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 on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform. Sonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Perplexity: Sonar Pro Search, a sophisticated agentic search system designed for deeper reasoning and analysis, demonstrates a balanced performance profile with notable strengths and areas for improvement. Its speed performance is moderate, ranking in the 25th percentile across benchmarks, indicating it is not among the fastest models available. Pricing is positioned at premium levels, falling into the 13th percentile, suggesting it is a more expensive option. A significant highlight is its exceptional reliability, achieving a 100% success rate across all benchmarks, meaning it consistently provides usable responses without technical failures. In terms of specific benchmarks, Sonar Pro Search excels in Coding (92.0% accuracy, 78th percentile) and Mathematics (92.0% accuracy, 71st percentile), showcasing strong capabilities in technical and quantitative domains. Its General Knowledge is also robust at 98.0% accuracy. However, it exhibits a notable weakness in Email Classification, with a low 73.0% accuracy (7th percentile), indicating potential struggles with nuanced categorization tasks. Hallucination control is moderate at 80.0% accuracy, suggesting occasional instances of generating ungrounded information. Instruction Following and Reasoning show average performance. Overall, Sonar Pro Search is a highly reliable model with strong analytical and technical skills, though its premium pricing and moderate speed should be considered.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $3 |
| Completion | $15 |
| Request | $0.018 per request |
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 |
Image input
Text input
Text output
|
★ | ★★★★ | $$$$$ |
| Perplexity: Sonar Pro | Mar 06, 2025 | — | 200K |
Image input
Text input
Text output
|
★★★ | ★★★ | $$$$$ |
| Perplexity: Sonar Deep Research | Mar 06, 2025 | — | 128K |
Text input
Text output
|
— | — | $$$$$ |
| Perplexity: R1 1776 Unavailable | Feb 19, 2025 | — | 128K |
Text input
Text output
|
★★ | ★★★★★ | $$$$$ |
| Perplexity: Sonar Reasoning | Jan 28, 2025 | — | 127K |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
| Perplexity: Sonar | Jan 27, 2025 | — | 127K |
Image input
Text input
Text output
|
★★★ | ★★★ | $$$$ |
| Perplexity: Llama 3.1 Sonar 70B Online Unavailable | Jul 31, 2024 | 70B | 127K |
Text input
Text output
|
★★★ | ★ | $$$$ |
| Perplexity: Llama 3.1 Sonar 8B Online Unavailable | Jul 31, 2024 | 8B | 127K |
Text input
Text output
|
★★★ | ★ | $$ |