How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Exa Agent API

The Agent API from Exa — 4 operation(s) for agent.

Exa Agent API is one of 19 APIs that Exa publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 2 JSON Schema definitions.

Tagged areas include Agents. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, a JSON-LD context, and 2 JSON Schemas.

This API exposes 6 operations across 4 paths, and defines 19 schemas. It is described by OpenAPI 3.2.0, at version 2.0.0.

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

6 operations 4 paths 19 schemas 1 DELETE3 GET2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
2.0.0
Base URL
https://api.exa.ai
Authentication
API Key, HTTP Bearer
Resource Areas
1

Authentication & Security 2

Exa Agent API declares 2 security schemes for authenticating requests. An API key is passed in the header as x-api-key (apiKey). It accepts HTTP bearer tokens (bearer). By default, every request must be authenticated.

  • apiKey — Pass your Exa API key in the x-api-key header. You can also authenticate with Authorization: Bearer .
  • bearer — Pass your Exa API key in the x-api-key header. You can also authenticate with Authorization: Bearer .

Paths & Operations 6

Across 4 paths, the API surfaces 6 operations — 1 DELETE, 3 GET, 2 POST. Each is listed below with its method, path, parameters, and response codes.

Agent 6
POST
/agent/runs
Create a run
createAgentRun 2 params body → 200400401429500
GET
/agent/runs
List runs
listAgentRuns 3 params → 200400401500
GET
/agent/runs/{id}
Get a run
getAgentRun 2 params → 200400401404429500
DELETE
/agent/runs/{id}
Delete a run
deleteAgentRun 2 params → 200400401404429500
POST
/agent/runs/{id}/cancel
Cancel a run
cancelAgentRun 2 params → 200400401404429500
GET
/agent/runs/{id}/events
List run events
listAgentRunEvents 6 params → 200400401404429500

Schemas 19

The contract defines 19 schemas that model the data the API accepts and returns. The most detailed are AgentRun (10 properties), CreateAgentRunRequest (8 properties), AgentRunRequest (7 properties), AgentCostDollars (5 properties). Each schema is shown below with its type and property counts.

AgentRunList
object
4 properties 4 required
AgentRunId
string
Agent run ID. New run IDs are returned with the agentrun prefix.
JsonValue
Any JSON value.
AgentRun
object
10 properties 10 required
AgentRunEvent
object
4 properties 4 required
AgentCitation
object
2 properties 1 required
AgentStopReason
string
AgentUsage
object
4 properties 4 required
CreateAgentRunRequest
object
8 properties 1 required
AgentGrounding
object
4 properties 2 required
DeleteAgentRunResponse
object
3 properties 3 required
AgentRunRequest
object
Canonicalized request fields stored with the run.
7 properties
AgentRunStatus
string
AgentRunEventList
object
4 properties 4 required
AgentRunOutput
object
3 properties 3 required
AgentErrorResponse
object
1 property 1 required
AgentEffort
string
Cost and reasoning effort preference for the run. auto lets Exa choose the appropriate effort.
AgentError
object
3 properties 3 required
AgentCostDollars
object
5 properties 5 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

exa-ai-agent-api-openapi.yml Raw ↑

Other APIs Exa publishes across the network.

Exa Answer API
Exa Contents API
Exa Enrichments API
Exa Events API
Exa Imports API
Exa Items API
Exa Monitors API
Exa Monitors Runs API
Exa Research API
Exa Runs API
Exa Search API
Exa Searches API
Where this information came from

This is an independent, third-party profile of Exa Agent API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.