Use this level when you want to minimize latency, allowing for minimal thought. This level is faster than low.

This level is suitable for simpler queries or when speed is the priority. This level is faster than medium.

Offers a balanced approach suitable for tasks of moderate complexity that benefit from reasoning but don’t require deep, multi-step planning. It provides more reasoning capability than low while maintaining lower latency than high.

Use this level for complex queries where quality is more important than speed. It allows the model to engage in deeper reasoning but increases latency.