Skip to main content
Dust gives you access to models from OpenAI, Anthropic, Google, Mistral, and other providers, plus three auto models: Basic, Standard, and Premium. Each auto model is an ordered list of model and reasoning-effort combinations maintained by Dust. Dust periodically benchmarks and updates those lists, then uses the first available candidate on the selected list when you send a message. Auto models do not choose a different model for each request based on the task. They give you a maintained choice at a defined capability and cost level, so you do not have to track individual models or update agents when the preferred model changes. You choose a model in two places: the model picker in the conversation input bar, and Advanced > Model selection in Agent Builder. For the current auto-model lists and guidance on which one to use, see Auto models. Administrators can cap which models, reasoning efforts, and auto models each member can select. See Model access tiers. The exact list of available models changes as providers ship new models and as Dust updates its curated lists. The picker always shows what is currently available to you.