POST
/
deep-research
curl --request POST \
  --url https://api.firecrawl.dev/v1/deep-research \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "maxDepth": 7,
  "timeLimit": 300,
  "maxUrls": 20,
  "analysisPrompt": "<string>",
  "systemPrompt": "<string>",
  "formats": [
    [
      "markdown"
    ]
  ],
  "jsonOptions": {
    "schema": {},
    "systemPrompt": "<string>",
    "prompt": "<string>"
  }
}'
{
  "success": true,
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

The Deep Research endpoint enables AI-powered deep research and analysis on any topic. Simply provide a research query, and Firecrawl will autonomously explore the web, gather relevant information, and synthesize findings into comprehensive insights.

Looking for the status endpoint? Check out the Deep Research Status endpoint.

​
Response Structure

The response includes:

  • activities: List of research activities with:

    • type: Activity type (‘search’, ‘extract’, ‘analyze’, ‘reasoning’, ‘synthesis’, ‘thought’)
    • status: Status (‘processing’, ‘complete’, ‘error’)
    • message: Description of activity/finding
    • timestamp: ISO timestamp
    • depth: Research depth level

  • sources: Referenced URLs with:

    • title: Source title
    • description: Source description
    • url: Source URL
    • icon: Source favicon

  • finalAnalysis: Comprehensive analysis (when completed)

  • status: Overall status (‘processing’, ‘completed’, ‘failed’)

  • currentDepth: Current research depth

  • maxDepth: Maximum research depth

  • totalUrls: Number of URLs analyzed

  • expiresAt: ISO timestamp when results expire

​
Limitations

  1. Best suited for topics with publicly available information
  2. Research jobs limited to 10 minutes maximum
  3. Manual verification recommended for critical information
  4. Alpha feature - methodology and output may evolve

​
Billing

Billing is based on number of URLs analyzed:

  • Each URL = 1 credit
  • Control usage with maxUrls parameter

Authorizations

​
Authorization
string
header
required

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

Body

application/json
​
query
string
required

The query to research

​
maxDepth
integer
default:7

Maximum depth of research iterations

Required range: 1 <= x <= 12
​
timeLimit
integer
default:300

Time limit in seconds

Required range: 30 <= x <= 600
​
maxUrls
integer
default:20

Maximum number of URLs to analyze

Required range: 1 <= x <= 1000
​
analysisPrompt
string

The prompt to use for the final analysis. Useful to format the final analysis markdown in a specific way.

​
systemPrompt
string

The system prompt to use for the research agent. Useful to steer the research agent to a specific direction.

​
formats
enum<string>[]
Available options:
markdown,
json
​
jsonOptions
object

Options for JSON output

Response

200
application/json
Research job started successfully
​
success
boolean
Example:

true

​
id
string

ID of the research job

Suggest editsRaise issue