POST
/
crawl
/
params-preview
Preview crawl parameters generated from natural language prompt
curl --request POST \
  --url https://api.firecrawl.dev/v2/crawl/params-preview \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "<string>",
  "prompt": "<string>"
}'
{
  "success": true,
  "data": {
    "url": "<string>",
    "includePaths": [
      "<string>"
    ],
    "excludePaths": [
      "<string>"
    ],
    "maxDepth": 123,
    "maxDiscoveryDepth": 123,
    "crawlEntireDomain": true,
    "allowExternalLinks": true,
    "allowSubdomains": true,
    "sitemap": "skip",
    "ignoreQueryParameters": true,
    "deduplicateSimilarURLs": true,
    "delay": 123,
    "limit": 123
  }
}

​
What’s New in v2

​
Crawl Params Preview

{
  "url": "https://example.com",
  "prompt": "Crawl the entire website but exclude /admin and /api"
}

​
Response

{
  "url": "https://example.com",
  "prompt": "Crawl the entire website",
  "crawlEntireDomain": true,
  "excludePaths": ["/admin/.*", "/api/.*"],
  "sitemap": "include"
}

Authorizations

​
Authorization
string
header
required

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

Body

application/json
​
url
string<uri>
required

The URL to crawl

​
prompt
string
required

Natural language prompt describing what you want to crawl

Maximum length: 10000

Response

Successful response with generated crawl parameters

​
success
boolean
Example:

true

​
data
object