Skip to main content

​
What it does

  • Extracts all text from PDF documents
  • Returns page count and document metadata
  • Works with any public PDF URL

​
Pricing

**0.002perrequest∗∗(0.002 per request** (2 per 1,000 requests)

​
Authentication

Include your API key in the Authorization header: 
Authorization: Bearer YOUR_LLMLAYER_API_KEY

​
Endpoint

POST /api/v2/get_pdf_content

​
SDK Usage

from llmlayer import LLMLayerClient

client = LLMLayerClient(api_key="your-api-key")

response = client.get_pdf_content(
url="https://example.com/document.pdf"
)

print(response.text)  # Extracted text
print(response.pages)  # Number of pages

​
Request

​
url
string
required
The URL of the PDF document. Must be a direct link to a PDF file.Example: "https://example.com/document.pdf"

​
Response

​
text
string
The extracted text content from the PDF
​
pages
integer
Total number of pages in the PDF document
​
url
string
The PDF URL (same as input)
​
statusCode
integer
HTTP status code (200 for success)
​
cost
number
Cost in USD for this request (0.002)

​
Limitations

  • PDF must be publicly accessible (no authentication)
  • 15-second timeout for extraction
  • Direct PDF URLs only (must end in .pdf or be a direct PDF link)

​
Error Codes

Invalid or missing API key
PDF took too long to process (15-second limit)
Failed to extract PDF content
Need Help? Join our Discord or email support@llmlayer.ai