Models
Choosing between Dropstone Fast 1.5, Pro 1.5, and Heavy 1.5, the three model tiers Dropstone ships, plus how to set defaults and tune reasoning depth.
Dropstone ships three model tiers that cover the full range of coding work, from cheap throwaway questions to long-horizon agentic refactors. You pick a tier; Dropstone runs the inference. There is no concept of an external "provider" to configure.
The three tiers
| Tier | Model ID | Best for |
|---|---|---|
| Fast 1.5 | dropstone/dropstone-fast | Default daily-driver. Chat, single-file edits, quick answers, code review, simple tool use. Cheapest, fastest. |
| Pro 1.5 | dropstone/dropstone-pro | Frontier coding capability with a balanced speed/cost tradeoff. Multi-file edits, bugs that need real reasoning, design discussions. |
| Heavy 1.5 | dropstone/dropstone-heavy | Long-horizon work: architecture, large refactors, multi-agent orchestration. Deepest reasoning ceiling. |
To switch between them during a session:
/models
or press Ctrl+X M.
How to set a default
Add the model ID to your dropstone.json. Project config overrides global config, so you can pick a different default per-project.
Set Fast 1.5 as your default
{
"$schema": "https://dropstone.io/schema/config.json",
"model": "dropstone/dropstone-fast"
}
Set Pro 1.5 as your default
{
"$schema": "https://dropstone.io/schema/config.json",
"model": "dropstone/dropstone-pro"
}
Set Heavy 1.5 as your default
{
"$schema": "https://dropstone.io/schema/config.json",
"model": "dropstone/dropstone-heavy"
}
You can also pick a model for a single run with --model:
dropstone --model dropstone/dropstone-heavy
Reasoning depth
Each tier supports four reasoning depths via /effort:
low: fast answers, minimal creditsmedium: everyday balance (default)high: deeper reasoning for tricky problemsxhigh: maximum reasoning depth, biggest credit spend
Switch during a session:
/effort
To lock in a depth as your default, add variant:
{
"$schema": "https://dropstone.io/schema/config.json",
"model": "dropstone/dropstone-pro",
"variant": "high"
}
Trivial questions on low cost a fraction of high-effort answers. Pick the level that matches the task.
The 1.5 version naming
Fast, Pro, and Heavy are branded names, not specific model checkpoints. Each carries a calendar-aligned version suffix:
1.5means Year 1, Month 5 (May 2026)1.6will mean Year 1, Month 6 (June 2026)- And so on
Every month, the best frontier coding model for each tier is re-evaluated and the top performer becomes the new month's pick. The brand stays stable; the underlying model improves over time.
This is documented openly on the Dropstone Trust page: each release's branded tier and its underlying model are public. You always know what's powering your prompts.
Switching tiers mid-session
Use the command palette or a keyboard shortcut to switch without restarting. The conversation history persists across tier changes.
| Action | Slash command | Shortcut |
|---|---|---|
| Switch tier (Fast / Pro / Heavy) | /models | Ctrl+X M |
| Quick-switch to a recently-used tier | F2 | |
| Adjust reasoning depth | /effort |
Picking the right tier
| Workload | Tier | Why |
|---|---|---|
| "What does this function do?" | Fast | Single-file context, fast answer needed |
"Fix this bug in auth.ts" | Fast or Pro | Pro if the bug needs deeper reasoning |
"Refactor the entire routes/ directory" | Pro or Heavy | Multi-file changes benefit from longer-context reasoning |
| "Design a new caching layer for our API" | Heavy | Architecture-level reasoning needs the deepest model |
| Daily quick-fix flow | Fast | 5× more turns per dollar than the top frontier CLIs |
When in doubt: start on Fast and step up if the answer isn't deep enough.
Loading order
When Dropstone starts, it picks a model in this priority:
- The
--model/-mcommand-line flag (e.g.dropstone --model dropstone/dropstone-pro) - The
modelvalue in yourdropstone.jsonconfig - The last-used model from the previous session
- Fast 1.5 as the safe default