An advanced search model designed for complex queries, delivering deeper content understanding with enhanced citation accuracy.

Model Type: Non-reasoning
Use Case: Suitable for multi-step Q&A tasks requiring deeper content understanding.

Key Features:

  • In-depth answers with 2x more citations than Sonar
  • Uses advanced information retrieval architecture
  • Optimized for multi-step tasks

Real-World Examples:

  • Conducting academic literature reviews
  • Researching competitors and industry trends
  • Generating restaurant catalogs with reviews
  • sonar-pro has a max output token limit of 8k.

​
Pricing

Legacy Pricing (Active Until 04/18/2025)

Legacy Pricing (Default if no search mode is specified)

Pricing:

Pricing ComponentCost
Input Tokens (Per Million)$3
Output Tokens (Per Million)$15
Price per 1,000 Requests$5

New Pricing (Available Now)

New Pricing with Search Modes
Explicit API call with search_context_size required to use new pricing.

MetricHigh  Medium  Low  
Input Tokens (Per Million)$3$3$3
Output Tokens (Per Million)$15$15$15
Price per 1,000 Requests$14$10$6

​
Test the Model

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sonar-pro",
  "messages": [
    {"role": "user", "content": "Summarize the latest research papers on climate change."}
  ],
  "max_tokens": 300
}'