AI API Gateway

The Euron AI API Gateway provides access to 200+ AI models from major providers through a single, unified API. Use the same API format to access models from OpenAI, Anthropic, Google, Meta, Mistral, and more.

Supported Models

Provider	Models
OpenAI	GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo
Anthropic	Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
Google	Gemini 1.5 Pro, Gemini 1.5 Flash
Meta	Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B
Mistral	Mistral Large, Mistral Medium, Mixtral
And 20+ more providers	200+ models total

Getting Started

Step 1: Get Your API Key

Go to Settings → AI Tools → API Gateway.
Click Generate API Key.
Copy your API key and store it securely.

Step 2: Make Your First Request

The API follows the OpenAI-compatible chat completions format:

curl https://api.euronsystems.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Step 3: Switch Models

Change the model by simply updating the model parameter:

{
  "model": "claude-3-5-sonnet",
  "messages": [...]
}

No other code changes needed — the API format is identical across all models.

Features

Unified API — Same format for all 200+ models
Load Balancing — Automatic failover between providers
Rate Limiting — Configurable rate limits per key
Usage Tracking — Detailed logs of every API call
Cost Optimization — Route to cheaper models for simple tasks
Streaming — Real-time streaming responses supported
Function Calling — Supported on compatible models

Billing

API usage is billed per token from your AI Wallet:

Input tokens and output tokens are priced differently.
Prices vary by model (GPT-4o costs more than GPT-3.5 Turbo).
View detailed usage in Analytics → AI Usage.

AI Chat (Euri) — Student-facing AI chat
AI Wallet — Token billing
AI Usage Analytics — Monitoring usage