The right model for the job - how Rovo chooses its LLM

This AI Cast episode explains that Rovo does not rely on a single LLM, but instead selects the right model for each task. In the Rovo CLI, users can either let Rovo auto choose or explicitly select from OpenAI (GPT) models, Anthropic (Claude) models, and Gemini models. The key budgeting detail is the credit multiplier column, since different models use different credits per prompt. Heavier models can cost more but are better for demanding work like coding or deep financial analysis, while lighter models can summarize emails efficiently at lower credit cost. For partners, the recommendation is to keep auto selection enabled for most users and provide power users guidance on when higher-cost models are worth it.

About Atlassian:
Behind every great human achievement, there is a team. From medicine and space travel to disaster response and pizza deliveries, we help teams all over the planet advance humanity through the power of software. Our mission is to help unleash the potential of every team.

Connect with Atlassian:
Subscribe: https://www.youtube.com/@Atlassian
Follow Atlassian on LinkedIn: https://www.linkedin.com/company/atlassian
Follow Atlassian on Instagram: https://instagram.com/atlassian
Follow Atlassian on X: https://twitter.com/atlassian
Follow Atlassian on Facebook: https://facebook.com/atlassian