# TikTok Detect fake views in video API

> Check whether a TikTok video has fake views. Paste a video ID and get a fake-view score, the estimated share of inflated views, and a risk level, based on engagement ratios, follower growth, creator credibility and TikTok's traffic-pool tiers. Built for creators, MCN agencies and brands vetting influencers.

Source: https://www.sandbase.ai/apis/tiktok/analytics/detect-fake-views
API reference: https://www.sandbase.ai/apis/tiktok/analytics/detect-fake-views/docs

## Facts

- Provider: TikTok
- Type: Data API
- Endpoint: `POST https://api.sandbase.ai/v1/api/tiktok/analytics/detect-fake-views`
- Price: $0.01 per call
- Free allowance: 100 calls per organization per UTC day, shared across eligible APIs
- Capabilities: api, tiktok
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

`POST https://api.sandbase.ai/v1/api/tiktok/analytics/detect-fake-views` with `Authorization: Bearer $SANDBASE_API_KEY` and the parameters as a JSON body.

| Parameter | Type | Required | Allowed values |
| --- | --- | --- | --- |
| `item_id` | string | yes |  |
| `content_category` | string | no | default, entertainment, education, product, verified_large |

## FAQ

### How do I use the Detect fake views in video API?

Send a POST request to https://api.sandbase.ai/v1/api/tiktok/analytics/detect-fake-views with your SandBase API key in the Authorization header (Bearer) and the parameters as a JSON body. You can also try it in the Playground on this page without writing code.

### How much does the Detect fake views in video API cost?

$0.01 per call. Every organization gets 100 free calls per UTC day, shared across eligible SandBase APIs including this one; after that each call is billed at this price from your SandBase balance. There is no subscription.

### What parameters does the Detect fake views in video API accept?

Required: item_id (string). Optional: content_category (one of default, entertainment, education, product, verified_large). The Parameters table and the Playground on this page list every field.

### What does the Detect fake views in video API return?

A JSON response returned in the same HTTP request (synchronous). The README on this page includes a sample response.

### Do I need a TikTok developer account or API key?

No. Detect fake views in video runs through SandBase, so one SandBase API key covers this endpoint and every other API and model in the catalog. You do not need to apply for TikTok API access separately.

## README

### TikTok Fake View Checker

Find out whether a TikTok video's views are real. Give this API a video ID and it returns a **fake-view score**, the **estimated number and percentage of fake views**, a **risk level**, and the specific signals that look suspicious.

#### Who it is for

- **Brands and agencies** vetting influencers before signing a sponsorship deal.
- **MCN agencies** monitoring the traffic quality of the creators they manage.
- **Creators** checking whether a sudden spike in views is organic.

#### How to use it

1. Copy the TikTok video URL, e.g. `https://www.tiktok.com/@tiktok/video/7460937381265411370`.
2. Take the number after `/video/`. That is the `item_id`: `7460937381265411370`.
3. Optionally set `content_category` (`default`, `entertainment`, `education`, `product`, `verified_large`) so engagement is compared against the right benchmark.
4. Run it in the playground above, or call the API:

```bash
curl -X POST "https://api.sandbase.ai/v1/api/tiktok/analytics/detect-fake-views" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"item_id": "7460937381265411370"}'
```

#### What the report checks

The score combines eight dimensions and 20+ metrics:

| Dimension | What it looks at |
|---|---|
| Engagement health | Like, comment, share and favorite ratios against category benchmarks |
| Follower correlation | Views compared with what an account of this follower tier usually gets |
| Fan growth | Follower milestones and abnormal daily growth |
| Creator credibility | Account age, verification and trust score |
| Content authenticity | AI-generated or heavily edited content flags |
| Traffic pool | Current vs. expected TikTok traffic-pool tier (level 1 to 8) |
| Distribution and consistency | How views and engagement are spread and whether they move together |
| Statistical anomalies | Outliers that point to bought or bot traffic |

#### Example result

Real output for the video above (trimmed):

```json
{
  "fake_view_analysis": {
    "fake_score": 4.34,
    "fake_view_percentage": 5.0,
    "estimated_fake_views": 8102490,
    "is_suspicious": false,
    "confidence_level": "Minimal"
  },
  "traffic_pool": {
    "current_tier_name": "8th-Level Traffic Pool",
    "expected_tier_name": "8th-Level Traffic Pool",
    "current_views_range": "30M+"
  },
  "suspicious_features": [
    "Suspicious: Account gaining 22670 followers per day on average"
  ],
  "recommendations": {
    "risk_level": "low",
    "action": "no_action",
    "suggested_steps": ["No immediate action required", "Include in routine monitoring"]
  }
}
```

#### How to read the result

- `fake_view_analysis.fake_score`: overall suspicion score; higher means more likely to be inflated.
- `fake_view_analysis.is_suspicious`: quick yes/no verdict.
- `fake_view_analysis.fake_view_percentage` and `estimated_fake_views`: how much of the view count is likely fake.
- `suspicious_features`: plain-language reasons behind the score.
- `recommendations.risk_level` and `suggested_steps`: what to do next.
- `mcn_report`: business impact summary (brand safety, estimated revenue impact) for agency reports.

The result is a statistical estimate, not a verdict from TikTok. Use it to screen and prioritize, and combine it with your own review for high-stakes decisions.

#### Related TikTok analytics APIs

- [Get video metrics](/model/tiktok/analytics/video-metrics): views, likes and engagement trends for a video.
- [Get creator info and milestones](/model/tiktok/analytics/creator-info-and-milestones): follower milestones and creator profile.
- [Get comment keywords analysis](/model/tiktok/analytics/comment-keywords): what viewers are saying in the comments.