Which model am I using?
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.
In Dropstone Chat, look at the button at the foot of the composer. It names the tier, the version, and the effort level, for example Dropstone Fast 1.8 at Max effort.
Open it and you get the three tiers at the version you are on:
- Dropstone Fast, "Fastest for quick everyday work".
- Dropstone Pro, "Balanced speed and quality".
- Dropstone Heavy, "Most capable for complex work".
One version covers all three tiers. Below those, Effort sets how much reasoning the tier does, and More models opens the previous lineup, labelled Previous Fast, Previous Pro, and Previous Heavy.
A tier with no version on it always runs the latest lineup. In the CLI, run /models for the same list.
For the full record, open Usage and analytics, which breaks your usage down by model. An organization gets the same in its audit log. Dropstone records the tier and the version, not an internal model name, so what you see is what you selected rather than a code name you have to look up.
Related articles
- Which AI models does Dropstone use?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.
- Model versions and the monthly lineupDropstone 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.
- Dropstone lineup historyEvery 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.
- Choose a modelHow 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.
- Usage and analyticsThe usage page in your Dropstone dashboard shows how much of your weekly allowance you have used, by day, by surface, and by model, plus how much prompt caching has saved you.