Clatter LabsHelp Center

How long can a SuperCosmos answer be?

ReferenceUpdated

From GET /v1/models:

TierMax output tokens
Flash32,768
Max32,768
Heavy49,152

On Max and Heavy that budget includes reasoning. On the Model API you can set a lower max_tokens; when a reply hits the limit, finish_reason is length.

For longer outputs (a whole book, a big codebase), generate in parts.

Good to know#

Still need help?#

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.xyz
For deleting your whole account or the data of one service.