Why did Line Code Ultra Fast use so many tokens?

Ultra Fast combined deep reasoning with parallel (hedged) generation: it sent each step twice in parallel and took the faster answer, so the input of the second copy counted too. That's why it used about 30× the tokens of Fast on the same task. It's history now; SuperCosmos doesn't have an equivalent mode.

Good to know#

• Prices per 1M input / output tokens: Flash $1.60 / $3.40, Max $1.80 / $3.80, Heavy $2.00 / $4.40. All prices
• Not sure which tier? auto lets the product choose per step. What auto does
• 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.