Know whether a video is safe to advertise against before an ad runs. Every video gets a risk score from 0 to 5 in 11 categories, an overall risk score from 0 to 100, and a suitability level with the reasoning behind it.

The 11 risk categories

Adult content · Violence · Hate speech · Drugs · Weapons · Crime · Profanity · Alcohol & tobacco · Gambling · Political extremism · Negative news.

How it works

  1. Send video URLs in batches of up to 500.
  2. Choose risk profile, suitability, or both.
  3. Apply your own thresholds. The scores are yours to tune: block, tier or route content by the rules your advertisers set.

What comes back

{"type": "RISK_PROFILE", "result": {"overallRiskScore": 0, "categories": [{"category": "VIOLENCE", "score": 0, "reasoning": ""}]}}
{"type": "SUITABILITY", "result": {"level": "None", "categories": [], "explanation": "No listed sensitive content is meaningfully present."}}

What teams build with it

  • Pre-bid screening of video inventory.
  • Suitability tiers advertisers can choose from.
  • Platform policy screening before content is monetized or promoted.

Frequently asked questions

Do you explain the scores?

Yes. Each category carries its reasoning, and suitability comes with an explanation.

Does it read speech and visuals?

It analyzes the transcript and storyboard frames of each video.

Can we add our own categories?

Yes, custom models are available on request.

Whose models, and at what scale

Our own models, trained and curated in-house by advertising and media people, so we can tune them to your needs. Your video isn't sent to a big LLM provider.

Built for libraries and feeds: our infrastructure processes 100k+ videos per hour.

New signals added regularly. Custom models on request.

Ready to test it on your own video? Get API access.