How do I detect and act on abuse warnings in JavaScript?

const { data, response } = await client.chat.completions
  .create({ model: "supercosmos-flash", messages })
  .withResponse();

if (response.headers.get("x-clatter-notice") === "abuse_warning") {
  const text = decodeURIComponent(response.headers.get("x-clatter-notice-text") ?? "");
  await flagEndUser(currentUserId, text); // e.g. block or rate-limit this user
}

A second strike within 30 days pauses your whole account for 24 hours, so act on the first one. See the Abuse policy.

Good to know#

• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Base URL: https://api.gateway.clatterlabs.xyz/v1, with Authorization: Bearer clsk_... and X-Clatter-Account: CL-... on every call. Quick reference
• Your key's account is responsible for your end users' text under the Abuse policy. What it means for apps

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.