Perplexity Sonar Pro

Perplexity Sonar Pro, a web-search-augmented LLM.

Perplexity Sonar Pro, a web-search-augmented LLM. Every answer cites live sources retrieved in real time so you can verify and dig deeper. Use it for research, current events, fact-checking, and any question where you need up-to-date information beyond a model's training cutoff. Maximum context window (input and output combined): about 200,000 tokens. Maximum output per reply: about 8,000 tokens (model reasoning, if any, counts toward this limit). Maximum total upload size per request: 256MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: gif, jpeg, jpg, png, webp. Maximum size per image: 50MB. Image dimensions: at least 200 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Text This module supports continuous conversations. AI can make mistakes. Please verify important information.