Available models
The same list appears in the dashboard composer and in the Word add-in.
The model line-up changes as providers release and retire models. If a model you had selected is retired, your composer falls back to Auto rather than failing.
The model picker
Open the model menu in the composer toolbar to see the list. The first row is the Auto switch; below it are the individual models, each with its maker’s mark.1
Leave Auto on for everyday work
Auto is on by default. It sends your conversation to Casa Conect’s default model, chosen for speed and low cost on routine requests. Today that is ChatGPT 5.6 Luna.
2
Pick a model when the task calls for it
Turn Auto off and choose a model. Your choice is remembered in that browser for future conversations until you change it.
3
Switch at any point
You can change model between messages in the same conversation. The next message runs on the new model and the conversation history carries over.
Where models run
Claude models
Opus 5 and Sonnet 5 run on Amazon Bedrock through its EU inference profile, so requests are processed in EU regions.
ChatGPT models
Astra, Sol, Terra and Luna run on the OpenAI Platform. Casa Conect sends every request with response storage switched off, so OpenAI does not retain the conversation as a stored response.
Models that work behind the scenes
Some work never reaches the model picker because Casa Conect assigns a fixed model to it:Model policies govern the model a member picks for an agent conversation. Background helpers use the fixed models above regardless of policy.
Limits that apply to every model
These limits protect you from runaway conversations. They are the same whichever model you pick.
The final step of a turn is always reserved for a written answer, so a turn that reaches its budget still ends with an explanation of where it got to.
Next steps
Choosing a model
Match the model to the work: a decision table and worked examples.
Model policies
Let admins decide which models the team can use.
AI credits
How model usage is metered and what each model costs.
AI data handling
What is sent to model providers, and what is not.