Perplexity
Models published by Perplexity, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
PPLX Decider v1 (27B) is Perplexity's multimodal decision model: send application state and typed questions (noul / choice / score) and get back a probability distribution over a fixed set of answers — it returns probabilities, not generated chat text, and produces no free-form output. `state` may be a string, an object, or an array of OpenAI-style `image_url` parts carrying base64 PNG/JPEG/WebP data URLs, so it also scores images. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).
PPLX Decider v1.1 (27B) is a newer checkpoint of Perplexity's multimodal decision model, with the same Decisions API contract as v1: send application state and typed questions (noul / choice / score) and get back a probability distribution over a fixed set of answers — it returns probabilities, not generated chat text, and produces no free-form output. `state` may be a string, an object, or an array of OpenAI-style `image_url` parts carrying base64 PNG/JPEG/WebP data URLs, so it also scores images. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).
pplx-embed-v1-0.6B is Perplexity's lightweight text embedding model for web-scale dense retrieval, aimed at low-latency use. 32K-token input.