- Home
- Models
- Perplexity
- Sonar Deep Research
Specialized autonomous research model conducting dozens of searches and processing hundreds of sources to generate comprehensive reports. Features iterative research planning with reasoning capabilities, ideal for expert-level analysis across finance, marketing, and technology domains.
- Autonomous research capabilities conducting dozens of searches and analyzing hundreds of sources
- Iterative research planning that refines understanding and strategy as it learns about subject areas
- Comprehensive report generation with expert-level analysis across finance, marketing, and technology
- Export and sharing functionality with PDF generation and Perplexity Pages for collaboration
- Research with reasoning combining search, coding, and analytical capabilities for thorough investigations
Model Information
Supported Formats
In-house search-grounded model based on Llama 3.3 70B, optimized for speed and cost-efficiency with real-time web research capabilities. Ideal for straightforward factual queries requiring fast, cited responses with lightweight question-and-answer integration.
Enhanced search model achieving best-in-class factuality with F-score of 0.858 on SimpleQA benchmark. Designed for complex multi-step tasks with double the citations of base Sonar, providing deeper understanding and context retention.
Chain-of-thought reasoning model with embedded live search capabilities, specialized for logical reasoning and step-by-step inference. Excels in mathematical, coding, and analytical challenges requiring sustained reasoning over multiple steps.