Real-Time Streaming

Live Chat Moderation API

Moderate live chat in under 500ms.

WebSocket and SSE for streaming platforms, gaming, and AI chatbots.

What it detects

  • • Live chat messages
  • • AI chatbot outputs
  • • Gaming chat
  • • Streaming comments
  • • Real-time feeds
  • • Custom rules

Why developers choose Vettly

  • • Sub-500ms latency with fast path
  • • WebSocket and SSE connections
  • • Provider pre-warming
  • • Async persistence for throughput
Example request
bash
import { createStreamingClient } from '@vettly/sdk';

const streaming = createStreamingClient('YOUR_KEY');
const ws = streaming.connectRealtime({
  policyId: 'chat-policy',
  onResult: (result) => {
    if (result.safe) showMessage(result);
    else logBlocked(result);
  }
});

await ws.connect();
const result = await ws.moderate(message);
Example response
json
{
  "safe": true,
  "action": "allow",
  "categories": {
    "harassment": 0.02,
    "spam": 0.01
  },
  "latency_ms": 47
}

Compared to batch moderation APIs

Traditional APIs add 200-500ms latency. Vettly streaming delivers decisions before users notice.

Keep exploring

Content Moderation API

One endpoint for text, image, and video moderation.

Image Moderation API

Policy-driven image checks with clear allow, review, and block actions.

Video Moderation API

Async video moderation without stitching together multiple vendors.

Get an API key

Start making decisions in minutes with a Developer plan and clear upgrade paths.

Get an API key