Cookie Consent by Free Privacy Policy Generator LLM & AI Bot IP Range Checker API | LLM Tools | CL SEO

LLM & AI Bot IP Range Checker

Free tool and API to identify AI crawler traffic from ChatGPT, Claude, Perplexity, Gemini, and Mistral.

Your current IP: 216.73.216.118
Check if a User-Agent matches known LLM bot patterns
Enter up to 50 IPs for fair usage. Use our API for larger volumes.
Browse our database of 237 known LLM IP addresses

ChatGPT-User Citations 168 IPs

Used when ChatGPT needs to browse the web for real-time information

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/bot

View IP addresses
GPTBot Training 21 IPs

OpenAI's web crawler for training future GPT models - respects robots.txt

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.1; +https://openai.com/gptbot

View IP addresses
OAI-SearchBot Ingestion 34 IPs

OpenAI's search product crawler for real-time information retrieval

User-Agent:
OAI-SearchBot/1.0; +https://openai.com/searchbot

View IP addresses

ClaudeBot Training 1 IPs

Anthropic's web crawler for training Claude models

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; [email protected])

View IP addresses

PerplexityBot Training 8 IPs

Perplexity's crawler for training their AI models

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)

View IP addresses
Perplexity-User Citations 2 IPs

Used when Perplexity searches the web for real-time answers

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Perplexity-User/1.0; +https://perplexity.ai/perplexity-user)

View IP addresses

Gemini-Deep-Research Citations 1 IPs

Google Gemini's deep research crawler for comprehensive web analysis

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Gemini-Deep-Research; +https://gemini.google/overview/deep-research/) Chrome/135.0.0.0 Safari/537.36

View IP addresses

MistralAI-User Citations 2 IPs

Mistral AI's web crawler for real-time information retrieval

User-Agent:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)

View IP addresses

API Documentation

5

LLM Providers

8

Bot Types

237

Known IPs

4/3

Citation/Training

API Endpoint Available

GET https://chrisleverseo.com/tools/llm-ip-verification-tool/?api=1&ip=YOUR_IP

10 req/sec

Rate Limit

Free

No API Key Required

JSON

Response Format
Note: Unlike Googlebot, LLM bots don't support reverse DNS verification. IP matching is the primary verification method.

Quick Start

Example Request:
curl "https://chrisleverseo.com/tools/llm-ip-verification-tool/?api=1&ip=13.65.138.112"
Example Response:
{
    "ip": "13.65.138.112",
    "timestamp": "2024-11-21T10:30:00Z",
    "is_llm_ip": true,
    "provider": "OpenAI",
    "bot_type": "Citations",
    "bot_name": "ChatGPT-User",
    "user_agent_pattern": "Mozilla/5.0...ChatGPT-User/1.0...",
    "description": "Used when ChatGPT needs to browse...",
    "rate_limit": {
        "requests_used": 1,
        "requests_remaining": 9
    }
}

Rate Limiting & Fair Usage

  • 10 requests/second per IP address
  • Free to use - No API key required
  • 3 violations trigger 72-hour block
  • Headers included:
    • X-RateLimit-Limit: 10
    • X-RateLimit-Remaining: 9
    • X-RateLimit-Used: 1
    • Retry-After: 1 (on 429 errors)
Abuse Prevention: IPs exceeding rate limits repeatedly will be blocked for 72 hours. Please implement proper rate limiting in your applications.

Response Codes

Code Meaning Description
200 Success IP checked successfully (may or may not be an LLM IP)
400 Bad Request Missing or invalid IP parameter
429 Too Many Requests Rate limit exceeded or IP blocked

Understanding LLM Bot Traffic

Training Bots

These bots crawl your content to train AI models:

  • GPTBot: Training future GPT models
  • ClaudeBot: Training Claude AI
  • PerplexityBot: Building Perplexity's knowledge base

Consider blocking if: You don't want your content used for AI training

Citation/Search Bots

These bots access content for real-time AI responses:

  • ChatGPT-User: Web browsing for ChatGPT
  • Perplexity-User: Real-time search results
  • Gemini Deep Research: Google's AI search
  • MistralAI-User: Mistral's web access

Consider allowing if: You want visibility in AI-powered search

How to Block LLM Bots

Add these rules to your robots.txt file:

# Block all AI training bots
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

# Allow citation bots (for visibility in AI search)
User-agent: ChatGPT-User
Allow: /

User-agent: Perplexity-User
Allow: /

API Usage Examples

Python Example
import requests
import time

def check_ip(ip):
    url = "https://chrisleverseo.com/tools/llm-ip-verification-tool/"
    params = {"api": "1", "ip": ip}
    
    response = requests.get(url, params=params)
    
    if response.status_code == 200:
        data = response.json()
        if data["is_llm_ip"]:
            print(f"{ip} is {data['provider']} {data['bot_name']}")
        else:
            print(f"{ip} is not an LLM bot")
    elif response.status_code == 429:
        print("Rate limit exceeded, waiting...")
        time.sleep(1)
    
    return response.json()

# Example usage
check_ip("13.65.138.112")
JavaScript Example
async function checkIP(ip) {
    const url = 'https://chrisleverseo.com/tools/llm-ip-verification-tool/';
    const params = new URLSearchParams({
        api: '1',
        ip: ip
    });
    
    try {
        const response = await fetch(`${url}?${params}`);
        const data = await response.json();
        
        if (data.is_llm_ip) {
            console.log(`${ip} is ${data.provider} ${data.bot_name}`);
        } else {
            console.log(`${ip} is not an LLM bot`);
        }
        
        return data;
    } catch (error) {
        console.error('Error:', error);
    }
}

// Example usage
checkIP('13.65.138.112');