search

Create search

Execute web search queries using specified search engine. Supports three search engines:Exa (AI-native search, default), Tavily (with AI summary), Google (custom search)

Request

POST /search

Request Body

Field	Type	Required	Description
engine	string (exa, tavily, google)	No	Search engine name (optional, defaults to exa) - exa: AI-native search engine, suitable for semantic search - tavily: AI search API, supports deep search and summary answers - google: Google custom search, most comprehensive index
extra	object	Yes	Engine-specific parameters. Different engines support different parameters: Exa engine parameters: - query (string, required): Search query - num (integer): Number of results to return, default 10 - contents.text (boolean): Whether to return full text content Tavily engine parameters: - query (string, required): Search query - max_results (integer): Maximum number of results, default 10 - search_depth (string): Search depth, “basic” or “advanced”, default “basic” - include_answer (boolean): Whether to include AI-generated summary answer, default true Google engine parameters: - query (string, required): Search query - num (integer): Number of results (1-10), default 10 - start (integer): Starting position (pagination), default 1 - safe (string): Safe search, “active” or “off”, default “active”

Request Examples

Exa simple search

{
  "engine": "exa",
  "extra": {
    "query": "What is artificial intelligence?",
    "num": 5,
    "contents": {
      "text": true
    }
  }
}

Tavily advanced search (recommended for AI)

{
  "engine": "tavily",
  "extra": {
    "query": "Latest developments in quantum computing",
    "max_results": 10,
    "search_depth": "advanced",
    "include_answer": true
  }
}

Google custom search

{
  "engine": "google",
  "extra": {
    "query": "Python best practices 2024",
    "num": 10,
    "safe": "active"
  }
}

Use default engine (omit engine field)

{
  "extra": {
    "query": "machine learning tutorials",
    "num": 3
  }
}

Exa with full text snippets

{
  "engine": "exa",
  "extra": {
    "query": "LLM routing architectures",
    "num": 3,
    "contents": {
      "text": true,
      "highlights": true
    }
  }
}

Successful response

Response Schema

Field	Type	Required	Description
engine	string (exa, tavily, google)	Yes	Search engine used
result	object	Yes	Search results, format depends on the engine used. Exa response format: - requestId: Request ID - results: Results array (includes id, title, url, text, publishedDate, author, etc.) - searchTime: Search duration Tavily response format: - query: Original query - answer: AI-generated summary answer (if enabled) - results: Results array (includes title, url, content, score, etc.) - response_time: Response time - request_id: Request ID Google response format: - items: Results array (includes title, link, snippet, etc.) - searchInformation: Search metadata (totalResults, searchTime)

Response Examples

Exa search response

{
  "engine": "exa",
  "result": {
    "requestId": "req_abc123",
    "autoDate": "2024-01",
    "resolvedSearchType": "neural",
    "results": [
      {
        "id": "result_1",
        "title": "Artificial Intelligence - Wikipedia",
        "url": "https://en.wikipedia.org/wiki/Artificial_intelligence",
        "text": "Artificial intelligence (AI) is intelligence demonstrated by machines...",
        "publishedDate": "2024-01-15",
        "author": "Wikipedia Contributors"
      }
    ],
    "searchTime": 0.234
  }
}

Tavily search response (with AI summary)

{
  "engine": "tavily",
  "result": {
    "query": "Latest developments in quantum computing",
    "answer": "Recent advances in quantum computing include breakthrough achievements in error correction and qubit stability...",
    "results": [
      {
        "title": "Quantum Computing Breakthrough 2024",
        "url": "https://example.com/quantum-news",
        "content": "Scientists have achieved a major breakthrough in quantum error correction...",
        "score": 0.92
      },
      {
        "title": "IBM Quantum Roadmap Update",
        "url": "https://example.com/ibm-quantum",
        "content": "IBM has announced significant progress in their quantum computing roadmap...",
        "score": 0.88
      }
    ],
    "response_time": 1.23,
    "request_id": "tvly_abc123"
  }
}

Google search response

{
  "engine": "google",
  "result": {
    "items": [
      {
        "title": "Python Best Practices 2024",
        "link": "https://example.com/python-practices",
        "snippet": "Learn the latest Python best practices for writing clean, maintainable code..."
      },
      {
        "title": "Modern Python Development",
        "link": "https://example.com/modern-python",
        "snippet": "A comprehensive guide to modern Python development practices..."
      }
    ],
    "searchInformation": {
      "totalResults": "1234567",
      "searchTime": 0.45
    }
  }
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.r9s.ai/v1/search', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
  "engine": "exa",
  "extra": {
    "query": "What is artificial intelligence?",
    "num": 5,
    "contents": {
      "text": true
    }
  }
})
});

const data = await response.json();
console.log(data);

Python (requests)

import requests

url = "https://api.r9s.ai/v1/search"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={
  "engine": "exa",
  "extra": {
    "query": "What is artificial intelligence?",
    "num": 5,
    "contents": {
      "text": true
    }
  }
}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.r9s.ai/v1/search" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"engine":"exa","extra":{"query":"What is artificial intelligence?","num":5,"contents":{"text":true}}}'

Schema Reference

SearchRequest

Field	Type	Required	Description
engine	string (exa, tavily, google)	No	Search engine name (optional, defaults to exa) - exa: AI-native search engine, suitable for semantic search - tavily: AI search API, supports deep search and summary answers - google: Google custom search, most comprehensive index
extra	object	Yes	Engine-specific parameters. Different engines support different parameters: Exa engine parameters: - query (string, required): Search query - num (integer): Number of results to return, default 10 - contents.text (boolean): Whether to return full text content Tavily engine parameters: - query (string, required): Search query - max_results (integer): Maximum number of results, default 10 - search_depth (string): Search depth, “basic” or “advanced”, default “basic” - include_answer (boolean): Whether to include AI-generated summary answer, default true Google engine parameters: - query (string, required): Search query - num (integer): Number of results (1-10), default 10 - start (integer): Starting position (pagination), default 1 - safe (string): Safe search, “active” or “off”, default “active”

SearchResponse

Field	Type	Required	Description
engine	string (exa, tavily, google)	Yes	Search engine used
result	object	Yes	Search results, format depends on the engine used. Exa response format: - requestId: Request ID - results: Results array (includes id, title, url, text, publishedDate, author, etc.) - searchTime: Search duration Tavily response format: - query: Original query - answer: AI-generated summary answer (if enabled) - results: Results array (includes title, url, content, score, etc.) - response_time: Response time - request_id: Request ID Google response format: - items: Results array (includes title, link, snippet, etc.) - searchInformation: Search metadata (totalResults, searchTime)

Related APIs

• API Overview - Learn about authentication and basic information
• models - View models related APIs
• chat - View chat related APIs
• responses - View responses related APIs
• messages - View messages related APIs
• completions - View completions related APIs
• edits - View edits related APIs
• images - View images related APIs
• embeddings - View embeddings related APIs
• engine-embeddings - View engine-embeddings related APIs
• moderations - View moderations related APIs
• audio - View audio related APIs
• proxy - View proxy related APIs