Which BI tools let you pin the AI model version?

Quoted from Databricks’s docsWhen partner-powered AI features are disabled, AI assistive features use Databricks-hosted models, which are entirely Databricks-selected and Databricks-managed.

Quoted from Snowflake’s docsYou can pick a specific model, or one of these Auto options that choose a model for you:

Quoted from Omni’s docsIn the Custom models field, enter your model identifiers as a comma-separated list (e.g., llama3.1:70b, gpt-4-turbo-2024-04-09, or your Azure deployment name).

Quoted from Hex’s docsAdmins can also set a default model for the whole workspace from Settings > AI & Agents.

Quoted from Sigma’s docsYou cannot choose which model Sigma uses, and Sigma might update the supported models over time.

Quoted from BigQuery’s docsIn the Model section, choose which types of models are available to users in a conversation with the agent.

Quoted from Looker’s docsTurn on the following settings to enable each of their corresponding features:

Quoted from Tableau’s docsEnsure the model version assigned to the deployment is supported by Tableau Server.

Quoted from Power BI’s docsAdmins need to be aware of four main settings related to Copilot:

Quoted from Metabase’s docsIt lists the models from each working connection, grouped by connection and labeled with both the connection and the model, like "Anthropic · Claude Sonnet 4.6".

Quoted from Alteryx’s docsThe LLM can be selected via the LLM Provider and Model.

Quoted from MotherDuck’s docsThese capabilities are provided by MotherDuck's integration with Azure OpenAI.

Quoted from Mode’s docsAs the models progress, we will update the versions if they improve the performance of our features.

Quoted from Redshift’s docsAmazon Q Developer is powered by Amazon Bedrock, and uses cross-region inference to distribute traffic across different AWS Regions to enhance large language model (LLM) inference performance and reliability.