Perplexity: Sonar Pro Search
Analysis Summary
Perplexity's Sonar Pro Search is a retrieval-augmented model designed to combine live web search with language generation. Its intelligence index of 15.5 and GPQA at 0.471 place it in the lower-mid tier for pure reasoning, but its core value proposition is real-time information access rather than benchmark performance. Vision support and a 200K context window add flexibility.
For businesses, this model is best suited to research-heavy content workflows, competitive intelligence, and tasks where up-to-date information is more important than deep reasoning. It is less appropriate for coding, agentic pipelines, or analytical tasks requiring sustained multi-step logic.
At $3.00 input and $15.00 output per million tokens, it is among the more expensive options in its capability tier. The premium is justified only when real-time retrieval is required; for static knowledge tasks, cheaper and more capable models are available.
Assessed July 10, 2026
Editorial notes
Perplexity Sonar Pro Search pairs real-time web retrieval with a 200K context window and vision support, but its reasoning benchmarks are modest and pricing is high for pure generation tasks.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
DFO Verdict
Perplexity Sonar Pro Search pairs real-time web retrieval with a 200K context window and vision support, but its reasoning benchmarks are modest and pricing is high for pure generation tasks.
Benchmark scores
Magenta = intelligence Ā· Ink = technical/agentic Ā· Cyan = content & long-context Ā· Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.
15.5 Intelligence Index
How Perplexity: Sonar Pro Search compares
Perplexity: Sonar Pro Search ranks #179 of 393 AI models we track for overall intelligence. Its 200K-token context window is larger than 63% of the models we list. At $3.00 per million input tokens it is cheaper than 11% of comparable models.
Dark bar = input Ā· light bar = output, scaled to the priciest peer.
1M tokens ā 8 full-length novels or ~2,500 pages of business documents in a single request.
Strongest on value. The pulled-in technical corner is the trade-off, and if the shape matters more than the price, this is your model.
Compare shapes side-by-side āPricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $3.00 | $0.003000 |
| Output | $15.00 | $0.015000 |
What would Perplexity: Sonar Pro Search cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 612 models ā Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Perplexity: Sonar Pro Search for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout Perplexity: Sonar Pro Search
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based..
Frequently asked questions about Perplexity: Sonar Pro Search
How much does Perplexity: Sonar Pro Search cost?
Perplexity: Sonar Pro Search costs $3.00 per million input tokens and $15.00 per million output tokens.
What is the context window of Perplexity: Sonar Pro Search?
Perplexity: Sonar Pro Search has a context window of 200,000 tokens (200K).
What can Perplexity: Sonar Pro Search do?
Perplexity: Sonar Pro Search supports image/vision input.
Who created Perplexity: Sonar Pro Search?
Perplexity: Sonar Pro Search is developed by Perplexity and was released on October 30, 2025.
