Need help with your APIs? I offer API discovery, governance & evangelism services. Explore services →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Perplexity Agent API

The Agent API from Perplexity — 1 operation(s) for agent.

Perplexity Agent API is one of 12 APIs that Perplexity publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

Tagged areas include Agent. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, authentication docs, pricing, and an AsyncAPI specification.

This API exposes 1 operation across 1 path, and defines 58 schemas. It is described by OpenAPI 3.1.0, at version 1.0.0.

Requests are made against a single base URL, https://api.perplexity.ai.

1 operations 1 paths 58 schemas 1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
1.0.0
Base URL
https://api.perplexity.ai
Authentication
HTTP Bearer
Resource Areas
1

Authentication & Security 1

Perplexity Agent API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (HTTPBearer).

Paths & Operations 1

Across 1 path, the API surfaces 1 operation — 1 POST. Each is listed below with its method, path, parameters, and response codes.

Agent 1
POST
/v1/agent
Create Agent Response
createAgent body → 200

Schemas 58

The contract defines 58 schemas that model the data the API accepts and returns. The most detailed are ResponsesRequest (12 properties), ResponsesResponse (8 properties), FunctionCallOutputItem (7 properties), ResponsesCost (7 properties). Each schema is shown below with its type and property counts.

FunctionCallOutputInput
object
5 properties 3 required
Input
Input content - either a string or array of input items
FinanceSearchTool
object
Finance search tool configuration for the Agent API
1 property 1 required
FetchUrlQueriesEvent
object
URL fetch queries event (type: "response.reasoning.fetchurlqueries"). Contains URLs being fetched.
4 properties 3 required
WebSearchFilters
Date
string
Input: MM/DD/YYYY, Output: YYYY-MM-DD
OutputItem
FunctionCallInput
object
5 properties 4 required
ReasoningConfig
object
1 property
SearchDomainFilter
object
1 property
SearchQueriesEvent
object
Search queries event (type: "response.reasoning.searchqueries"). Contains search queries being executed.
4 properties 3 required
ResponseCompletedEvent
object
Response event Contains the full or partial response object.
3 properties 2 required
FetchUrlResultsOutputItem
object
2 properties 2 required
OutputItemAddedEvent
object
Output item added event (type: "response.outputitem.added"). Emitted when a new output item (message or tool call) starts.
4 properties 4 required
SearchResultsEvent
object
Search results event (type: "response.reasoning.searchresults"). Contains search results returned.
5 properties 3 required
SearchResult
object
A single search result used in LLM responses
7 properties 4 required
ResponseCreatedEvent
object
Response created event (type: "response.created"). Contains the initial response object.
3 properties 2 required
ContentPartType
string
Type of a content part
SearchResultsOutputItem
object
3 properties 2 required
ToolUserLocation
object
User's geographic location for search personalization
5 properties
ResponsesRequest
object
12 properties 1 required
TextDoneEvent
object
Text done event (type: "response.outputtext.done"). Contains the final text content.
6 properties 6 required
ReasoningStoppedEvent
object
Reasoning stopped event (type: "response.reasoning.stopped"). Signals the model has finished reasoning/searching.
3 properties 2 required
FunctionCallOutputItem
object
7 properties 6 required
ResponsesResponse
object
Non-streaming response returned when stream is false
8 properties 6 required
FetchUrlResultsEvent
object
URL fetch results event (type: "response.reasoning.fetchurlresults"). Contains fetched URL contents.
4 properties 3 required
ToolCallDetails
object
Details about a tool call invocation
1 property
FetchUrlTool
object
2 properties 1 required
ResponsesObjectType
string
Object type in API responses
OutputItemDoneEvent
object
Output item done event (type: "response.outputitem.done"). Emitted when an output item (message or tool call) completes.
4 properties 4 required
ResponseInProgressEvent
object
Response in progress event (type: "response.inprogress"). Emitted when response processing has started.
3 properties 2 required
Tool
JSONSchemaFormat
object
Defines a JSON schema for structured output validation
4 properties 2 required
InputContent
Message content - either a string or array of content parts
SearchRecencyFilter
string
Time-based recency filter for search results
MessageOutputItem
object
5 properties 5 required
RoleType
string
Role in a message
Annotation
object
Text annotation (URL citation)
5 properties
ErrorInfo
object
Error information returned when a request fails
3 properties 1 required
UrlContent
object
Content fetched from a URL
3 properties 3 required
ContentPart
object
3 properties 2 required
Currency
string
Currency code for cost values
DateFilters
object
5 properties
InputMessage
object
3 properties 3 required
FunctionTool
object
5 properties 2 required
InputContentPart
object
3 properties 1 required
EventType
string
SSE event type discriminator
SearchSource
string
Source of search results
InputItem
ResponsesUsage
object
Token usage and cost information for a Responses API request
6 properties 3 required
ResponseStreamEvent
SSE stream event. Discriminate by the type field: - response.created: Initial response object - response.inprogress: Response processing started - response.com…
Status
string
Status of a response or output item
ResponseFailedEvent
object
Response failed event (type: "response.failed"). Contains error details when streaming fails.
3 properties 3 required
TextDeltaEvent
object
Text delta event (type: "response.outputtext.delta"). Contains incremental text content.
6 properties 6 required
ResponsesCost
object
Cost breakdown for a Responses API request
7 properties 4 required
ResponseFormat
object
Specifies the desired output format for the model response
2 properties 1 required
WebSearchTool
object
Web search tool configuration for the Responses API
5 properties 1 required
ReasoningStartedEvent
object
Reasoning started event (type: "response.reasoning.started"). Signals the model has started reasoning/searching.
3 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

perplexity-agent-api-openapi.yml Raw ↑

Other APIs Perplexity publishes across the network.

Perplexity
Perplexity Async Chat Completions API
Perplexity Search API
Perplexity Responses API
Perplexity Embeddings API
Perplexity Async API
Perplexity Contextualizedembeddings API
Perplexity Embeddings API
Perplexity Models API
Perplexity Search API
Perplexity Sonar API