You can now select which AI model powers your Underlord editing assistant through our new model picker, which includes Claude Sonnet 4.5.
Different editing tasks benefit from different AI approaches, so we've integrated several powerful models including the latest from Anthropic. Whether you need lightning-fast responses or deep creative understanding, you can now choose the right AI for each project.
Why choose different models?
Each AI model offers unique strengths for different editing scenarios:
- Auto: Our smart default that balances speed, quality, and efficiency for most tasks
- Auto (experimental): Enhanced capabilities for complex, multi-step editing workflows
- Claude Sonnet 4.5: Superior understanding for complex script editing and creative work
- GPT 4.1: The lowest cost model for simple tasks and a different tone/style familiar to OpenAI users
- Claude Opus 4.1: Premium performance for nuanced creative decisions and complex projects, can take slightly longer during processing
Our testing with Claude Sonnet 4.5 demonstrates notable improvements in script editing quality, content writing capabilities, and performance with complex multi-step prompt templates, while being a somewhat less reliable in interacting with our built in tools like captions, and translation.
We’re still testing and refining how these models perform in the Editor, and we’d love for you to join us in pushing the limits.
You can switch models anytime by clicking the model icon at the bottom of the Underlord chat panel. While premium models deliver enhanced results, they do use more AI credits, so you can always select the option that best fits your current needs.
Note: These models are available on all plans for a limited time, including Legacy and Sunset plans.