Perplexity
MultimodalAUTO PROFILEPriced via OpenRouter

Sonar Pro Search

text+image->text

Sonar Pro Search is a retrieval-tuned model designed for grounded answers over a corpus or live web search rather than pure generation. Available via Perplexity. 200,000-token context. Premium pricing.

Sonar Pro Search is a multimodal AI model from Perplexity. It costs $3.00 per million input tokens and $15.00 per million output tokens (blended $6.60/M), with a 200,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$3.00/M
per million input tokens
OUTPUT
$15.00/M
per million output tokens
BLENDED 70/30
$6.60/M
unchanged since 3 May
CONTEXT
200,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Grounded answers with citations
  • Live web or doc retrieval
  • Lower hallucination on factual queries
  • Multimodal: handles images alongside text
Typical use cases
  • Knowledge-base chat
  • Citation-required answers
  • Live news/research assistants

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Perplexity

See all 6 →

Frequently asked questions

How much does Sonar Pro Search cost?

Sonar Pro Search costs $3.00 per million input tokens and $15.00 per million output tokens, for a blended reference rate of $6.60 per million tokens.

What is Sonar Pro Search's context window?

Sonar Pro Search supports up to 200,000 tokens of context in a single request.

What is Sonar Pro Search best for?

Sonar Pro Search is well suited to Grounded answers with citations, Live web or doc retrieval and Lower hallucination on factual queries.

Who makes Sonar Pro Search?

Sonar Pro Search is developed and served by Perplexity.

Terms used on this page