~5 minutes. Then Claude can pull LinkedIn, X, Google Maps & more for deal diligence.
| Plan | Price | Monthly credit | Catch |
|---|---|---|---|
| Free | $0 | $5 | Many of the best scrapers block free-tier users |
| Starter ✓ | $29/mo | $29 usage | None — this is the pick |
| Scale | $199/mo | $199 | Overkill for our volume |
apify_api_…).🔒 Treat the token like a password. Paste it only into our Claude chat — not anywhere public. (This page is unlisted and holds no secrets.) You can rotate or scope it anytime from the same settings page.
Open token page →Every actor below is cookieless where it matters — no logging into your accounts, no ban risk. All prices are pay-per-result.
| What | Use | Cost |
|---|---|---|
| LinkedIn profiles | Founder background checks cookieless | $4 / 1,000 |
| LinkedIn companies | Headcount, growth | $3 / 1,000 |
| LinkedIn jobs | Hiring = traction signal | $1 / 1,000 |
| Twitter / X | Founder & company posts | $0.40 / 1,000 |
| Google Maps + reviews | Business diligence | ~$1–2 / batch |
| Website traffic (SimilarWeb) | Is traffic real & growing? Where from? cookieless | $1 / 1,000 |
| Website → markdown | Feed company sites into DRA | ~$0.02–0.50 / site |
| App Store / Play reviews | Consumer traction | $0.10–1 / 1,000 |
| Instagram / TikTok | Consumer startup reach | ~$2 / 1,000 |
| Google Search (SERP) | Open-web diligence | $1.80 / 1,000 |
| Trustpilot / News | Reputation, signal | cheap |
skip Crunchbase & G2 scrapers — they're losing the anti-bot war (flaky). We stay on Harmonic / Dealroom / SEC EDGAR for funding data.
You asked about PitchBook. Short version: don't scrape it — it's the one source on your list where scraping is genuinely a bad idea, for three reasons:
| Issue | Why it matters |
|---|---|
| It's paywalled | The real data (valuations, AUM, cap tables) sits behind a paid login. The working scrapers only return the free public shell — near-worthless. |
| Needs your login | To get anything real, an actor needs your own PitchBook cookies. That can get your seat banned ($20–30k/yr) and breaches your subscriber terms. |
| Legal exposure | Public data is fair game (LinkedIn). Paywalled data is not — that's the line where the "hacking" law actually applies. PitchBook is Morningstar-owned and litigious, and their terms ban feeding their data into AI. |
Several of the best diligence sources are free official APIs — Claude can hit these with no Apify token at all. The rest are cheap Apify actors.
| Source | Use | How |
|---|---|---|
| SEC EDGAR Form D | US private raises (who raised how much) | free API |
| Court records | Founder lawsuit history | free CourtListener API |
| Hacker News | Founder / product sentiment | free Algolia API |
| Wayback Machine | What the company claimed months ago (drift) | free CDX API |
| Patents | IP ownership / chain-of-title (deeptech) | free PatentsView, or Apify |
| Company registries | Catch dissolved / forfeited entities | OpenCorporates (Apify) |
| Product sentiment | Apify, ~pay-per-result | |
| YouTube | Founder talks, demos, conference clips | Apify, $0.50–5 / 1k |
| BuiltWith / WHOIS | Verify tech stack & real company age | Apify, cheap |
The free APIs (EDGAR, CourtListener, HN, Wayback, Patents) are the diligence spine — funding, litigation, sentiment, claim-drift, IP — all free and legal. Apify fills the gaps. None of this needs anything from you beyond the one token in section 3.
Full diligence sweep on one company ≈ $5–8.
(Founder LinkedIn + company page + 1k tweets + Instagram/TikTok + both app stores + site crawl + search + job postings + reviews + news — all of it.) A 100-company batch enrichment ≈ $2–5. These are rounding errors against the deal sizes, and they draw from the $29 monthly credit.
Short version: yes, for what we're doing. We scrape public data only, cookieless (never logging into your accounts), for internal diligence, and we never republish or resell it. That's standard practice across the VC industry — every sales-intelligence tool (Apollo, ZoomInfo, Harmonic) does the same. Courts have held that scraping public data isn't “hacking.” We keep it clean by tying scraped data to an active deal and deleting it when the deal dies — flag-raiser, not a permanent dossier.
Daxos Capital · internal · unlisted