Skip to main content
GET
Detect fake views in video
Detect fake views in video Pricing — billed per successful call; the final charge scales by your plan multiplier. Charged only when the upstream response body code is 200.
Response structure is not yet fully documented — refer to the actual API response.

Example

Authorizations

Authorization
string
header
required

AIsa API key. Get yours at https://aisa.one

Query Parameters

item_id
string
required

Video ID, required parameter, can be extracted from video URL (e.g., 7460937381265411370 from https://www.tiktok.com/@tiktok/video/7460937381265411370)

content_category
string
default:default

Content category, optional parameter, affects engagement rate benchmarks, options include:

  • default: Default category for general content
  • entertainment: Entertainment content, expected to have higher engagement
  • education: Educational content, expected to have moderate engagement and higher save rates
  • product: Product content, expected to have lower engagement but higher conversion
  • verified_large: Large verified accounts, expected to have appropriately lower engagement rates

Response

200 - application/json

Successful response. The outer object follows ResponseModel; the endpoint-specific payload is in data.

Return Description

  • video_metrics: Core video metrics

    • total_views: Total number of views
    • total_likes: Total number of likes
    • total_comments: Total number of comments
    • total_favorites: Total number of saves
    • total_shares: Total number of shares
    • engagement_rates: Engagement rate metrics, higher is better
      • like_ratio: Like rate, normal range 1-10%, may be lower for large accounts
      • comment_ratio: Comment rate, normal range 0.1-0.5%, excellent if above 1%
      • favorite_ratio: Save rate, normal range 0.05-0.8%
      • share_ratio: Share rate, normal range 0.05-0.5%, excellent if above 1%
  • creator_metrics: Creator account health indicators

    • account_age_days: Account age in days, longer is more credible
    • follower_count: Number of followers, affects expected view count
    • verified: Whether account is verified, verified accounts have higher credibility
    • trust_score: Account trust score (0-100), higher is more trustworthy
  • content_metrics: Content quality indicators

    • content_type: Content type (video, image, etc.)
    • created_by_ai: Whether AI-generated, AI-generated content may have specific traffic patterns
    • high_quality_upload: Whether high-quality upload, high-quality uploads are more credible
  • fake_view_analysis: Comprehensive fake traffic analysis

    • fake_score: Fake view score (0-100), lower is better:
      • 0-20: Very low risk, natural traffic patterns
      • 20-40: Low risk, may have minor anomalies but not problematic
      • 40-60: Medium risk, anomalies worth attention
      • 60-80: High risk, obvious fake traffic characteristics
      • 80-100: Very high risk, almost certainly fake traffic
    • confidence_level: Risk level, categorized as "Minimal", "Low", "Medium", "High"
    • estimated_fake_views: Estimated fake views, calculated based on fake traffic model
    • fake_view_percentage: Fake view percentage, proportion of fake views to total views
    • is_suspicious: Whether suspicious, comprehensive judgment if attention is needed
    • main_detection_reason: Main detection reason, most significant anomaly feature
    • component_scores: Dimensional anomaly scores, each 0-100, lower is better:
      • engagement_score: Engagement anomaly score
      • distribution_score: Distribution anomaly score
      • consistency_score: Consistency anomaly score
      • creator_credibility_score: Creator credibility anomaly score
      • content_authenticity_score: Content authenticity anomaly score
      • follower_correlation_score: Follower correlation anomaly score
      • racing_mechanism_score: Racing mechanism anomaly score
      • fan_growth_score: Fan growth anomaly score
  • traffic_pool: Traffic pool analysis (TikTok racing mechanism)

    • current_tier: Current traffic pool level (1-8), higher means more traffic
    • current_tier_name: Current traffic pool name
    • expected_tier: Expected traffic pool level, based on organic traffic prediction
    • expected_tier_name: Expected traffic pool name
    • current_views_range: Current traffic pool expected view range
    • expected_views_range: Expected traffic pool view range
    • estimated_organic_views: Estimated organic views, real views after deducting fake ones
  • suspicious_features: List of suspicious features, specific detected anomalies

  • recommendations: Recommended actions

    • action: Recommended action type, possible values include:
      • no_action: No action needed, healthy content
      • monitor: Continuous monitoring, minor anomalies present
      • scheduled_review: Schedule review, anomalies worth attention
      • immediate_review: Immediate review, serious anomalies present
    • risk_level: Risk level ("low", "medium", "high", "critical")
    • potential_revenue_impact: Potential revenue impact
    • suggested_steps: Suggested steps, specific action recommendations
  • mcn_report: (Optional) MCN business impact analysis report, applicable for business accounts

    • summary: Summary information
    • business_impact: Business impact assessment
      • revenue_impact: Revenue impact assessment
      • brand_safety_impact: Brand safety impact
      • platform_relationship: Platform relationship impact
      • contract_impact: Contract impact assessment
    • recommended_actions: Recommended action list
    • historical_context: Historical background data

The media-type example is an illustrative response from the official documentation, not a live response. Its router and params metadata use upstream naming.

code
integer
default:200

HTTP status code

request_id
string | null

Unique request identifier

message
string
default:Request successful. This request will incur a charge.

Response message (EN-US)

message_zh
string
default:请求成功,本次请求将被计费。

Response message (ZH-CN)

support
string
default:Discord: https://discord.gg/aMEAS8Xsvz

Support message

time
string

The time the response was generated

time_stamp
integer

The timestamp the response was generated

time_zone
string
default:America/Los_Angeles

The timezone of the response time

docs
string | null

Link to the API Swagger documentation for this endpoint

cache_message
string | null
default:This response is cached and accessible via the URL below for 24 hours at no extra cost. The cache is for request tracing only — it doesn't affect the API's data freshness and won't be returned through the API again.

Cache message (EN-US)

cache_message_zh
string | null
default:本次响应已缓存,可通过下方 URL 直接查看,有效期 24 小时,访问缓存链接无额外费用。缓存仅用于请求溯源,不影响接口数据的时效性,也不会再次通过接口返回。

Cache message (ZH-CN)

cache_url
string | null

The URL to access the cached result

router
string
default:""

The endpoint that generated this response

params
any
default:{}

The parameters used in the request

data
any | null

Endpoint-specific response payload. The official shared model does not declare a fixed type or field set. Use the operation's documented return fields or response example; an operation-specific schema, when present, describes the documented fields. Undocumented fields must be read from the actual response rather than assumed.