3 docs tagged with "routing"

Step-by-step guidance for platform administrators on how to set the Thinking directive for a tier on the Tier map of a PaletteAI Inference Launchpad appliance.

How the Thinking directive on the Tier Map controls reasoning depth, why the off option is disabled for some providers, and how a token budget is interpreted across engines.

Reference of the Thinking directive modes on the Tier map, the value each mode carries at request time, the console states that override the setting, and how each engine family interprets a token budget.