How do we get consistent results across a team?

• Share system prompts and LINE.md / AGENTS.md files in your repos.
• Fix the tier per task type rather than leaving it to each person.
• Keep a small set of test prompts with expected answers; re-run them when GET /v1/models reports a new version.
• On the Model API, use low temperature and a seed where repeatability matters.

Good to know#

• SuperCosmos reads text only; it doesn't take image input. What it can't do
• Every tier shares the same 1M-token context window (1,048,576 tokens). Context window
• Prices per 1M input / output tokens: Flash $1.60 / $3.40, Max $1.80 / $3.80, Heavy $2.00 / $4.40. All prices

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.