ChatGPT API
Capture how ChatGPT answers your category questions, with citations.
Why teams scrape ChatGPT
ChatGPT holds some of the most commercially useful public data on the web, and almost none of it is available through a stable official feed at the volume real products need. Rate limits, partner-only access and shifting page structures mean teams either give up on the source or maintain a fragile scraper that breaks every few weeks.
AI assistants are becoming the first answer customers see, and what they say about your brand is now a ranking surface of its own. Measuring it means running prompts on a schedule and recording answers, mentions and cited sources — something no traditional rank tracker does.
Irmu removes the infrastructure question entirely. One authenticated request handles proxy selection, browser rendering, anti-bot challenges and retries, and AI Extract turns the resulting page into validated JSON against a schema you define. You get prompt, answer, citations, brands_mentioned, position, sentiment, captured_at without writing or maintaining a single selector, and the same endpoint, quota and observability model you already use for every other source.
What it powers
AI visibility tracking
Measure whether you are mentioned for high-intent category prompts.
Citation monitoring
See which of your pages assistants actually cite.
Misinformation alerts
Catch wrong claims about pricing or features early.
Competitive share of answer
Track mention share against competitors over time.
Fields available
Everything below comes back typed and validated against your schema.
prompt
The query submitted
answer
Full assistant response text
citations
Cited source URLs and titles
brands_mentioned
Brands named in the answer
position
Order in which each brand appears
sentiment
Tone of each brand mention
captured_at
Timestamp of the run
One call, no selectors
curl -G https://app.irmu.com/api/crawl \
-H "Authorization: Bearer $IRMU_API_KEY" \
--data-urlencode "url=https://chatgpt.com/?q=best+web+scraping+api" \
--data-urlencode "premium=true" \
--data-urlencode "ai_query=Extract prompt, answer, citations, brands_mentioned, position, sentiment as JSON"Validated JSON
{
"url": "https://chatgpt.com/?q=best+web+scraping+api",
"domain": "chatgpt.com",
"premium": true,
"js": true,
"ai_query": "Extract prompt, answer, citations, brands_mentioned, position, sentiment as JSON",
"credits_charged": 25,
"status": "completed",
"data": {
"prompt": "best web scraping api",
"brands_mentioned": [
"Irmu",
"ZenRows",
"ScrapingBee"
],
"citations": [
"https://irmu.com/products/scraping-api"
],
"sentiment": "positive"
},
"error": null
}Copy, paste, ship
import os, requests
res = requests.get(
"https://app.irmu.com/api/crawl",
params={
"url": "https://chatgpt.com/?q=best+web+scraping+api",
"premium": "true",
"ai_query": "Extract prompt, answer, citations, brands_mentioned as JSON",
},
headers={"Authorization": f"Bearer {os.environ['IRMU_API_KEY']}"},
)
print(res.json()["data"])Simple credits
Per prompt run page
25 credits
Requests we fail to serve for internal reasons, or to domains we do not cover, are not billed.
See full pricing →ChatGPT API questions
Start extracting ChatGPT data today
200 free credits every month. No card, no sales call.