SuperCosmos glossary: tokens, tiers, efforts and more
| Term | Meaning |
|---|---|
| Token | A small piece of text. Usage and prices are counted in tokens. |
| Input tokens | What you send (prompt, history, instructions). |
| Output tokens | What the model writes, including reasoning. |
| Context window | How much text the model can consider at once: 1M tokens. |
| Tier | Flash, Max or Heavy (the Agent API's word). |
| Effort | The same thing in Line CLI's words. |
| Extended thinking / reasoning | Thinking before answering (Max and Heavy). |
| auto | Let the product choose the tier per step. |
| Model id | The name you call on the Model API, e.g. supercosmos-max. |
| Family id | supercosmos, used with an effort. |
| Long-context input | A prompt over 262K tokens; its input bills at 1.5×. |
| Mixture-of-experts | Only part of the model (55B of 550B parameters) runs per token. |
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.
Related articles
Still need help?
Tried the steps above and still stuck? Email us. We usually reply within the first hour, and always within 24 hours. A full support team is with you.
Infrastructure questions, or permanent deletion of your data
infrastructure@clatterlabs.xyzFor deleting your whole account or the data of one service.