API Documentation

Integrate comprehensive AI model data into your applications with our powerful RESTful API.

Comprehensive Data

Access detailed information on 300+ AI models including performance metrics, pricing, and specifications.

Real-time Updates

Get the latest model data with automatic updates as new models are released and benchmarked.

Secure & Reliable

Enterprise-grade security with 99.9% uptime SLA and comprehensive rate limiting.

Global CDN

Fast response times worldwide with our distributed content delivery network.

Quick Start

1. Get Your API Key

curl -X POST https://api.cognion.io/auth/register \\
  -H "Content-Type: application/json" \\
  -d '{"email": "[email protected]"}'

2. Make Your First Request

curl -H "Authorization: Bearer YOUR_KEY" \\
  https://api.cognion.io/api/models

API Configuration

Base URL (Development)

http://localhost:5000

Authentication

🚀 Development Mode: No authentication required! The API is currently running in development mode for easy testing and integration.

API Endpoints

GET/api/models

Get all AI models with their specifications

Parameters

Name	Type	Required	Description
type	string	Optional	Filter by model type (LLM, Text-to-Image, Image Editing)
creator	string	Optional	Filter by model creator
limit	number	Optional	Limit number of results (default: 100)
offset	number	Optional	Offset for pagination (default: 0)

Example Request

curl -X GET "http://localhost:5000/api/models?type=LLM&limit=10" \
  -H "Content-Type: application/json"

GET/api/models/{id}

Get detailed information about a specific model

Parameters

Name	Type	Required	Description
id	string	Required	Model ID

Example Request

curl -X GET "http://localhost:5000/api/models/gpt-4o" \
  -H "Content-Type: application/json"

GET/api/leaderboard

Get ranked models by specific metrics

Parameters

Name	Type	Required	Description
metric	string	Required	Ranking metric (intelligence, speed, price)
type	string	Optional	Model type filter
limit	number	Optional	Number of top models (default: 10)

Example Request

curl -X GET "http://localhost:5000/api/leaderboard?metric=intelligenceIndex&limit=5" \
  -H "Content-Type: application/json"

GET/api/trends

Get historical trend data for AI model metrics

Parameters

Name	Type	Required	Description
metric	string	Required	Trend metric (intelligence, speed, price)
period	string	Optional	Time period (6m, 1y, 2y)

Example Request

curl -X GET "http://localhost:5000/api/trends?period=30d&type=LLM" \
  -H "Content-Type: application/json"

Third-party Integrations

Connect with popular AI platforms and services to enhance your workflow

OpenAI

Direct integration with OpenAI's API for real-time model comparisons and benchmarking.

• GPT-4o, GPT-4, GPT-3.5 models

• Real-time pricing updates

• Performance benchmarking

Anthropic

Connect with Claude models for comprehensive AI assistant comparisons.

• Claude 3.5 Sonnet, Claude 3 Opus

• Safety and alignment metrics

• Constitutional AI insights

Google AI

Integration with Google's Gemini and PaLM models for comprehensive analysis.

• Gemini Pro, Gemini Ultra

• Multimodal capabilities

• Google Cloud AI services

Hugging Face

Access to the largest collection of open-source models and datasets.

• 500,000+ models

• Model cards and documentation

• Community metrics

GitHub

Track model repositories, releases, and community contributions.

• Repository monitoring

• Release notifications

• Code quality metrics

Social Sharing

Share benchmarks and comparisons across social media platforms.

• Twitter/X integration

• LinkedIn sharing

• Custom embed codes

Quick Setup Guide

1. API Keys

Configure your API keys in the dashboard settings for seamless integration.

POST /api/integrations/configure

2. Webhooks

Set up webhooks to receive real-time updates when new models are added.

POST /api/webhooks/subscribe

API Pricing

Free

1,000/month

• Basic model data
• Standard support
• Rate limit: 10/min

Pro

$29

50,000/month

• Full model data
• Priority support
• Rate limit: 100/min
• Historical trends

Enterprise

Custom

Unlimited

• Custom endpoints
• 24/7 support
• No rate limits
• SLA guarantee

Best Practices

Rate Limits

• Free tier: 10 requests per minute
• Pro tier: 100 requests per minute
• Enterprise: No limits
• Use exponential backoff for retries

Optimization Tips

• Cache responses when possible
• Use pagination for large datasets
• Filter results to reduce payload size
• Monitor your usage in the dashboard

🤓 Geek Note: Our API is built on a modern microservices architecture with Redis caching and PostgreSQL storage. We use GraphQL internally but expose REST endpoints for maximum compatibility. All responses include ETag headers for efficient caching.

AI Benchmark API for Enterprise Integration and Research

Our REST API gives enterprise development teams, data science platforms, and academic researchers programmatic access to AI model benchmarks, leaderboard rankings, pricing data, and historical performance trends. Use it to build internal model selection dashboards, feed evaluation data into MLOps pipelines, or power analyst reports with up-to-date benchmark scores from evaluations like MMLU-Pro, GPQA Diamond, LiveCodeBench, SWE-bench, and MATH-500.

Endpoints cover intelligence rankings, coding benchmarks, math evaluations, performance metrics, pricing comparisons, and multimodal model data for image generation, speech synthesis, and video generation. For questions about rate limits, authentication, or enterprise plans, see our FAQ or contact us.