How do I count tokens before sending a request in Python?

Clatter Labs doesn't publish a tokenizer for SuperCosmos, so there's no exact way to count tokens offline. Practical approach:

1. Send a representative request and read usage.prompt_tokens.
2. Use the ratio of tokens to characters from that request to estimate similar texts.
3. Keep a safety margin near limits (the 262K long-context threshold, max_tokens).

usage on every response is the exact, billed count.

Good to know#

• Keep keys on your server, never in a browser or mobile app. Why
• Each key has its own limit: 10, 30 (default), 60 or 120 requests per minute. Rate limits
• Model ids: supercosmos-flash, supercosmos-max, supercosmos-heavy (SuperCosmos 1.1). Which to call

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.