Adapt still decides how much intelligence each task needs. Now you decide which models it reaches for. Owners and admins can pick a model recipe for the organization: a named set of models mapped across all four intelligence levels, chosen for cost, speed, or raw reasoning ceiling.
Pick a recipe
Go to Settings > Intelligence. Every recipe is laid out as a card showing exactly what you get: the model and reasoning effort behind Super Fast, Fast, Balanced, and Deep, whether the stack is Frontier or Efficient, and a relative cost indicator from $ to $$$$ so you can compare spend at a glance.
Select a recipe and it applies immediately to everyone in the organization. There's nothing to publish or roll out.
The recipes
| Recipe | Best for | Cost |
|---|---|---|
| Anthropic stack (default) | Best all-round for long agentic runs | $$$ |
| OpenAI stack | Cheapest for high-volume automations | $$ |
| OpenAI stack, Sol baseline | Highest ceiling for hard reasoning tasks | $$$$ |
| xAI Grok | Frontier reasoning with Grok 4.6 | $$$ |
| Open Source | Self-hostable weights, lowest cost per turn | $ |
New organizations start on the Anthropic stack.
What doesn't change
You still never pick a model to send a message. Adapt reads the work in front of it and picks the intelligence level, the same as before. The recipe only decides which model answers at each level, so switching stacks is a single decision an admin makes once instead of a choice everyone makes on every request.
The page is visible to owners and admins only. Members keep working exactly as they did.
