What if I set a tiny max_tokens on Heavy?

On Max and Heavy, max_tokens includes reasoning. With a tiny value, the model may use it all thinking and stop before writing the answer: you get finish_reason: "length" and little or no content. Give Heavy room (thousands of tokens), or use Flash for short answers.

Good to know#

• Clatter Labs publishes its measurements of honesty, coding, efficiency and purity. Benchmark 2 results
• Insulting or cursing at the assistant earns a warning, then a 24-hour pause on a second strike within 30 days. Abuse policy
• A request whose prompt is over 262K tokens bills its whole input at 1.5×; output prices don't change. Long-context pricing

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.