AI providers, models & effort
Choose the route, not just the model name.
Use your own supported AI connection and choose a model suited to the task.
Choose the route, not just the model name.
At the start of a conversation or when you need a different approach.
A model name does not tell you whether work uses a subscription or an API key. Provider, engine, billing route and model settings belong together.
Configure supported connections and choose which models appear in the composer. Available effort levels depend on the selected route.
Take a closer look.
Explore the actual screens and controls. Click an image to see every detail.
How to get started.
From your first choice to the result. Here is how to use this feature in your own project.
- 01
Connect your API key or supported subscription account. Provider settings exist for OpenAI, Anthropic, Google Gemini and Perplexity.
- 02
Manage the models shown in your selection list, including custom models.
- 03
Choose a model, supported effort and any speed options. The engine and billing route determine execution.
How it could work for you.
Use an available subscription route for one conversation and deliberately select an API route for another.
How to assess the result
Adding a model name does not grant access. The provider must support the model and requested options.
Where to find it.
Settings → AI; conversation → Model selection
Available actions depend on your plan, mode and project state. Features that require a task become available within an appropriate conversation.What is saved?
Provider settings and model preferences are saved. API keys are kept in separate protected storage.
What you need to know
A listed model does not guarantee access. Subscription connections, effort and Fast options vary by provider, model and engine. AI usage is separate from your Linqbase subscription.