perplexity-search

Search the web with Perplexity models via OpenRouter and return cited results.

21|1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/OwnLabAI/ownlab --skill perplexity-search-ownlabai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/OwnLabAI/ownlab/tree/main/mart/skills/scientific-skills/perplexity-search
Command: npx skills add https://github.com/OwnLabAI/ownlab --skill perplexity-search-ownlabai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires litellm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Real-time web-grounded information for scientific questions with source citations, ensuring up-to-date results beyond model training data.

Core Features & Use Cases

  • Real-time web searches with Perplexity models via LiteLLM and OpenRouter to provide current results with citations.
  • Access to multiple Perplexity models (sonar-pro, sonar-pro-search, sonar, sonar-reasoning-pro, sonar-reasoning) via a single API key.
  • Seamless integration guidance for literature reviews, fact-checking, and rapid background research across biomedical, technical, and clinical domains.
  • Simple setup and CLI utilities to validate environment and perform searches.

Quick Start

Run a simple Perplexity search to obtain current web results with citations.

Frequently Asked Questions about perplexity-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get real-time web search results with citations for a literature review?

Real-time web search results with citations are generated by querying Perplexity models via LiteLLM and OpenRouter. This provides current, web-grounded answers with source citations for literature reviews, ensuring information is up-to-date beyond model training data.

Do I need a separate API key for each Perplexity model I want to use?

No, a single OpenRouter API key is required to access multiple Perplexity models (sonar-pro, sonar, sonar-reasoning-pro, and sonar-reasoning) through a LiteLLM-capable environment, simplifying authentication and model selection.

Can I use Perplexity search for fact-checking biomedical and clinical research?

Yes, Perplexity search supports rapid background research and fact-checking across biomedical, technical, and clinical domains. It retrieves real-time scientific information with grounded citations, ensuring accurate verification of up-to-date clinical data.

What's the best way to integrate web-grounded search into an existing LiteLLM environment?

The best way to integrate web-grounded search into a LiteLLM environment is by using the provided CLI utilities and scripts. These tools validate the environment, handle errors, manage token budgeting, and perform searches through an OpenRouter API key.

Does LiteLLM support token budgeting and model selection for OpenRouter queries?

Yes, LiteLLM supports token budgeting, model selection, and error handling when accessing Perplexity models via OpenRouter. This ensures controlled resource allocation and flexible switching between sonar models during web-grounded searches.