Configuring a run
Choosing models
Balanced or Powerful, what a tier sets, and when a bigger model actually pays off.
There is one model choice to make: Balanced or Powerful. We pick and maintain the models behind each tier, so a run always uses models we have tested for RTL work.
The quick picker
The model button on the composer, and the Model control in Run setup, offer two presets. They are not model names: each one sets how much capability a run uses, and we choose the models behind it.
| Preset | When to reach for it |
|---|---|
| Balanced | The default, and the right answer most of the time. Balanced across quality, speed and cost. |
| Powerful | Most rigorous. Worth it for intricate protocol logic, tricky clock-domain crossings, and anything you would otherwise spend an afternoon reviewing. |
What a tier sets
The tier applies to every model the run uses. In Agent mode that is the agent itself. In Plan mode a run has three roles, and the tier sets the generator and the verifier:
| Role | What it does |
|---|---|
| Planner | Writes the clarifying questions in Plan mode and folds your answers into the specification. The same model on either tier. |
| Generator | Writes the RTL and the testbench. The one that matters most. |
| Verifier | Used by Reflection to review and repair the module after a failed simulation. It is only paid for when a run actually fails. |
Note
Individual models cannot be chosen per role. When a better model is released, we switch to it and the tier you picked stays the same.
Which models run your design
RTLBridge Agent uses Anthropic Claude together with RTLBridge's hardware-specific tools and orchestration.
Plan mode uses models RTLBridge selects for each step. Those models come from several providers and change as better ones are released. The tier you pick stays the same when they do.
The menu behind the model button says which applies to the mode you have selected. We do not publish the exact model or version behind a tier, because it changes without notice. How your requests reach these providers is covered in the privacy policy.
Does a bigger model actually help?
Sometimes, and it is worth being honest about when:
- It helps on specifications with several interacting requirements, multi-clock designs, protocol compliance, and code that has to fit into conventions described in prose rather than in the code itself.
- It rarely helps on a counter, a shift register, a mux, or a small state machine. A cheaper model writes those correctly, and the run finishes sooner.
- It never fixes a vague spec. If the description is ambiguous, a larger model produces a more confident version of the wrong module. Spend the effort on the spec first.
Models and cost
Model choice, context size and tools all affect how much credit a run uses; a run is charged for the work it actually did rather than at a fixed price. Your billing page quotes a typical figure so a balance means something at a glance, and lists the real charge for every completed run. See Plans and Billing and usage.