Documentation Index
Fetch the complete documentation index at: https://mintlify.com/perplexityai/modelcontextprotocol/llms.txt
Use this file to discover all available pages before exploring further.
Overview
Theperplexity_research tool performs comprehensive, in-depth research using the Sonar Deep Research model. It analyzes multiple sources to provide thorough, well-researched answers with extensive citations.
This tool uses the sonar-deep-research model with streaming enabled for real-time progress updates during long research operations.
Use Cases
- Literature reviews and academic research
- Comprehensive topic overviews
- Investigative journalism queries
- Multi-perspective analysis
- In-depth market research
- Complex technical documentation
Parameters
Array of conversation messages in OpenAI format.Each message must have:
role: One of"system","user", or"assistant"content: The message text (string)
If
true, removes <think>...</think> tags and their content from the response.The model may include internal reasoning in <think> tags. Stripping these saves context tokens in long conversations.Default: false (shows thinking process)Example: trueControls the depth of deep research reasoning.Options:
"minimal", "low", "medium", "high""minimal": Fastest, less thorough analysis"low": Balanced speed and depth"medium": Comprehensive analysis"high": Most thorough, slowest
"high"Response Format
The tool returns a detailed, AI-generated research report with extensive citations:Comprehensive research response with:
- In-depth analysis from multiple sources
- Numbered citation references
[1],[2], etc. - Optional
<think>...</think>tags (ifstrip_thinking: false) - Citations list appended at the end
Example Response
Usage Examples
Common Patterns
Academic Literature Review
Produce comprehensive research summaries:Market Research
Analyze industry trends and competitive landscapes:Technical Deep Dive
Investigate complex technical topics:Advanced Usage
Multi-turn Research Conversation
Token Optimization
For long conversations, strip thinking to save tokens:Tips and Best Practices
The tool uses streaming to provide real-time progress updates. You’ll receive partial results as the research progresses, rather than waiting for the entire response.
Understanding Thinking Tags
Whenstrip_thinking: false (default), responses may include <think>...</think> tags:
- Research strategy and planning
- Source evaluation reasoning
- Analytical approach
- Information synthesis logic
strip_thinking: true to remove these tags and save ~10-20% of response tokens.
Comparison with Other Tools
| Feature | perplexity_research | perplexity_ask | perplexity_reason |
|---|---|---|---|
| Model | sonar-deep-research | sonar-pro | sonar-reasoning-pro |
| Speed | Very slow (30s+) | Fast (< 5s) | Medium (5-15s) |
| Sources | Many (10+) | Few (3-5) | Moderate (5-8) |
| Depth | Comprehensive | Standard | Analytical |
| Best For | Literature reviews | Quick Q&A | Logic problems |
| Thinking Tags | Yes (optional) | No | Yes (optional) |
| Reasoning Effort | Adjustable | N/A | N/A |
| Filters | No | Yes (recency, domain, context) | Yes (recency, domain, context) |
perplexity_research is the only tool that supports reasoning_effort parameter and uses streaming by default.Error Handling
Common errors and solutions:- Timeout errors: Increase
PERPLEXITY_TIMEOUT_MSenvironment variable - Invalid messages array: Ensure each message has
roleandcontentfields - Invalid reasoning effort: Must be
minimal,low,medium, orhigh - Network errors: Check API key and connectivity
- Stream parsing errors: Usually transient, retry the request
Performance Optimization
Reduce Timeout
Use
reasoning_effort: "low" or "minimal" for faster resultsSave Tokens
Enable
strip_thinking: true to reduce response size by 10-20%Cache Results
Store research results locally to avoid re-running expensive queries
Parallel Research
Run multiple focused queries in parallel instead of one broad query
Related Tools
Ask Tool
Use for quick questions that don’t need deep research
Reason Tool
Use for logical analysis and step-by-step reasoning
Search Tool
Use to find sources before conducting research
Tools Overview
Compare all available tools and their capabilities