NEW YEAR SALE: Get 15% Extra Credits, up to $150.Top Up Now!
feature
Molmo2-4B Video Content Moderator analyzes video content for safety, appropriateness, and policy compliance. Detects violence, nudity, gore, and other harmful visual content in videos using an open-source vision-language model. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Idle
{ "hate": false, "sexual": false, "violence": false, "harassment": false, "sexual/minors": false }
Your request will cost $0.003 per run.
For $1 you can run this model approximately 333 times.
ExamplesView all
README
Molmo2 Video Content Moderator
Automatically screen videos for harmful content with Molmo2 Video Content Moderator. This AI-powered moderation tool analyzes videos and returns safety classifications for harassment, hate speech, sexual content, and violence — essential for content platforms, user-generated content, and compliance workflows.
Need image moderation? Try Molmo2 Image Content Moderator for image analysis.
Why It Works Great
- Comprehensive detection: Screens for harassment, hate, sexual content, and violence.
- Child safety: Dedicated detection for content involving minors.
- Fast processing: Quick analysis with results in seconds.
- JSON output: Clean, structured results for easy integration.
- Ultra-affordable: Just $0.003 per video — 333 videos for $1.
- Custom criteria: Optional text input for additional context.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Video to analyze (upload or public URL). |
| text | No | Optional context or custom moderation criteria. |
How to Use
- Upload your video — drag and drop or paste a public URL.
- Add context (optional) — provide additional text for custom criteria.
- Run — click the button to analyze.
- Review results — check the JSON output for safety classifications.
Pricing
Flat rate per video analyzed.
| Output | Cost |
|---|---|
| Per video | $0.003 |
| 100 videos | $0.30 |
| 1,000 videos | $3.00 |
Output Format
The model returns a JSON object with boolean flags for each content category:
{
"harassment": false,
"hate": false,
"sexual": false,
"sexual/minors": false,
"violence": false
}
Detection Categories
| Category | Description |
|---|---|
| harassment | Bullying, intimidation, or targeted abuse |
| hate | Hate speech, discrimination, or prejudice |
| sexual | Adult sexual content or nudity |
| sexual/minors | Any sexual content involving minors |
| violence | Graphic violence, gore, or harmful acts |
Best Use Cases
- Content Platforms — Screen user-uploaded videos before publishing.
- Social Media — Moderate video content at scale.
- E-commerce — Review product videos for policy compliance.
- Education — Ensure learning content is age-appropriate.
- Compliance — Meet content moderation requirements efficiently.
- Pre-screening — Filter content before human review.
Pro Tips for Best Results
- Use as a first-pass filter before human moderation for edge cases.
- Integrate via API for automated moderation pipelines.
- At $0.003 per video, batch processing is extremely cost-effective.
- Combine with image moderation for comprehensive content screening.
- Use the text parameter to provide context for borderline content.
Notes
- If using a URL, ensure it is publicly accessible.
- Processing time scales with video length.
- Returns boolean values — true indicates detected content.
- Designed for automated workflows with JSON output.
- Consider human review for flagged content or edge cases.