muapi Logomuapi Logo
muapi Logomuapi Logo

Molmo2 Video Content Moderator: AI Tool

Scan a video for unsafe or policy-violating content. Supports MP4, MOV, and WebM URLs and returns structured safety classifications across harassment, hate, sexual, sexual-minors, and violence categories — useful for moderating user-generated or AI-generated video before publishing.

Interactive model controls

Scan a video for unsafe or policy-violating content. Supports MP4, MOV, and WebM URLs and returns structured safety classifications across harassment, hate, sexual, sexual-minors, and violence categories — useful for moderating user-generated or AI-generated video before publishing.

📝

Overview

About this model

Scan a video for unsafe content across the major safety categories — harassment, hate, sexual, sexual-involving-minors, and violence. Submit a video URL and an optional context prompt, and receive a structured verdict you can use to gate publishing or trigger human review.

1AI video pipelines: Post-check generated clips before delivering to the user.
2UGC platforms: Pre-screen uploads against your community standards.
3Compliance review: Triage incoming media for moderator queues.
💰

Pricing & Value

Cost analysis

muapiapp$0.02 per video

Flat fee per moderation call regardless of duration.

Fal.aiNot available

No equivalent first-party video-moderation model.

ReplicateNot available

No equivalent first-party video-moderation model.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Video URLstring

Video URL to moderate. Supports MP4, MOV, and WebM formats.

Default Valuehttps://d3adwkbyhxyrtq.cloudfront.net/ai-videos/sample.mp4
Context Textstring

Optional context or custom moderation criteria to bias the moderator.

Default Value
📖

Implementation Guide

Developer documentation

How to Use Video Moderation

  1. Submit the video: POST video_url (MP4, MOV, or WebM) and an optional text describing custom moderation criteria.

  2. Wait for the verdict: Poll /api/v1/predictions/{request_id}/result or pass a webhook query param. Video inference scales with clip length — expect a handful of seconds for short clips.

  3. Read the result: output.flagged is the top-level gate. output.categories enumerates which categories were tripped (e.g. sexual, violence), and output.outputs carries the raw detection strings from the moderator.

❓

Common Questions

Frequently asked

Which video formats work?

MP4, MOV, and WebM hosted at a public URL.

Is there a length limit?

There's no hard length cap, but inference time grows with clip length. Trim previews to the most representative segments for the fastest results.

What categories does it cover?

Harassment, hate, sexual, sexual involving minors, and violence — plus any custom criteria you pass via `text`.