What is a token, and why does the Model API count them?

A token is a small piece of text: often a short word or part of a longer word. Models read and write text as tokens, so that's how usage is measured.

• Input tokens (prompt_tokens): everything you send, including the system prompt, the chat history and a short Clatter Labs instruction block added to every request.
• Output tokens (completion_tokens): everything the model writes, including reasoning tokens on Max and Heavy.

Prices are per 1 million tokens. On Flash, input is $1.60 and output $3.40 per 1M tokens, so 1,000 input tokens cost $0.0016.

Every response has a usage object with the exact counts that were billed. See How is a call billed?.

Good to know#

• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Retry only 429 and 5xx errors, with backoff; honour Retry-After when it's sent. Which errors to retry
• Keep keys on your server, never in a browser or mobile app. Why

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.