Why is my input token count so much bigger than output?
Agents read far more than they write. Each step sends Line's instructions, your project notes, the conversation, files it read and tool output as input, while the reply (an edit or a short answer) is small output.
To keep input down:
/newfor unrelated tasks./compactlong sessions.- Point to exact files with
@. - Check
/contextfor what's taking space.
Input above 262K tokens in a single request counts at 1.5×, so very long sessions are worth compacting.
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.