Sonar Pro Search
VerifiedDelivers precise real-time answers via integrated web search and image analysis.
About Sonar Pro Search
Sonar Pro Search combines large-scale language processing with live web retrieval. Its architecture prioritizes factual grounding by pulling current information during inference. The model accepts both textual prompts and visual data for richer context handling.
Key strengths include extensive context retention and seamless multimodal fusion. It maintains accuracy on time-sensitive queries without relying on static training cutoffs. Users benefit from transparent source citations in generated outputs.
Typical applications range from in-depth research assistance to real-time news summarization. Professionals leverage it for verifying claims across documents and images. The system suits scenarios requiring up-to-date multimodal insights rather than creative generation.
Capabilities
How Sonar Pro Search compares
Sonar Pro Search (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Sonar Pro Search ranks #87 of 104
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Current Events Summarization
This model excels at delivering concise overviews of breaking news and developments by combining real-time web search with source-backed reasoning.
Long-Form Document Review
It handles detailed analysis of lengthy reports and files up to 200000 tokens while incorporating multimodal image and text understanding.
Cited Factual Research
Ideal for users seeking verified answers to complex questions through integrated search results and explicit source citations.
Strengths & limitations
Strengths
- +Up-to-date information retrieval
- +Transparent citations and sourcing
- +Strong knowledge-intensive query handling
- +Efficient large-context analysis
Limitations
- –Dependent on search result quality
- –Less emphasis on open-ended creative tasks
- –Potential added latency from retrieval
Cost calculator
Estimate what Sonar Pro Search would cost for your usage.
Based on Sonar Pro Search's $3.00/1M input · $15.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "perplexity/sonar-pro-search",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: perplexity/sonar-pro-search
Editor's verdict
Sonar Pro Search is Perplexity's proprietary multimodal with a 200K-token context window.
At $15.00 per 1M output tokens, it is premium-priced for its class.
It is available through Perplexity's API and aggregators like OpenRouter.
Best suited to up-to-date information retrieval and transparent citations and sourcing.
Frequently asked questions
It supports a context length of 200000 tokens for processing extended inputs and documents.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Similar models
Other multimodal worth comparing.