Perplexity
California, 美国Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Premier reasoning offering powered by DeepSeek R1 with Chain of Thought (CoT).
Premier search offering with search grounding, supporting advanced queries and follow-ups.
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
Lightweight offering with search grounding, quicker and cheaper than Sonar Pro.
Perplexity's most thorough research agent. It runs many rounds of web search and page reading on a frontier model, then writes a long, cited report. Requests can take several minutes.
Perplexity decision model distilled from 27B decision models onto Qwen3.5-4B. Answers typed choice, yes/no and score questions over text and images using joint question processing.
Perplexity decision model based on Qwen3.8-27B. Answers typed choice, yes/no and score questions over text and images, processing related questions together in one sequence.
Perplexity's 0.6B text embedding model with Matryoshka dimensions and quantized INT8 or binary output.
Perplexity's 4B text embedding model with Matryoshka dimensions and quantized INT8 or binary output.
Perplexity decision model for typed yes/no, choice, and score questions over text, JSON, and images.
Decider 27B is a decision model from Perplexity that answers typed yes/no, choice and score questions with probabilities instead of generated text. It accepts text, JSON or image input with up to 262,144 tokens per request.