Perplexity: Sonar Deep Research
Review
Perplexity's Sonar Deep Research is positioned as a research-focused model but has no published benchmark data to assess its capability independently. Without measurable performance data, it is difficult to recommend for business-critical applications beyond exploratory research use.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Instruct Type | deepseek-r1 |
How does Perplexity: Sonar Deep Research stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
perplexity/sonar-deep-research
|
| Provider | perplexity |
| Release Date | March 7, 2025 |
| Context Length | 128,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $2.00 | $0.002000 |
| Output | $8.00 | $0.008000 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
