pplx-decider-v1.2 is the 27B default for nuanced decisions at $0.02 per million input tokens.
pplx-decider-flash-v1.2 is for high-volume decisions with clear criteria like routing, labeling, and filtering, at half the price.
Perplexity launches pplx-decider-v1.2 models for AI decision tasks
AISummary
Perplexity says pplx-decider-v1.2, a 27B model, is its default for nuanced decisions at $0.02 per million input tokens. Its lower-cost sibling, pplx-decider-flash-v1.2, targets high-volume work with clear criteria, such as routing, labeling, and filtering, at half that price.
Post on XView on X
Source: Perplexity Developers · x.comPublished · added here