Connectors

AI, LLM & Vector Stores

Perplexity

AI answer engine: search-grounded chat completions with cited sources

Perplexity API referenceAPI checked August 18, 2026

Signs in with: API token
Runs on: Cloud or On-Prem Worker
Operations: 28
Ready-made triggers: 0

Connect Perplexity

In Neblex open Connect › Connections and click New Connection.
Search for Perplexity and give the connection a clear name.
Fill in the fields. Secret values are encrypted and never shown again.
Click Test, then Create Connection.

Field	What to enter
API keyRequiredSecret	Perplexity API key; organization analytics endpoints require an organization analytics API key.

Use it in a flow

Open a flow, open the node library and search for Perplexity.
Drag it onto the canvas and choose an Operation and your connection.
Map the operation's fields from earlier steps, or click Map with Matt.
Use Test this step to see what it returns, then save.

Operations

28 operations in 3 groups. Each one is a step you can add to a flow.

Auth2

Generate Auth Token`generateAuthToken`	POST	Generates a new authentication token for API access.
Revoke Auth Token`revokeAuthToken`	POST	Revokes an existing authentication token.

Main18

Cancel Agent Response`cancelAgentResponse`	POST	Requests cancellation of response {id}.
Chat completion (single message compatibility)`chat`	POST	Generate a chat completion response for the given conversation.
Computer Usage Analytics`computerUsageAnalytics`	GET	Returns your organization's Computer usage analytics as a bucketed time series for a single dataset.
Computer Usage Analytics per Member`computerUsageAnalyticsV2`	GET	Returns your organization's Computer credit usage broken down per member, as daily buckets.
Create Agent Response`createAgentResponse`	POST	Generate a response for the provided input with optional web search and reasoning.
Create Agent Response (exact SSE bytes)`createAgentResponseStream`	POST	Generate a response for the provided input with optional web search and reasoning.
Create Async Chat Completion`createAsyncChat`	POST	Submit an asynchronous chat completion request.
Create Chat Completion`chatMessages`	POST	Generate a chat completion response for the given conversation.
Create Chat Completion (exact SSE bytes)`chatMessagesStream`	POST	Generate a chat completion response for the given conversation.
Create Contextualized Embeddings`contextualizedEmbeddings`	POST	Generate contextualized embeddings for document chunks.
Create Embeddings`embeddings`	POST	Generate embeddings for a list of texts.
Download Agent Response File`downloadAgentResponseFile`	GET	Download the raw bytes of a file the response delivered with the share file tool.
Get Async Chat Completion`getAsyncChat`	GET	Retrieve the response for a given asynchronous chat completion request.
List Agent Response Files`getAgentResponseFiles`	GET	List the files a response produced in the sandbox and delivered with the share file tool.
List Async Chat Completions`listAsyncChats`	GET	Retrieve a list of all asynchronous chat completion requests for a given user.
List Models`listModels`	GET	List the models available for the Agent API.
Retrieve Agent Response`getAgentResponse`	GET	Retrieve a response created earlier.
Search the Web`search`	POST	Search the web and retrieve relevant web page contents.

Router8

Create Chat Completion`routerChatCompletions`	POST	Send a conversation to any Router model using the OpenAI Chat Completions schema.
Create Chat Completion (exact SSE bytes)`routerChatCompletionsStream`	POST	Send a conversation to any Router model using the OpenAI Chat Completions schema.
Create Message`routerMessages`	POST	Send a conversation to any Router model using the Anthropic Messages schema.
Create Message (exact SSE bytes)`routerMessagesStream`	POST	Send a conversation to any Router model using the Anthropic Messages schema.
Create Response`routerResponses`	POST	Generate a model response using the OpenAI Responses schema.
Create Response (exact SSE bytes)`routerResponsesStream`	POST	Generate a model response using the OpenAI Responses schema.
List Models`routerListModels`	GET	List the models available through the Router, sorted by id.
Retrieve Model`routerGetModel`	GET	Retrieve one model by id, including its base token prices.