After a long period of testing and iteration, I’m ready to share a first look of something new.
ARIMA: Artificial Intelligence Modeling Assistant is my experimental plugin that explores how AI can generate simple 3D geometry from text or images, directly inside Vectorworks.
The idea of integrating artificial intelligence into Vectorworks started about a year after the release of ChatGPT. At the time, I had to put it on hold:
- models weren’t reliable enough
- APIs were too expensive
- building something sustainable felt unrealistic
Even today, things are evolving fast — new models appear constantly, and what works today may be outdated in a few weeks. What made ARIMA possible now is OpenRouter: a single API key that gives access to many different AI models, both free and paid.
Through OpenRouter, you can access multiple AI models from one place, using free models with daily limits. You can try more advanced models by adding credits — even $5 can go a long way and let you run a surprising number of experiments.
At the moment:
- Free usage allows around 50 requests per day
- If you purchase at least 10 credits, your daily limit is increased to 1000 free model requests per day
Not all free requests succeed (server load can cause errors), and performance and cost vary significantly between models. I have also noticed significant variations in performance depending on the time of day, possibly due to higher server load when too many requests are being processed simultaneously.
First, you need to enter your API key, which you can generate after signing up for free on OpenRouter.
Model selection: choose the AI model that best fits your workflow.
ARIMA provides three model selection options:
- Recommended: the model personally recommended by me for ARIMA. It is currently the latest available Gemini Flash model, offering the best balance of results, capabilities, and low cost for the plugin.
- Free Model: let OpenRouter automatically select the first available free model. This allows you to use ARIMA without API costs, but results and capabilities are very limited and may vary depending on which model OpenRouter selects.
- Custom Model: paste the ID of any model available on OpenRouter. This gives you full control over the model you want to use. OpenRouter sometimes makes professional models temporarily available for free, allowing you to experiment with them for a limited period before they become paid.
After you selected a model, the workflow is very simple:
- If you selected to attach an image, you can paste a direct image URL
- Use the “Write Prompt” button and adjust the prompt according to your needs
- Wait for the response from the selected model. Response times can vary and may be slow, especially with complex prompts or image
For the best overall experience, Recommended is the suggested option but you need some credits. Free Model is mainly intended for experimentation, while Custom Model is useful when you want to try a specific model or take advantage of temporary free access.
What ARIMA can do today
ARIMA is built around a simple idea: using AI to generate 3D geometry and data from descriptions or images, while leveraging Vectorworks tools. However, ARIMA is designed to be flexible, giving users the freedom to experiment and discover new workflows and applications — for example, by generating and working with record data alongside geometry.
Current capabilities – Updated 2026.08.25
Create 3D geometry from text descriptions and images (depending on the model’s capabilities)
Use materials from the Resource Manager
Insert walls using available wall styles
Read/use supported named objects in the active layer (circles, rectangles, polylines, polygons, lines)
Insert symbols by specifying the exact symbol name in the prompt
Creating and applying data to objects using record format
Show token usage and cost of the last prompt
Results depend heavily on the model you choose. Some free models already produce interesting results. More advanced paid models can significantly improve output quality — but also increase cost. This balance is constantly changing. A model that is “best” today might be surpassed very soon.
⚠️ Current limitations
ARIMA is still experimental, and it’s important to be clear about what it cannot do.
- It cannot fully read your entire drawing
- It cannot modify or delete existing objects
- It works within strict context limits imposed by AI models
Sending too much data (e.g. entire layers) would:
- Increase costs
- Reduce output quality
- Increase the likelihood of errors
Because of this, ARIMA focuses on generation, not full scene understanding. ARIMA is not a finished product: it’s an ongoing exploration. Some results are surprisingly good. Others are inconsistent or fail entirely. That’s part of the process!
ARIMA is available for Vectorworks 2026 starting with update 2026.1, and will also be available for Vectorworks 2027. It is part of the bundle as an experimental plugin, designed to evolve alongside the rapidly advancing field of AI.
The goal is not to replace modeling. It’s to explore:
- How quickly ideas can be prototyped
- How new workflows might emerge inside Vectorworks
- How AI can be used to generate both geometry and data within the Vectorworks environment
ARIMA is an early step in that direction, and its future will largely be shaped by what users discover and create with it.
I’m also open to feedback, ideas, and feature requests, and will evaluate new functionality based on how it could improve ARIMA and enable new workflows.