Skip to main content

Decisions API: pplx-decider-v1.2 and pplx-decider-flash-v1.2

By Steven Van ·

The 27B decider stays at $0.02 per million input tokens, and a new 4B flash model costs $0.01, with both accepting text and images.

Perplexity's Decisions API has a new 27B model, pplx-decider-v1.2, which replaces pplx-decider-v1.1-27b. It also gains a smaller 4B option, pplx-decider-flash-v1.2. The change is part of the Perplexity October 2026 changelog.

Models and pricing

  • pplx-decider-v1.2 is the 27B decision model, at $0.02 per million input tokens.
  • pplx-decider-flash-v1.2 is a new 4B decision model, at $0.01 per million input tokens.

Both models accept text and images and use the same request limits. Output tokens stay free.

Following the newest version

Use pplx-decider-latest or pplx-decider-flash-latest to follow the newest version of each model. The names perplexity/pplx-decider-latest and perplexity/pplx-decider-flash-latest are also accepted.

Existing requests

Requests that name pplx-decider-v1.1-27b or pplx-decider-v1-27b continue to work and now select pplx-decider-v1.2.

Perplexity
Perplexity
AI-powered answer engine — ask anything and get cited, real-time answers from across the web.
View Perplexity →
Sources

Original source

Read Decisions API: pplx-decider-v1.2 and pplx-decider-flash-v1.2 on Creators Toolbox