Content & moderation

Content moderation

Text or an image against YOUR policy → allow, review, or block, with the categories and excerpts that drove the call.

POST /v1/moderate$0.02/item · 2 credits, charged only on success

Send this

{
  "text": "This supplement cures anxiety in 3 days, guaranteed — DM me for a discount code.",
  "policy": "No medical claims. No off-platform solicitation."
}

Every response carries usage — the credits burned and your remaining balance. A failed call never burns credits.

Try it live against your own key in the interactive reference; every account gets 500 free credits a month, no card.

Get this back

{
  "flagged": true,
  "decision": "block",
  "categories": [
    {
      "category": "medical claim",
      "severity": "high",
      "excerpt": "cures anxiety in 3 days, guaranteed"
    },
    {
      "category": "off-platform solicitation",
      "severity": "medium",
      "excerpt": "DM me for a discount code"
    }
  ],
  "rationale": "Direct cure claim violates the medical-claims rule; DM solicitation violates platform policy.",
  "usage": {
    "credits": 2,
    "balanceRemaining": 298
  }
}

Four ways in. Same $0.02/item.

curl
curl https://api.kynth.studio/v1/moderate \
  -H "Authorization: Bearer ksk_live_…" \
  -H "Content-Type: application/json" \
  -d '{"text":"This supplement cures anxiety in 3 days, guaranteed — DM me for a discount code.","policy":"No medical claims. No off-platform solicitation."}'
TypeScript
import { KynthCore } from "@kynth/api";

const kynth = new KynthCore({ apiKey: process.env.KYNTH_API_KEY! });
const result = await kynth.moderate({
  "text": "This supplement cures anxiety in 3 days, guaranteed — DM me for a discount code.",
  "policy": "No medical claims. No off-platform solicitation."
});
Python
from kynth import Kynth

client = Kynth(api_key=os.environ["KYNTH_API_KEY"])
result = client.moderate(
    text="This supplement cures anxiety in 3 days, guaranteed — DM me for a discount code.",
    policy="No medical claims. No off-platform solicitation.",
)
MCP
// One-time setup in your MCP client (Claude, Cursor, …):
{ "mcpServers": { "kynth-core": {
    "command": "npx", "args": ["@kynth/api-mcp"],
    "env": { "KYNTH_API_KEY": "ksk_live_…" } } } }

// Then the agent just calls the kynth_moderate tool.

More from content & moderation