- Home
- Models
- Perplexity
- Sonar Reasoning
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.
- Chain-of-thought reasoning capabilities with embedded live search for enhanced logical problem-solving
- Specialized performance in logical, mathematical, and coding challenges requiring step-by-step analysis
- Enhanced decision-making with ability to maintain multiple pieces of information across reasoning steps
- Cost-efficient reasoning model delivering advanced analytical capabilities at accessible pricing
- Integrated search grounding ensuring factual accuracy during complex reasoning processes
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.
Advanced reasoning model powered by DeepSeek-R1 1776 integration, delivering superior step-by-step inference and comparison capabilities. Optimized for research synthesis, evaluation tasks, and complex analytical workflows requiring deep reasoning.