Perplexity: Sonar Reasoning Pro

Image input Text input Text output
Author's Description

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.

Key Specifications
Cost
$$$$$
Context
128K
Released
Mar 06, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Frequency Penalty Max Tokens Reasoning Presence Penalty Include Reasoning Temperature
Features

This model supports the following features:

Reasoning
Performance Summary

Perplexity: Sonar Reasoning Pro, created on March 6, 2025, is positioned as a premier reasoning model. In terms of speed, it tends to have longer response times, ranking in the 12th percentile across benchmarks. Its pricing is at a premium level, placing it in the 5th percentile for cost-effectiveness. Notably, the model demonstrates strong reliability, achieving the 95th percentile, indicating consistent and usable responses with minimal technical failures. Across benchmarks, Sonar Reasoning Pro exhibits a mixed performance profile. It excels in Coding and Reasoning, achieving 89th and 88th percentile accuracy respectively, suggesting strong capabilities in structured problem-solving and logical inference. General Knowledge is also a strength, with 99.0% accuracy. However, its performance in Ethics (33rd percentile) and Instruction Following (34th percentile) is moderate, while Email Classification shows a significant weakness, ranking in the 11th percentile. The model's key strengths lie in its robust reasoning and coding abilities, supported by high reliability. Its primary weaknesses are its slower response times, premium pricing, and lower accuracy in specific classification and instruction-following tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2
Completion $8
Web Search $5000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Perplexity
Perplexity | perplexity/sonar-reasoning-pro 128K $2 / 1M tokens $8 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by perplexity