Why do long prompts cost more?

SuperCosmos has a 1M-token context window. A request whose prompt is over 262K tokens bills its whole input at 1.5×. For example, on Flash, $1.60 per 1M becomes $2.40 for that request's input. Output is unaffected. Keep only what's needed in context.

Good to know#

• The usage in each Model API response is what's billed.
• Logs shows the cost of every metered request.
• Plans cover app usage (Line CLI, Cosmos Agent, Telegram); credits pay for the Model API and Agent API on every plan.

Learn more#

• Rates
• Models
• Choose a tier

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.