Connect AI & choose models
Connect your AI providers and bind a model to each role so every studio is ready to work.
The first-run wizard connects your AI providers and picks the models Atelier uses, so a fresh install is ready to work in a couple of minutes.
A fresh install ships keyless, so the wizard runs automatically the first time you open the console. It has two steps.
1. Connect your AI
Connect one provider or several:
Anthropic
OpenAI
Google Gemini
Ollama (local)
Paste each provider's API key (or, for Ollama, your local server URL). Each key is validated against the provider before anything is saved, and stored on your own server — never in code or git.
Tip
Connecting Google Gemini also turns on image generation. One Google AI Studio key powers both Gemini chat and Nano Banana image generation.
2. Choose your models
Atelier works in roles, not per-chat model picks. There are three chat roles — high thinking, task, and fast — plus image description and image generation.
Pick a model for each role from any connected provider. The wizard suggests sensible defaults, so you can accept them and move on.
Because you bind a model to a role (never to a single conversation), swapping one model rebinds every studio that uses that role. Choose once, and the whole console follows.
Changing providers or models later
You can revisit the wizard any time:
- Open the avatar menu (top-right) and choose Set up AI providers, or visit
/atelier?onboarding=1. - Already-connected providers show as Connected, so you only fill in what's new.
To rebind a role without the wizard:
- Go to Configuration → Atelier models at
/admin/config/aincient/models. - Or run
drush aincient:model-set <role> <provider> <model>.