These docs cover RhinoArtisan 7.0, which is still in beta. The contents are provisional: features and pages can still be added, changed or removed before the final release.
AI Models & Services in RhinoArtisan
Quality, Speed and Cost: Choosing the Right Model
Every model sits somewhere on a triangle of quality, speed and cost, and you cannot have all three at once. The strongest models are slower and more expensive; the fast cheap ones give up accuracy on hard problems.
There is no universally correct answer. There is a correct answer per job.
Two settings, on purpose
Options → Integrations has a separate model for the Assistant and for Flow Studio AI. That is deliberate, and it is the single most useful lever you have.
The Assistant answers questions all day. Most are short and factual: what a command does, how a setting behaves, what a term means. Volume is high and each question is easy, so a fast mid-tier model is usually the better trade. You feel the speed on every message and rarely feel the missing capability.
Flow Studio AI writes code. Volume is low and the stakes are high: a script that is subtly wrong wastes far more of your time than the price difference between models. This is where a frontier model earns its cost. Set it to the strongest one you are willing to pay for.
The Assistant currently defaults to Claude Opus, a frontier model, because the questions jewelers bring it are rarely as simple as they look.
When to move up
Reach for a stronger model when the job has any of these:
- A long instruction with several conditions. Weaker models drop constraints halfway through.
- Real consequences. Anything you will act on in production.
- Code. The gap between models is widest here.
When to move down
Drop to something cheaper and faster when:
- You are asking short, factual questions in a long session.
- You are exploring, and a rough answer is enough to point you in a direction.
- You are repeating a task you have already validated.
Generative AI works the same way
The image, video and 3D models in Generative AI sit on the same triangle. Use a fast, inexpensive model while you are exploring composition and framing, then regenerate the one you like on a stronger model for the final image. Paying the top rate for a draft you will discard is the most common way to overspend.