Does setting max_tokens lower my cost?

max_tokens limits how many output tokens (including reasoning) a call can produce, so it caps the worst case. If the answer would have been short anyway, it changes nothing. If the cap is too low, answers get cut off and you may need another call, which can cost more overall.

Good to know#

• Flash $1.60/$3.40, Max $1.80/$3.80, Heavy $2.00/$4.40 per 1M tokens in/out.
• The usage in each Model API response is what's billed.
• Logs shows the cost of every metered request.

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.