How can I spend less on API calls?

1. Start with Flash (or auto on the Agent API).
2. Keep prompts lean; stay under 262K tokens of context.
3. Cap output with max_tokens.
4. Write clear Agent API tasks with a definition of done; fewer steps means less computer time.
5. Cancel runs you no longer need.
6. Set member limits on teams.
7. Watch Usage › By tier for surprises.

Good to know#

• 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.
• Console › Billing shows % used and reset times for each limit, your credit balance and your history.

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.