WebSearchAPI.ai Search API Reference
Complete reference for the WebSearchAPI.ai Search endpoint with examples, parameters, and response details
WebSearchAPI.ai offers a powerful search API built on Google's search infrastructure, enhanced with AI-powered content extraction capabilities. This reference provides comprehensive details about the API endpoints, parameters, response formats, and usage examples.
Introduction
The WebSearchAPI.ai Search API allows you to:
- Execute Google-powered search queries programmatically
- Retrieve high-quality search results with relevance scoring
- Automatically extract and structure content from result pages
- Generate AI-created summaries of search results
- Customize search parameters for regional and language preferences
Endpoint Details
POST
/ai-searchBase URL: https://api.websearchapi.ai
Full Endpoint: https://api.websearchapi.ai/ai-search
Authentication
Authentication Required
All API requests require authentication using your API key in the Authorization header.
Include your API key in the Authorization
header using the Bearer token format:
Authorization: Bearer YOUR_API_KEY
You can obtain an API key by signing up for a WebSearchAPI.ai account. Each account receives 1,000 free API credits monthly.
Request Format
All requests to the Search API should be made as HTTP POST requests with a JSON body containing the search parameters.
Required Headers
Header | Value |
---|---|
Content-Type | application/json |
Authorization | Bearer YOUR_API_KEY |
Request Body
The request body should be a JSON object containing your search parameters:
{
"query": "your search query",
"maxResults": 5,
"includeContent": true,
"country": "us",
"language": "en",
"timeframe": "month",
"includeAnswer": true,
"safeSearch": true
}
Request Parameters
Example Requests
curl --request POST \
--url https://api.websearchapi.ai/ai-search \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"query": "latest advancements in AI",
"maxResults": 5,
"includeContent": true,
"contentLength": "medium",
"country": "us",
"language": "en",
"timeframe": "month",
"includeAnswer": true,
"safeSearch": true,
"includeDomains": [],
"excludeDomains": []
}'
Response Format
Success Response (200 OK)
A successful API call returns a JSON object with the following structure:
{
"searchParameters": {
"query": "latest advancements in AI",
"maxResults": 5,
"includeContent": true,
"contentLength": "medium",
"country": "us",
"language": "en",
"timeframe": "month",
"includeAnswer": true,
"safeSearch": true,
"includeDomains": [],
"excludeDomains": []
},
"answer": "Recent advancements in AI include significant improvements in large language models with systems like GPT-4 and Claude 3, breakthroughs in AI-generated content with text-to-image models like Midjourney v6 and DALL-E 3, and progress in multimodal AI systems that can process text, images, audio, and video simultaneously. These advancements are enhancing AI's capabilities across various domains, from creative content generation to scientific research and business applications.",
"organic": [
{
"title": "Breakthrough AI Research: Recent Advancements and Future Directions",
"url": "https://example.com/ai-research-advancements",
"description": "An exploration of the latest breakthroughs in artificial intelligence research, including large language models, multimodal AI, and emerging architectures...",
"content": "# Recent Advancements in AI Research\n\nThe field of artificial intelligence continues to evolve at a rapid pace, with several significant breakthroughs achieved in recent months.\n\n## Large Language Models\n\nLarge language models have seen remarkable improvements in their capabilities, with new benchmarks being set in reasoning, knowledge representation, and problem-solving abilities. Research teams have developed more efficient training methods that reduce computational requirements while maintaining or improving performance.\n\n## Multimodal AI Systems\n\nOne of the most promising directions in current AI research is the development of multimodal systems that can process and generate content across different types of media - text, images, audio, and video. These systems are showing unprecedented abilities to understand context across modalities.\n\n## Efficient AI Architectures\n\nResearchers have made significant progress in creating more efficient neural network architectures that require less computational resources while maintaining high performance. These advancements are particularly important for deploying AI systems on edge devices with limited processing capabilities.",
"position": 1,
"score": 0.94
}
],
"responseTime": 1.24
}
Response Fields
Error Responses
WebSearchAPI.ai returns standard HTTP status codes with JSON error details:
{
"error": "Bad Request",
"message": "Invalid request parameters",
"details": {
"query": "This field is required"
}
}
Returned when the request contains invalid or missing parameters.
Rate Limits and Quotas
WebSearchAPI.ai uses a credit-based system for API usage. Each account receives 1,000 free API credits monthly. Usage is calculated as follows:
Operation | Credits |
---|---|
Basic search without content | 1 credit |
Search with content extraction | 2 credits |
Search with answer generation | +1 credit |
Pro Tip: Optimize Credit Usage
Only enable includeContent
and includeAnswer
when
you need these features. For exploratory searches or when you only need URLs
and titles, keep these options disabled to conserve credits.
Advanced Features
Content Extraction
When includeContent
is set to true
, WebSearchAPI.ai not only performs a search but also:
- Retrieves each page in the search results
- Extracts the main content from the page, removing ads, navigation, footers, etc.
- Processes the content to create a clean, structured representation
- Returns the content in your preferred format (markdown, text, or HTML)
This content extraction capability eliminates the need for separate web scraping and content cleaning steps in your workflow.
How Content Extraction Works
Our advanced content extraction system:
- Uses machine learning algorithms to identify the primary content on a page
- Preserves important structural elements (headings, lists, tables, etc.)
- Removes noise like ads, popups, navigation elements, and irrelevant sidebars
- Intelligently processes images and captions when relevant to the main content
- Converts the extracted content into a clean, consistent format (default: markdown)
- Optimizes the content for consumption by AI models
This automated process ensures you receive high-quality, structured content that's immediately usable in your applications without additional cleaning or processing steps.
Content Format Options
You can specify how you want the extracted content formatted using the contentFormat
parameter:
Format | Description |
---|---|
markdown | Well-structured markdown format ideal for LLMs and text processing (default) |
text | Plain text with basic formatting preserved but all markup removed |
html | Clean HTML with essential elements preserved but extraneous tags removed |
Advanced Search Options
The Search API supports various advanced search options:
- Time-based filtering: Limit results to recent content using the
timeframe
parameter - Domain filtering: Include or exclude specific domains with
includeDomains
andexcludeDomains
- Site search: Restrict results to a specific website with
siteSearch
- Exact matching: Find pages containing exact phrases with
exactTerms
- Exclusions: Exclude pages containing specific terms with
excludeTerms
- File type filtering: Find specific document types with
fileType
These options allow you to create highly targeted searches for specific use cases.