How much can Cosmos keep in mind during a run?
Every tier uses SuperCosmos 1.1, with a 1M-token context window (1,048,576 tokens).
Long context costs more#
A request whose prompt is over 262K tokens bills its whole input at 1.5× the tier's rate. Long runs that read a lot of code can reach this, so:
- Point Cosmos at the files that matter instead of "read the whole repo".
- Split very large jobs into several runs.
Learn more#
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.