Models

Dropstone runs three tiers. On the 1.8 lineup, Fast runs DeepSeek V4.1 Flash, Pro runs GLM-5.3 Flash, and Heavy runs Kimi K3, re-evaluated every month.

How to pick between Dropstone Fast, Pro, and Heavy, where the selector lives in chat and in the CLI, and why the name Fast describes what a tier costs rather than how fast the model inside it runs.

The button at the foot of the composer names the tier, the lineup version and the effort level, and your usage page records which model handled each request.

Dropstone numbers each lineup with the year and the month it was cut, and a new version ships only when a tier's pick changes. How to read the number, and which lineup you get.

Every Dropstone model lineup from 1.5 to 1.8, with the open-weight model that filled each tier. 1.8 is in service, 1.7 is still selectable, and 1.5 and 1.6 are retired.

Every month Blankline re-evaluates the open-weight models available for each Dropstone tier against three tests, how well it does the work, what it costs to serve, and how safely it behaves with tools. A model has to beat the one already in the slot.

The models behind Dropstone Fast, Pro, and Heavy are open-weight, so the weights are published and anyone can check which model is behind a tier. Here is what that gives you, and what it does not mean.