Optional
apiAPI key for Perplexity. Defaults to the value of PERPLEXITY_API_KEY environment variable.
Optional
disableWhen set to true, disables web search completely and the model will only use its training data to respond. This is useful when you want deterministic responses without external information.
Optional
enableEnables a classifier that decides if web search is needed based on your query.
Optional
frequencyFrequency penalty greater than 0
Optional
lastFilters search results to only include content last updated after this date.
Optional
lastFilters search results to only include content last updated before this date.
Optional
maxMaximum number of tokens to generate
Model name to use
Optional
presencePresence penalty between -2 and 2
Optional
reasoningControls how much computational effort the AI dedicates to each query for deep research models. Only applicable for sonar-deep-research.
Optional
returnWhether to return images
Optional
returnDetermines whether or not a request to an online model should return related questions.
Optional
searchFilters search results to only include content published after this date.
Optional
searchFilters search results to only include content published before this date.
Optional
searchSearch domain filter - limit the citations used by the online model to URLs from the specified domains.
Optional
searchControls the search mode used for the request. When set to 'academic', results will prioritize scholarly sources.
Optional
searchReturns search results within the specified time interval - does not apply to images. Values include month, week, day, hour.
Optional
streamingWhether to stream the results or not
Optional
temperatureTemperature parameter between 0 and 2
Optional
timeoutTimeout for requests to Perplexity
Optional
topTop K parameter between 1 and 2048
Optional
topTop P parameter between 0 and 1
Optional
webConfiguration for using web search in model responses.
Optional
runManager: anyGet the parameters used to invoke the model
Optional
options: unknownOptional
config: anyOptional
config: anyStatic
lc_
Wrapper around Perplexity large language models that use the Chat endpoint.