Does Flash think before answering?

Flash answers without extended thinking: no separate reasoning phase, no reasoning_content on the Model API. That's what makes it the fastest tier. In Benchmark 2 it wrote a median of 57 output tokens per task, versus about 205 for Max and Heavy.

Flash is still careful (same weights, tuned to look before changing and verify before reporting); it just doesn't spend extra tokens thinking out loud.

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
• Insulting or cursing at the assistant earns a warning, then a 24-hour pause on a second strike within 30 days. Abuse policy
• Not sure which tier? auto lets the product choose per step. What auto does

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.