Skip to main content
Perplexity models can be configured in Langdock using the Perplexity API. These models are particularly useful for search-augmented generation, combining LLM capabilities with real-time web search.

​
Prerequisites

Before setting up Perplexity models, you need:
  1. A Perplexity account at perplexity.ai
  2. An API key from the Perplexity API settings
  3. Admin access to your Langdock workspace

​
Setup Steps

  1. Go to the model settings and click on Add Model
  2. Configure the Display Settings:
    • Provider: Perplexity
    • Model name: The model you want to add (e.g., Sonar Pro, Sonar)
    • Hosting provider: Perplexity
    • Region: US (Perplexity’s API is hosted in the US)
    • Image analysis: Disabled (Perplexity models do not support vision)
  3. Configure the Model Configuration:
    • SDK: Select Perplexity
    • Base URL: Leave empty to use the default (https://api.perplexity.ai) or specify a custom endpoint
    • Model ID: Use the official model identifier (see Model IDs below)
    • API key: Paste your Perplexity API key
    • Context Size: Set according to the model (check Perplexity’s documentation for current values)
  4. Click Save and test the model by sending a prompt before making it visible to all users

​
Model IDs

Perplexity’s Sonar model family includes search-augmented and reasoning variants:
Model IDType
sonar-proAdvanced search-augmented generation — detailed responses with citations
sonarFast search-augmented responses — good for general-purpose queries
sonar-reasoning-proDeep analysis with search — multi-step reasoning with citations
sonar-reasoningReasoning with search augmentation
Check Perplexity’s model documentation for the full list of available models, their specifications, and context sizes.

​
Configuration Notes

  • Perplexity models include built-in web search capabilities, so they always have access to current information
  • The API endpoint https://api.perplexity.ai is automatically used when no custom Base URL is provided
  • Sonar Pro models provide more detailed responses with better source citations
  • Reasoning variants are best for complex analytical tasks that benefit from step-by-step thinking

​
Troubleshooting

Model not responding:
  • Verify your API key is valid and has not expired
  • Check that you have sufficient credits in your Perplexity account
  • Ensure the model ID matches exactly (case-sensitive)
Missing citations:
  • Perplexity models include citations automatically when web search is used
  • If citations are missing, the model may have answered from its base knowledge
Slow responses:
  • Perplexity models perform web searches, which adds latency
  • Sonar (non-Pro) variants are faster than Pro versions
  • For time-sensitive tasks without search needs, consider using a different model
If you run into any issues, contact support@langdock.com.