How do we evaluate SuperCosmos for our use case?

1. Collect 20–50 real tasks with known good answers (or clear pass/fail checks).
2. Run them on each tier through the Model API, logging usage and time.
3. Score quality with your checks; note "I don't know" replies separately (often a good sign).
4. Compare cost per task and time against your needs.
5. Repeat when GET /v1/models reports a new version.

That mirrors how Benchmark 2 was run: through the public API, one attempt per case, fixed checks.

Good to know#

• Insulting or cursing at the assistant earns a warning, then a 24-hour pause on a second strike within 30 days. Abuse policy
• SuperCosmos answers in your language, including Egyptian Arabic. Languages
• 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.