Skip to main content

Sonar Deep Research

Perplexity 🧠 Language Model

Perplexity's most thorough research model, multi-step deep web investigation with comprehensive citations and reasoning.

Specifications

Output modalitiestext
Capabilitiessearch, reasoning
Relative speed●○○○○ Slow
Context window128,000 tokens
Max output32,768 tokens
Input price$3.50 / 1M
Output price$14.00 / 1M

Pricing

$3.50 / 1M input tokens  ·  $14.00 / 1M output tokens

Platform credit pricing — live rates on the Models page.