What should I check before going to production?

• Keys: server-side, one per service, least permission, rate limit sized to traffic.
• Errors: retry only 429 and 5xx with backoff; stop on 4xx; handle errors inside streams.
• Timeouts: generous for Max and Heavy, or stream.
• Costs: log usage per request; alert before credits run low (a 402 stops everything).
• Abuse: moderate end-user input; act on the x-clatter-notice header.
• Observability: log X-Request-Id and the completion id.
• Status: subscribe to status.clatterlabs.com emails or RSS.
• Model choice: Flash by default; Max or Heavy only where needed.

Good to know#

• Model ids: supercosmos-flash, supercosmos-max, supercosmos-heavy (SuperCosmos 1.1). Which to call
• Base URL: https://api.gateway.clatterlabs.xyz/v1, with Authorization: Bearer clsk_... and X-Clatter-Account: CL-... on every call. Quick reference
• Every call shows in Console › Logs and Usage as Model API, with its price. See what you spent

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.