Creator Vetting Score

Know whether a creator's audience is real before you pay them. Fake-follower risk, engagement quality, posting consistency, red flags and a fair UGC rate — for any Instagram, TikTok or YouTube profile, in one call.

Follower counts are bought by the thousand. A brand or agent booking creators for UGC needs a quick, consistent answer to three questions: is this audience real, does it respond, and what should this person cost? This Actor turns public profile numbers into a deterministic score with the reasoning spelled out, so a human or an AI agent can shortlist hundreds of creators without opening a single profile.

What you get

For one profile, the Actor returns:

Field	What it tells you
score	0–100 composite (40% audience authenticity, 35% engagement quality, 25% consistency)
fakeFollowerRisk	0–100, higher = more likely bought or inactive followers
engagementQuality	0–100, how the audience actually responds vs the benchmark for that platform and size
consistency	0–100, posting cadence, gaps, recency and how stable the likes are
estimatedRateUsd	{ min, max } per UGC video or post, with the tier and multipliers used
redFlags[]	Plain-language reasons: "Follows more accounts than it has followers", "2 posts have over 3x the median likes"
summary	One-paragraph verdict you can paste into a brief
metrics	Every number behind the scores: engagement rate, benchmark, follow ratio, comment-to-like ratio, likes variance, posts per week, days since last post

Example output for a bought-audience account:

{
  "platform": "instagram",
  "handle": "fake_one",
  "score": 20,
  "fakeFollowerRisk": 100,
  "engagementQuality": 14,
  "consistency": 60,
  "estimatedRateUsd": { "min": 95, "max": 290, "currency": "USD", "unit": "per UGC video or post",
    "basis": { "tier": "mid", "baseMin": 400, "baseMax": 1200, "engagementMultiplier": 0.6, "riskMultiplier": 0.4 } },
  "redFlags": [
    "Engagement rate 0.51% is under half the 1.8% benchmark for mid instagram accounts",
    "Follows 7200 accounts; typical of follow/unfollow growth",
    "Almost no comments relative to likes (0 comments per 613 likes); likes may be purchased",
    "2 posts have over 3x the median likes; possible paid boosts",
    "120000 followers with only 8 posts",
    "Account is 60 days old with 120000 followers"
  ],
  "summary": "High risk. The audience shows strong signs of being bought or inactive; do not book without further checks. Mid-tier instagram creator with 120,000 followers, 0.51% engagement (benchmark 1.8%), posting 0.78x per week. Estimated UGC rate $95–$290 per deliverable. 8 red flags.",
  "metrics": { "followers": 120000, "following": 7200, "engagementRate": 0.00511, "benchmarkEngagementRate": 0.018, "engagementIndex": 0.284, "commentToLikeRatio": 0, "likesCv": 1.462, "spikeCount": 2, "postsPerWeek": 0.78 }
}

A healthy 45k-follower food creator with 3% engagement and three posts a week scores 93, risk 0, no red flags, rate $150–$400.

Who uses this

• Brands and UGC marketplaces screening creator applications at scale.
• Agencies and talent managers justifying rates to clients with numbers instead of gut feel.
• AI agents running influencer discovery: vet every candidate before it reaches a human.
• Fraud and payments teams flagging suspicious creator accounts before payout.

Pricing

Pay per event. No subscription.

• $0.15 per profile vetted
• $0.05 per profile fetched (only when we scrape the profile for you)

Vetting 100 creators from their handles costs 100 × ($0.15 + $0.05) = $20. Fetched profiles are cached for 24 hours, so re-vetting the same handle the same day is $0.15.

Bring your own data: pass profile with the numbers you already have (from your own scraper, the platform API or a creator's media kit) and the fetch step and its charge are skipped entirely. Pass apifyToken to run the upstream scrape on your own Apify account instead.

Input

Field	Required	Notes
platform	yes	instagram, tiktok or youtube
handle	yes	natgeo, @natgeo or a profile URL
profile		Your own stats, see below. Skips the upstream fetch.
apifyToken		Your Apify token, to pay for the scrape yourself

profile shape:

{
  "followers": 45000, "following": 800, "postsCount": 640,
  "recentPosts": [{ "likes": 1310, "comments": 48, "views": 29100, "date": "2026-10-28T10:00:00Z" }, "..."],
  "bio": "Home cook. Weeknight recipes.", "verified": false, "accountAgeDays": 1500
}

8–20 recent posts with dates give the best read. views is optional (used for Reels, TikTok and YouTube). YouTube has no public "following" count; pass 0.

Use from code or an AI agent

Apify API (Node):

import { ApifyClient } from "apify-client";
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor("exepal/creator-vetting").call({ platform: "tiktok", handle: "khaby.lame" });
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].score, items[0].fakeFollowerRisk, items[0].estimatedRateUsd);

MCP (Claude, ChatGPT, Cursor): add exepal/creator-vetting to the Apify MCP server at https://mcp.apify.com and ask: "Vet @weeknight.cook on Instagram and tell me if $300 per video is fair." The agent fills the input, pays per result and reads the redFlags and estimatedRateUsd back to you.

Direct HTTP with USDC (x402): the same tool is available at https://api.exepal.com/v1/creator-vetting for agents that pay per request in stablecoins. See exepal.com.

How it works

Scoring is deterministic and every threshold is a named constant in the source, so two runs on the same numbers give the same answer and the verdict can be audited.

1. Fetch the public profile and its last 12 posts (or use the stats you pass in).
2. Fake-follower risk adds points per signal: engagement far below the benchmark for that platform and follower tier, following more accounts than followers, mass-following, likes with almost no comments (or comment floods), wild like variance and spikes, a big audience with almost no posts, an empty bio, an account younger than 90 days with 10k+ followers. Verified accounts get a small credit.
3. Engagement quality maps engagement rate ÷ benchmark onto a curve (on-benchmark ≈ 55, 2× ≈ 80, falling again past 4× because that is rarely organic) and credits a healthy comment-to-like ratio and view rate.
4. Consistency scores posts per week, the longest gap, days since the last post and how stable likes are from post to post.
5. Rate starts from a per-platform, per-tier rate card (nano < 10k, micro < 100k, mid < 500k, macro < 1M, mega), then applies an engagement multiplier (0.6–1.25×) and a risk discount (down to 0.4×). The card is a single constants file and is tuned to English-speaking markets.

Benchmarks (average engagement per post, likes + comments over followers):

Tier	Instagram	TikTok	YouTube
nano (<10k)	4.0%	10%	4.0%
micro (<100k)	2.5%	7%	3.0%
mid (<500k)	1.8%	5%	2.0%
macro (<1M)	1.3%	4%	1.5%
mega (1M+)	1.0%	3%	1.0%

Limits and notes

• Scores are built from public numbers only; they catch bought followers and engagement pods, not a creator who is a poor fit for your brand. Read the content too.
• Private or deleted profiles fail with a clear error and are not charged.
• Rates are a negotiating range for a single organic-use deliverable, not a quote. Exclusivity, paid usage rights and whitelisting go on top.
• Fewer than 5 recent posts makes the engagement and consistency scores low-confidence; the report says so in redFlags.

About Exepal

Exepal builds paid, agent-ready tools: upstream APIs in, computed answers out. Questions or custom runs: contact@laxmankafle.com