Perplexity models
All 9 Perplexity models on OpenDunes, priced in Algerian Dinars.
9 models
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.
Embed V1 0.6B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 1,024 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the small, quick model of the pair.
Embed V1 4B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 2,560 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the larger model of the pair, tuned for the best result quality.
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.
Sonar answers a question with a web search behind it: you send text or a picture and get a written answer with citations, and you can choose which sources it draws on. It keeps about 127 pages in mind at once and is the lightest, fastest model of the Sonar line, meant for question-and-answer features inside an app.
Perplexity's enterprise search model for questions that take several searches to answer, citing about twice as many sources per search as Sonar and holding more context for long follow-up threads
Perplexity's most advanced agentic search, the system behind its Pro Search mode, which adds multi-step reasoning to Sonar Pro so it plans and runs a whole research workflow with tools rather than one query
The reasoning version of Perplexity's Sonar Pro, which thinks step by step before it answers in-depth search questions, with about twice Sonar's citations per search and image input
Perplexity's research model, which runs many searches on its own, reads and weighs sources, adjusts its approach as it learns and then reasons through everything to write a full report on the topic