From the source
Perplexity released pplx-decider-v1.2, replacing pplx-decider-v1.1-27b as the 27B decision model at $0.02 per million input tokens, and introduced pplx-decider-flash-v1.2, a new 4B decision model at $0.01 per million input tokens.
Both models accept text and images with the same request limits, and output tokens remain free.
