🚀 AI Prompts Collection API

Welcome to the AI Prompts Collection API! Access our database of 127,966+ curated AI prompts programmatically. Perfect for developers, AI researchers, and systems integration.

Base URL
https://aiprompts.run/api
Rate Limit
60 req/min
Format
JSON
GET

/api/answers

Get machine-readable answers about AI prompts for LLM integration.

curl https://aiprompts.run/api/answers
GET

/api/answers/{slug}

Get specific answer by identifier.

curl https://aiprompts.run/api/answers/what-is-aiprompts
GET

/api/dataset.json

Download complete dataset metadata and access information.

curl https://aiprompts.run/api/dataset.json
GET

/api/openapi.json

OpenAPI 3.0 schema for GPT Actions and API integration.

curl https://aiprompts.run/api/openapi.json
GET

Search API

Search through 127,966 AI prompts with real-time results.

curl "https://aqkcomcsny5nw37je3mrvkmi3q0kiyzt.lambda-url.eu-central-1.on.aws/?q=marketing&limit=5"
GET

/api/bot-health

Monitor AI bot crawling activity and site health metrics.

curl https://aiprompts.run/api/bot-health

🔧 Integration Examples

JavaScript Integration

// Fetch AI prompts
async function getAIPrompts(query) {
  const response = await fetch(
    `https://aiprompts.run/api/answers/what-is-aiprompts`
  );
  const data = await response.json();
  return data;
}

// Search prompts
async function searchPrompts(query) {
  const response = await fetch(
    `https://aqkcomcsny5nw37je3mrvkmi3q0kiyzt.lambda-url.eu-central-1.on.aws/?q=${encodeURIComponent(query)}&limit=10`
  );
  const prompts = await response.json();
  return prompts;
}

Python Integration

import requests

# Get API information
def get_ai_prompts_info():
    response = requests.get(
        "https://aiprompts.run/api/answers/what-is-aiprompts"
    )
    return response.json()

# Search prompts
def search_prompts(query, limit=10):
    url = "https://aqkcomcsny5nw37je3mrvkmi3q0kiyzt.lambda-url.eu-central-1.on.aws/"
    params = {"q": query, "limit": limit}
    response = requests.get(url, params=params)
    return response.json()

📊 Rate Limits & Usage

Rate Limits

  • 60 requests per minute
  • 1,000 requests per hour
  • 10 burst requests
  • • No authentication required
  • • CORS enabled for web apps

Response Format

  • Content-Type: application/json
  • Encoding: UTF-8
  • Cache: 1 hour (3600s)
  • CORS: * (all origins)
  • License: CC BY 4.0

⚠️ Error Handling

Common HTTP Status Codes

200 OK
Request successful
404 Not Found
Resource not found
429 Too Many Requests
Rate limit exceeded
500 Server Error
Internal server error