A lightweight, cost-effective search model optimized for quick, grounded answers with real-time web search.

Model Type: Non-reasoning
Use Case: Ideal for quick searches and straightforward Q&A tasks.

Key Features:

  • Real-time web search-based answers with citations
  • Optimized for speed and cost

Real-World Examples:

  • Summarizing books, TV shows, and movies
  • Looking up definitions or quick facts
  • Browsing news, sports, health, and finance content

​
Pricing

Legacy Pricing (Active Until 04/18/2025)

Legacy Pricing (Default if no search mode is specified)

Pricing:

Pricing ComponentCost
Input Tokens (Per Million)$1
Output Tokens (Per Million)$1
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.

Pricing ComponentHigh  Medium  Low  
Input Tokens (Per Million)$1$1$1
Output Tokens (Per Million)$1$1$1
Price per 1,000 Requests$12$8$5

​
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",
  "messages": [
    {"role": "user", "content": "What is the latest news in AI research?"}
  ],
  "max_tokens": 200
}'