Irmu
AI Assistants

Claude API

Track Claude's answers, citations and brand mentions over time.

Start freePOST https://app.irmu.com/api/extract25 credits
Why

Why teams scrape Claude

Claude 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.

Different assistants cite different sources for the same question. Monitoring only one gives you a distorted picture of how your category is being summarized for buyers.

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, 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.

Use cases

What it powers

  • Cross-assistant comparison

    Diff answers between Claude, ChatGPT and Perplexity.

  • Source influence mapping

    Find which third-party pages shape your category's answers.

  • Positioning research

    See how assistants describe your differentiators unprompted.

  • Compliance review

    Log answers about regulated products for the record.

Data

Fields available

Everything below comes back typed and validated against your schema.

prompt

The query submitted

answer

Full response text

citations

Referenced sources

brands_mentioned

Brands named

sentiment

Tone of mention

captured_at

Run timestamp

Request

One call, no selectors

request.sh
curl -X POST https://app.irmu.com/api/extract \
  -H "Authorization: Bearer irmu_sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://claude.ai/new?q=compare+scraping+apis",
    "schema": {
      "prompt": "string",
      "answer": "string",
      "citations": "string",
      "brands_mentioned": "string",
      "sentiment": "string",
      "captured_at": "string"
    }
  }'
Response

Validated JSON

response.json
{
  "data": {
    "prompt": "compare scraping apis",
    "brands_mentioned": [
      "Irmu",
      "Apify"
    ],
    "sentiment": "neutral"
  },
  "credits_used": 25,
  "status": 200
}
SDKs

Copy, paste, ship

import requests

res = requests.post(
    "https://app.irmu.com/api/extract",
    headers={"Authorization": "Bearer irmu_sk_live_..."},
    json={
        "url": "https://claude.ai/new?q=compare+scraping+apis",
        "schema": {
            "prompt": "string",
            "answer": "string",
            "citations": "string",
            "brands_mentioned": "string"
        },
    },
)

data = res.json()["data"]
print(data)
Pricing

Simple credits

Per prompt run page

25 credits

Failed requests are retried automatically and never billed.

See full pricing →
FAQ

Claude API questions

Related

Often used together

ChatGPT API

Capture how ChatGPT answers your category questions, with citations.

Perplexity API

Answer engine results with the full citation graph.

Start extracting Claude data today

1,000 free credits every month. No card, no sales call.

Start freeRead the docs