Perplexity’s Sonar is a lightweight search model with 127K context, live web search on every call, inline citations, and low-cost pricing.
Capabilities, design details, and architectural traits
Sonar is Perplexity’s lightweight search model for web-grounded answers. Perplexity positions it as the base tier of the Sonar API family, optimized for fast, citation-backed responses at low cost.
Sonar is intended for high-volume queries where cited answers matter more than deep reasoning. Perplexity also notes that it is optimized for answer quality and user experience, and that it can be used through the Sonar API.
The official Sonar API supports streaming, tools, search options, and OpenAI-compatible usage. Perplexity lists Sonar as the most accessible price point in the family, with API pricing documented separately for input and output tokens.
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Perplexity | Anthropic | Anthropic |
| Release Date | January 21, 2025 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | - | May 2026 | - |
| Context & Limits | |||
| Context Window | 127K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | Free Best Input Pricing | $5 | $10 |
| Output Pricing | Free Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | textimage | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 9.4 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | - | 78.0 Best Coding Index | 76.5 |
| Agentic Index | - | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
