Aerys AI API

Build powerful AI applications with our unified API. Access GPT, DeepSeek, Gemini, Mistral, and NVIDIA models through a single OpenAI-compatible interface.

Want an API Key?
Login or create an account to get your free API key with 100 requests.

Authentication

All API requests require authentication via Bearer token in the Authorization header.

Authorization: Bearer sk-aerys-your-api-key-here

Never expose your API key in frontend code or public repositories.

Quickstart

Make your first API request in seconds. Our API is fully compatible with OpenAI SDK.

OpenAI SDK Compatible!
Use the official OpenAI Python/Node.js SDK with our API. Just change the base_url.

Python (OpenAI SDK) ⭐ Recommended

from openai import OpenAI

                    client = OpenAI(
                    base_url="https://aerys.site/api/v1",
                    api_key="sk-aerys-your-key"
                    )

                    response = client.chat.completions.create(
                    model="gpt-4o-mini",
                    messages=[
                    {"role": "system", "content": "You are a helpful assistant."},
                    {"role": "user", "content": "Hello!"}
                    ]
                    )

                    print(response.choices[0].message.content)

cURL

curl https://aerys.site/api/v1/chat/completions \
                    -H "Content-Type: application/json" \
                    -H "Authorization: Bearer sk-aerys-your-key" \
                    -d '{
                    "model": "gpt-4o-mini",
                    "messages": [
                    {"role": "user", "content": "Hello!"}
                    ]
                    }'

JavaScript (Fetch)

const response = await
                    fetch('https://aerys.site/api/v1/chat/completions', {
                    method: 'POST',
                    headers: {
                    'Content-Type': 'application/json',
                    'Authorization': 'Bearer sk-aerys-your-key'
                    },
                    body: JSON.stringify({
                    model: 'gpt-4o-mini',
                    messages: [{ role: 'user', content: 'Hello!' }]
                    })
                    });

                    const data = await response.json();
                    console.log(data.choices[0].message.content);

Python (Requests)

import requests

                    response = requests.post(
                    'https://aerys.site/api/v1/chat/completions',
                    headers={'Authorization': 'Bearer sk-aerys-your-key'},
                    json={
                    'model': 'gpt-4o-mini',
                    'messages': [{'role': 'user', 'content': 'Hello!'}]
                    }
                    )

                    print(response.json()['choices'][0]['message']['content'])

Chat Completions

Create a model response for the given chat conversation.

POST https://aerys.site/api/v1/chat/completions

Request Body

{
                    "model": "openai",
                    "messages": [
                    {"role": "system", "content": "You are a helpful assistant."},
                    {"role": "user", "content": "Write a haiku about coding."}
                    ]
                    }

Response

{
                    "id": "chatcmpl-abc123",
                    "object": "chat.completion",
                    "created": 1699000000,
                    "model": "openai",
                    "choices": [{
                    "index": 0,
                    "message": {
                    "role": "assistant",
                    "content": "Logic flows like stream,\nPixels dance on glowing screen,\nBugs hide in the code."
                    },
                    "finish_reason": "stop"
                    }],
                    "usage": {
                    "requests_remaining": 99
                    }
                    }

Supported Models

Use any of these models by specifying the model parameter in your request.

Loading models...

Rate Limits

To ensure fair usage and API stability, the following limits apply:

Multi-Provider Failover
Our API automatically switches between providers if one becomes unavailable, ensuring high uptime.

Tier	Requests/Month	Rate Limit
Free	100	60 req/min
Pro (Coming Soon)	Unlimited	120 req/min

Error Codes

Code	Description
`401`	Invalid or missing API key
`429`	Rate limit or quota exceeded
`500`	Server error
`502`	Upstream AI provider error