Skip to main content

​
Welcome to LLMLayer API

LLMLayer adds web search capabilities to multiple LLMs. Our API lets you search the web using your preferred model - OpenAI models or LLMLayer’s own optimized models - without vendor lock-in.

​
Key Features

Any Model

Use multiple models from top providers. Switch with one parameter.

90% Cost Savings

Pay $ 0.004 per search

Real-time Search

Get current web data with citations and sources.

Streaming Support

Stream responses for better user experience.

​
API Endpoints

LLMLayer provides the following endpoints:

Answer API

/api/v2/answer - AI-powered answers with web search

Answer Stream

/api/v2/answer_stream - Stream answers in real-time

Web Search

/api/v2/web_search - Raw search results

Scraper

/api/v2/scrape - Extract page content

Map

/api/v2/map - Discover website URLs

Crawl

/api/v2/crawl_stream - Multi-page crawling

YouTube Transcript

/api/v2/youtube_transcript - Extract video transcripts

PDF Content

/api/v2/get_pdf_content - Extract PDF text

​
Authentication

Authenticate using a Bearer token in your request headers: 
{
  "headers": {
    "Authorization": "Bearer llm_xxxxxxxxxxxxx"
  }
}
Get your API key at llmlayer.ai. Start with $2 - no subscription required.

​
Getting Started

  1. Get your API key from llmlayer.ai
  2. Install the SDK: pip install llmlayer
  3. Make your first search:
from llmlayer import LLMLayerClient

client = LLMLayerClient(
    api_key="llm_xxxxxxxxxxxxx",
)

response = client.search(
    query="What happened today?",
    model="llmlayer-web",  # Recommended
    search_type="news",
    max_tokens=1000,
    temperature=0.5,
    citations=True,
    location='us'
)
See our Answer API Guide for full examples and language support.