Vettly Family
A parent-and-teen safety experience built on Vettly's moderation decisions, focused review context, and traceable actions.
Moderate text, images, and video in a single API call. Ship with built-in reporting, blocking, appeals, and audit trails.
Production-ready in minutes, not quarters.
15,000 decisions/mo free • No credit card required
A regex gives you a yes/no. An LLM gives you a score. Vettly gives you a complete decision record that tracks policy version, appeal outcome, and retention status so you're always ready for moderation reviews.
Content & context
Policy applied
Decision made
Securely pinned
Appeals handled
Fully searchable
You integrate three simple endpoints. Vettly handles filtering, reporting, blocking, appeals, audit trails, and policy versioning for you.
Call the /v1/check endpoint before content is published.
Enable user reporting and blocking endpoints.
Every decision logged with the policy version that produced it.
import { Vettly } from '@vettly/sdk';// Initialize the SDKconstvettly = new Vettly(process.env.VETTLY_API_KEY);// Block toxic content before it hits your DBconstdecision = await vettly.check({content: { text: "Hello world", type: "text" },user_id: "usr_123",policy_id: "pol_strict_v2"});if(decision.action === "block") {returnres.status(400).json({error: "Content violates community standards",reason: decision.flags[0]});}
Family and Discord are products we built on Vettly. They exercise the moderation decisions, policy controls, and review workflows available to teams through the API.
A parent-and-teen safety experience built on Vettly's moderation decisions, focused review context, and traceable actions.
A community bot that turns Vettly decisions into channel actions, moderator logs, and human review when a case needs judgment.
Want the primitives behind both products?
Build with VettlyDefine your content policy in plain English. Vettly enforces it across text, images, and video with decisions your team can trace, explain, and absolutely defend.

Chat, comments, and user profiles. Filter text and images before they appear, add report buttons, and let users block each other with a single integration.

Chat, comments, and user profiles. Filter text and images before they appear, add report buttons, and let users block each other with a single integration.
Edit the text, run Analyze, and see the real API response processing through our policy engine in milliseconds.
name: community-safeversion: "1.0"rules:- category: hate_speechthreshold: 0.6action: block- category: harassmentthreshold: 0.6action: flag- category: violencethreshold: 0.7action: warn- category: spamthreshold: 0.5action: flag
{"decisionId": "dec_xxxxxxxx","action": "allow","safe": true,"categories": [],"latency_ms": "---"}
Behind the Scenes
Start free. Upgrade when you need more volume, longer decision history, or advanced policy workflows.
Enough for a 5,000-user app
Ship your MVP securely
Ship publicly with protection
Pricing is simple: All plans include fully-searchable decision IDs, policy versioning, and our rigorous audit trail.
Overage pricing (all paid plans): text $0.0001/unit · image $0.001/unit · video $0.01/unit. Billed monthly.