SuperCosmos in one minute

• What: Clatter Labs' AI model. Current version 1.1 (Nov 2, 2026).
• Size: 550B parameters (55B active), 1M-token window, text in and out.
• Tiers: Flash (fast), Max (thinks first), Heavy (thinks longest).
• Prices per 1M in/out: $1.60/$3.40 · $1.80/$3.80 · $2.00/$4.40. Over 262K input tokens: 1.5× input.
• Where: Line CLI, Model API, Agent API, Console Playground, Cosmos on Telegram.
• Behaviour: says "I don't know", won't flatter, holds its ground, answers in English or Egyptian Arabic.
• Benchmark 2: honesty 20/21/22 of 22, purity 19/20/20 of 20, coding ~94% on all tiers.
• Retired: Line Code (Nov 1, 2026).

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 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

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.