There are two new arrivals in the GenViz stable: GPT 6 Sol and GPT 6 Luna. They join GPT 6 Astra in the OpenAI section of the model picker, giving you more choice when working through questions about your business data.
Both work with your existing GenViz conversations, connections, and analysis tools. Choose a model, ask a question, and inspect the results before moving to the next question.
Two more ways to approach a question
OpenAI describes GPT 6 Sol as a model for complex coding and agentic workflows, and GPT 6 Luna as its most efficient model for focused, high-volume tasks.
For conversation analytics, that gives you two useful starting points to evaluate on your own data:
- Try Sol for an investigation with several steps. Compare periods, examine the customers behind a change, and work through a calculation that needs more than one query.
- Try Luna for a focused question. Ask for a grouped total, a short comparison, or the rows behind a number you already understand.
Those are starting points, not a ranking of answers. We have not published a GenViz benchmark comparing these models. Use a question whose answer you can verify, then compare the quality of the result and the work needed to get there.
Set the reasoning effort for the work
Sol and Luna start at medium reasoning effort in GenViz. Both offer none, low, medium, high, xhigh, and max in the model picker. You can adjust the setting as you choose the model for your next question.
A straightforward lookup may need less reasoning than an analysis involving several joins and business definitions. Start with medium, check the answer, and adjust for your task. Selecting none explicitly turns off reasoning; it does not remove the model’s access to GenViz analysis tools.
Put the new arrivals to work
Start with a concrete question:
Compare sales this month with the same number of days last month. Group by region, exclude cancelled orders, and show the totals in a table.
Then follow the evidence:
Which customers account for most of the change in the region with the largest decline? Show their sales in both periods.
You can open the returned table, inspect the query, and refine the dates or definitions in the same conversation. Saved extracts keep results available for later inspection. When the question calls for a calculation across extracts, Python analysis can produce another result to examine.
Sol and Luna use the same read-only database tools and connection controls as the other models in GenViz. Your prompts and the context used to answer them, including relevant schema information and query results, are sent to the selected model provider. Choose a provider that fits your organization’s data requirements; our privacy policy explains the services involved.
Choose Sol or Luna in your next conversation
Open the model picker and choose OpenAI → GPT 6 Sol or OpenAI → GPT 6 Luna. Availability follows your organization’s OpenAI access. On the Team plan, an administrator needs to configure an OpenAI API key with access to the model.
Pick a familiar question, inspect the answer, and ask the follow-up. The stable has grown; your data is still the place to judge the result.
Explore conversation analytics or download GenViz to get started.