by ~perplexityReleased 12 October 2026
Perplexity's 27B decision model, the successor to Decider V1 that also reads images beside text and JSON and lifts its Decision Index from 56.4 to 61.56, answering up to 128 named questions in one request
About 260 pages per case
No. ~perplexity has retired it. Other ~perplexity models are on sale.
Perplexity's 27B decision model, the successor to Decider V1 that also reads images beside text and JSON and lifts its Decision Index from 56.4 to 61.56, answering up to 128 named questions in one request.
~perplexity names no languages for Decider 27B Latest. Arabic, French and Darja: not stated.
Yes or no, one choice from your list, or a score on your scale. Each answer comes with its probability.
~perplexity. Released 12 October 2026.
Decider Flash V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns a probability for every answer, so your own system sets its thresholds for sorting, routing or moderating high volumes.
Decider V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions of three kinds: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns the probability of every answer, so your own system sets its thresholds for sorting, routing or moderation. It is the larger model of the pair and reads about 262 pages; Decider Flash V1.2 is the smaller, lower-cost version.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 14 Oct 2026.
Classify screenshots or page images into one of your fixed action labels from image input
Route each incoming support ticket to a team by reading the ticket text as state
Score long conversation logs against a rule set and emit a single yes or no verdict
