader clicks than a list of retrieved URLs. Provider model APIs vs the answers users see compares the two side by side.

An annotated response

The excerpt follows the result schema for POST /v1/monitor/chatgpt. Values are illustrative; the request set include.markdown, include.searchQueries and include.shopping to true.

{
  "success": true,
  "result": {
    // Plain answer text; markdown is present because include.markdown was true.
    "text": "For flat feet, look for stability shoes with a firm midsole...",
    "markdown": "For **flat feet**, look for stability shoes with a firm midsole...",
    // Every cited page, in order. datePublished is omitted when unknown, never null.
    "sources": [
      {
        "position": 1,
        "url": "https://www.example-running.com/guides/flat-feet",
        "label": "Best Running Shoes for Flat Feet",
        "description": "We tested stability models on...",
        "footnote": false,
        "datePublished": "2026-08-02"
      }
    ],
    // One entry per (chip, source) pair. ChatGPT's citationPillId starts at 0.
    // position points into result.sources (1-based).
    "citationPills": [
      {
        "url": "https://www.example-running.com/guides/flat-feet",
        "label": "Best Running Shoes for Flat Feet",
        "domain": "example-running.com",
        "citationPillId": 0,
        "type": "searchResult",
        "position": 1
      }
    ],
    // Products from ChatGPT's shopping search, each once. Present only when include.shopping is true.
    "inlineProducts": [
      {
        "render_as": "inline",
        "product": {
          "title": "Example Stability Runner 5",
          "position": 1,
          "id": "1234567890",
          "url": "https://www.example-store.com/p/stability-runner-5",
          "price": "$139.95",
          "image_urls": ["https://images.example-store.com/runner-5.jpg"],
          "offers": [
            {
              "merchant_name": "Example Store",
              "product_name": "Example Stability Runner 5",
              "url": "https://www.example-store.com/p/stability-runner-5",
              "price": "$139.95",
              "available": true
            }
          ]
        }
      }
    ],
    // Every brand and product the answer names: ChatGPT's full name for it and its category.
    "entities": [{ "type": "product", "name": "Example Stability Runner 5" }],
    // Nullable.
    "model": null
  }
}

result.provenance says how an answer was obtained (all fields). interface is the surface that answered and loginState is signed_out. Each request is a new conversation with your prompt unchanged. model is absent when ChatGPT names none. complete is always true: if ChatGPT never finishes an answer, the request fails, uncharged. wireCaptured says whether rawWire could be filled.

Notes for this engine

Fields in your client

• shoppingCards and inlineProducts are absent when include.shopping is off. A requested list (searchQueries, ads, shoppingCards, inlineProducts) is an empty array when it has nothing. searchQueries, ads and shoppingCards are empty on the ChatGPT answers served today.
• inlineProducts holds the products from ChatGPT’s shopping search. entities lists every brand and product the answer names, those products too. Its name is ChatGPT’s full name for it, which can differ from the words in text; its type is its category (product, software, …). With include.shopping, an entity ChatGPT links to a product also carries product: its price, URL and merchant offers, in the shape of an inline product. entities is absent and citationPills empty when there are none.
• map holds the local businesses the answer names as cards (restaurants, shops), each once in answer order: name, address, latitude, longitude, categories, rating, reviewCount, description, phone, websiteUrl, ChatGPT’s own id and provider for it, and position. The same businesses are in entities with type local_business.
• images holds the pictures the answer shows beside what it names: thumbnail (the picture), url (the page it comes from), title and sizes. map and images are absent when the answer has none.
• model is nullable.
• No merchant field is filled on a product: read offers[0].merchant_name.
• product.position in inlineProducts is its own 1-based sequence. In shoppingCards it is a flat rank across all cards, not reset per card.

Answers vary between runs

The same prompt, market and hour can produce different text, sources and products, so one run per prompt tells you little. Run each prompt several times per period, store every sample, and report rates (“cited in 7 of 10 runs”) with the sample size. Put the sample number in the idempotency key (...-s3-2026-09-17) so samples are distinct tasks. Answer volatility and sampling vs census cover how many samples to take.

Prompt wording is a variable

Small wording changes shift answers. Freeze the prompt set, version it, and change it deliberately; see prompt set design.

Domains and pages are different metrics

Count citation share on citationPills[].domain for domains and on sources[].url for pages. Mixing them in one metric makes the numbers meaningless.

Markets and search

The finest market is a US state; there is no city-level option. For multi-market studies, keep the prompt text identical and vary only the market, so differences are attributable to it. How to see ChatGPT answers by US state runs one prompt in all 51, and the state-level answers post walks through a larger design.

ChatGPT decides for itself whether to search the web on every answer served today, so disableWebSearch is accepted and changes nothing (provenance.searchMode is engine-default). legacy is accepted and does not change the answer.

Related: ChatGPT state targeting, AI visibility tracking, measuring brand mentions in ChatGPT, competitor analysis, keyword research, ChatGPT shopping cards.

From the blog

Docs

• Quickstart
• API reference
• Engine features
• Async tasks and batches
• Webhooks
• Coverage
• Pricing and failures
• Rate limits

Other engines