Sonar Pro
Perplexity Sonar Pro is a search-augmented model for complex research queries, offering 200K context, multi-step web retrieval, and citation-rich answers.
Model Overview
Capabilities, design details, and architectural traits
Sonar Pro - Advanced Search Model for Deep Web Retrieval
Sonar Pro is Perplexity's premium search model for complex research queries. The official docs position it as a search-augmented model that retrieves more sources per query and returns citation-rich answers.
Core Design
Perplexity describes Sonar Pro as sharing the same foundational search-augmented architecture as Sonar, but with deeper web retrieval across more sources. It is intended for queries that need cross-referencing and broader evidence synthesis.
Operating Pattern
The model keeps the same single-call developer flow as base Sonar, with no external search configuration required. Perplexity notes that web search runs on each inference call, and Sonar Pro simply expands how many candidate sources are gathered and synthesized.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Perplexity | Anthropic | Anthropic |
| Release Date | January 21, 2025 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | - | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 200K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | Free Best Input Pricing | $4 | $2 |
| Output Pricing | Free Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | textimage | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 7.6 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | - | - | - |
| Agentic Index | - | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
SciCode Benchmark
Scientific coding and mathematical modeling.
Long Context Reasoning
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Perplexity
Other models by Perplexity
Top AI Models
Leading alternatives by intelligence score
