POST
/
llmstxt
curl --request POST \
  --url https://api.firecrawl.dev/v1/llmstxt \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "<string>",
  "maxUrls": 2,
  "showFullText": false
}'
{
  "success": true,
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

The LLMs.txt generation endpoint creates LLMs.txt and LLMs-full.txt files for any website. These files provide a structured, LLM-friendly format of the website’s content, making it easier for language models to understand and process the information.

Looking for the status endpoint? Check out the LLMs.txt Status endpoint.

Response Structure

The response includes:

  • success: Boolean indicating if the request was successful
  • id: Unique identifier for the generation job

Output Format

  1. LLMs.txt

    • Concise, structured summary of the website

    • Contains key links and descriptions

    • Formatted in markdown for easy parsing

    • Example:

      # http://example.com llms.txt
      
      - [Page Title](https://example.com/page): Brief description
      - [Another Page](https://example.com/another): Another description
      
  2. LLMs-full.txt (when showFullText is true)

    • Contains full content of processed pages

    • Maintains hierarchical structure

    • Includes more detailed information

    • Example:

      # http://example.com llms-full.txt
      
      ## Page Title
      
      Full content of the page...
      
      ## Another Page
      
      More detailed content...
      

Billing

Billing is based on API calls and URLs processed:

  • Base cost: 1 credit per API call
  • Additional: 1 credit per URL processed
  • Control URL costs 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

Response

200
application/json
LLMs.txt generation job started successfully

The response is of type object.