Skip to main content
POST
/
agent
Start an agent task for agentic data extraction
curl --request POST \
  --url https://api.firecrawl.dev/v2/agent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "urls": [
    "<string>"
  ],
  "schema": {},
  "maxCredits": 123,
  "strictConstrainToURLs": true
}
'
{
  "success": true,
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
prompt
string
required

The prompt describing what data to extract

Maximum string length: 10000
​
urls
string<uri>[]

Optional list of URLs to constrain the agent to

​
schema
object

Optional JSON schema to structure the extracted data

​
maxCredits
number

Maximum credits to spend on this agent task

​
strictConstrainToURLs
boolean

If true, agent will only visit URLs provided in the urls array

Response

Agent task started successfully

​
success
boolean
​
id
string<uuid>