perplexity-search

Search the web with Perplexity models via LiteLLM and OpenRouter.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill perplexity-search-scimate-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: perplexity-search
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/perplexity-search
Command: npx skills add https://github.com/SciMate-AI/scicli --skill perplexity-search-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web-based research often requires up-to-date information and verifiable sources; this skill provides real-time, web-grounded search results with citations by querying Perplexity models through OpenRouter via LiteLLM.

Core Features & Use Cases

  • Real-time web search with citations from current sources
  • Access to multiple Perplexity models via a single API key
  • Guided setup, usage, and troubleshooting references for OpenRouter and LiteLLM

Quick Start

Run a query through perplexity_search.py to fetch real-time, web-grounded results.

Frequently Asked Questions about perplexity-search

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

FAQPage Schema
How do I perform real-time web searches with citations using AI models?▼

You can perform real-time web search with citations by querying Perplexity models through OpenRouter via LiteLLM, which fetches web-grounded results with verifiable sources using a single API key.

Do I need an OpenRouter API key to access Perplexity models for research?▼

Yes, accessing multiple Perplexity models for research requires an OpenRouter API key and a LiteLLM installation to validate setup and execute web-grounded searches.

What's the best way to get verifiable sources for literature discovery tasks?▼

Using Perplexity models via LiteLLM provides optional citation extraction from current web sources, making it an effective way to get verifiable citations for literature discovery.

Can I select different Perplexity models through a single API key?▼

Yes, this approach provides model selection across multiple Perplexity models through a single OpenRouter API key, along with setup validation and optional citation extraction.

Why does my LiteLLM setup fail when querying Perplexity through OpenRouter?▼

LiteLLM setup may fail due to missing or invalid OpenRouter API keys; the skill provides guided setup, usage, and troubleshooting references to validate configurations and resolve errors.