How does the abuse policy affect my app on the Model API?
Insulting or cursing at the assistant isn't allowed on any Clatter Labs product. On the Model API, your key acts for your account, so your end users' text counts against your account exactly as if you'd written it.
| Strike | What happens |
|---|---|
| First in 30 days | Warning. The request is answered normally and carries a warning header. |
| Second within 30 days | 24-hour suspension of your account on every Clatter Labs product. |
What counts and what doesn't#
Counts: the person writing insults or curses at the assistant. Doesn't count: swearing at a bug, a build or a third party; quoted text (code, logs, pasted errors, quotes); asking about or translating a word, or building a filter for it. Only the newest message a person wrote is checked, never tool output, system prompts or the model's own replies.
What to do#
- Filter or moderate end-user input before sending it.
- Watch for the
x-clatter-notice: abuse_warningheader and act on it, for example by blocking that end user.
Full policy: Abuse policy.
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.
Related articles
Still need help?
Tried the steps above and still stuck? Email us. We usually reply within the first hour, and always within 24 hours. A full support team is with you.