What happens to the text I send to the Model API?

Your messages are processed by SuperCosmos on Clatter Labs infrastructure to produce the reply, and each call appears in Console › Logs with its usage and price.

According to the Privacy Policy:

• Content (prompts, inputs and outputs) may be used, pseudonymized and with secrets filtered automatically, to train Clatter Labs' own models.
• You can object at any time, without giving reasons, through the Support Center, identifying your account. There's no in-product switch.
• Content of users known to be under 18 isn't used for training.
• AI inference currently runs in the United States.

The Terms of Service have the full details.

Practical advice: don't send secrets (passwords, keys, card numbers) in prompts. For questions about data handling or to request deletion, write to infrastructure@clatterlabs.xyz.

Good to know#

• Every response has an X-Request-Id; log it so a request can be found later. Why log it
• Each key has its own limit: 10, 30 (default), 60 or 120 requests per minute. Rate limits
• Model ids: supercosmos-flash, supercosmos-max, supercosmos-heavy (SuperCosmos 1.1). Which to call

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.