# Creator Vetting Score (`exepal/creator-vetting`) Actor

Vet an Instagram, TikTok or YouTube creator before you book them: fake-follower risk, engagement quality, posting consistency, red flags and an estimated UGC rate range. Pay per profile.

- **URL**: https://apify.com/exepal/creator-vetting.md
- **Developed by:** [Laxman Kafle](https://apify.com/exepal) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $150.00 / 1,000 profile vetteds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 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:

```json
{
  "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:

```json
{
  "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):**

```js
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](https://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](https://exepal.com) builds paid, agent-ready tools: upstream APIs in, computed answers out. Questions or custom runs: contact@laxmankafle.com

# Actor input Schema

## `platform` (type: `string`):

Where the creator posts

## `handle` (type: `string`):

Username, @handle or profile URL, e.g. natgeo or https://www.tiktok.com/@khaby.lame

## `profile` (type: `object`):

Skip the upstream fetch by passing the numbers yourself: { followers, following, postsCount, recentPosts: \[{ likes, comments, views?, date }], bio?, verified?, accountAgeDays? }. No profile-fetched charge when supplied.

## `apifyToken` (type: `string`):

Use your own Apify account to pay for the profile scrape instead of ours

## Actor input object example

```json
{
  "platform": "instagram",
  "handle": "natgeo"
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "handle": "natgeo"
};

// Run the Actor and wait for it to finish
const run = await client.actor("exepal/creator-vetting").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "handle": "natgeo" }

# Run the Actor and wait for it to finish
run = client.actor("exepal/creator-vetting").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "handle": "natgeo"
}' |
apify call exepal/creator-vetting --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,exepal/creator-vetting"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/hFzEsYiOjoYqF1FyW/builds/w6YlkLQCO0gXlzx7d/openapi.json