How can a company keep Model API costs predictable?

1. Default to Flash ($1.60 / $3.40 per 1M) and send only hard request types to Max or Heavy.
2. Cap max_tokens for each use case.
3. Trim conversation history; it's billed as input every turn.
4. Stay under 262K input tokens where you can: above it the whole input bills at 1.5×.
5. Prepay credits as a budget; team members can have monthly limits.
6. Measure cost per feature from usage and review it monthly.

Good to know#

• Model ids: supercosmos-flash, supercosmos-max, supercosmos-heavy (SuperCosmos 1.1). Which to call
• Keep keys on your server, never in a browser or mobile app. Why
• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.

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.