Skip to main content

Overview

sonar-pro is Perplexity’s pro web-search model. Like sonar, it answers from a live search of the web with citations — but it searches deeper, reasons over more sources, and writes longer, more complete answers. Use it for complex current-events questions and research tasks where a one-line lookup is not enough. Sonar Pro does its own searching internally. You send a question; it returns a grounded, cited report. It does not support tool calling.

Specs

Pricing

Sonar Pro bills two ways on the same request:
  • Tokens4.05/1Minput,4.05 / 1M input, 20.25 / 1M output.
  • Web-search fee — a flat $0.00675 per request, on top of tokens, for the live search.
Because the search fee is flat, it matters less here than on sonar — Sonar Pro’s longer, multi-source answers make the output tokens the larger line item. Every response’s usage.cost already includes the search fee. See Pricing → Web search.

Use this when

  • The question is complex and current — multi-part research, comparisons across recent sources, “what changed and why.”
  • You want a longer, well-cited answer rather than a quick fact.
  • You need more context room (200K) for a large prompt plus a long grounded response.

Pick something else when

  • A quick cited lookup is all you need: sonar is cheaper per request.
  • You need function calling / tools: use kimi-k2.6.
  • The task does not need fresh web data: a standard model avoids the per-request search fee entirely.

Example