How can I estimate the cost of a request before sending it?

1. Estimate input tokens. Count roughly from your prompt size, or send a small test and look at usage.prompt_tokens. Remember the history and a short Clatter Labs instruction block are included.
2. Estimate output tokens. Use max_tokens as an upper bound. Max and Heavy add reasoning on top of the visible answer.
3. Multiply: input × input price + output × output price, per 1M. Use 1.5× input if the prompt is over 262K tokens.

After the call, usage (and Console › Logs) show the exact cost. Example scenarios: short chat, long document.

Good to know#

• Not sure which tier? auto lets the product choose per step. What auto does
• Prices per 1M input / output tokens: Flash $1.60 / $3.40, Max $1.80 / $3.80, Heavy $2.00 / $4.40. All prices
• Line Code was retired on Nov 1, 2026; its ids answer 410 model_retired. Line Code retirement

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.