Author's Description
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Perplexity's Sonar Pro Search, an advanced agentic search system, demonstrates a balanced performance profile with notable strengths and areas for improvement. Its speed performance is moderate, ranking in the 28th percentile across benchmarks, indicating it is not among the fastest models available. Pricing is positioned at a premium level, falling into the 16th percentile, suggesting it is a more expensive option. A standout feature is its exceptional reliability, achieving a 100% success rate across all benchmarks, meaning it consistently provides usable responses without technical failures. In terms of accuracy, Sonar Pro Search excels in Coding (92.0%), General Knowledge (98.0%), Ethics (99.0%), and Mathematics (92.0%), showcasing strong capabilities in these domains. Its agentic search system, designed for deeper reasoning and analysis, likely contributes to these high scores. However, the model exhibits weaknesses in Hallucinations (80.0% accuracy, indicating a tendency to not always acknowledge uncertainty) and particularly in Email Classification (73.0% accuracy), where it ranks in the 6th percentile. Instruction Following and Reasoning show moderate accuracy at 60.0% and 74.0% respectively. The model's cost per request is consistently high across all categories, aligning with its premium pricing tier.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $3 |
| Completion | $15 |
| Web Search | $18000 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Perplexity
|
Perplexity | perplexity/sonar-pro-search | 200K | $3 / 1M tokens | $15 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by perplexity
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Perplexity: Sonar Reasoning Pro | Mar 06, 2025 | — | 128K |
Text input
Image input
Text output
|
★★ | ★★★ | $$$$$ |
| Perplexity: Sonar Pro | Mar 06, 2025 | — | 200K |
Text input
Image input
Text output
|
★★★ | ★★★ | $$$$$ |
| Perplexity: Sonar Deep Research | Mar 06, 2025 | — | 128K |
Text input
Text output
|
— | — | $$$$$ |
| Perplexity: R1 1776 Unavailable | Feb 19, 2025 | — | 128K |
Text input
Text output
|
★★ | ★★★★★ | $$$$$ |
| Perplexity: Sonar Reasoning Unavailable | Jan 28, 2025 | — | 127K |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
| Perplexity: Sonar | Jan 27, 2025 | — | 127K |
Text input
Image input
Text output
|
★★★ | ★★ | $$$$ |
| Perplexity: Llama 3.1 Sonar 70B Online Unavailable | Jul 31, 2024 | 70B | 127K |
Text input
Text output
|
★★★ | ★ | $$$$ |
| Perplexity: Llama 3.1 Sonar 8B Online Unavailable | Jul 31, 2024 | 8B | 127K |
Text input
Text output
|
★★★ | ★ | $$ |