AI API

My API Keys

Recent Requests

AI API - Documentation

Complete documentation for using GreatHost's Artificial Intelligence API.

Table of Contents

Introduction

GreatHost's AI API allows you to integrate powerful artificial intelligence models into your applications. Our API is compatible with the OpenAI format and supports multiple advanced models.

Base URL

https://greathost.es/api/ai-api

Authentication

All API requests require a valid API Key. You can create and manage your API Keys from the control panel.

Authorization Header

Authorization: Bearer gha_your_api_key_here

Available Models

We currently offer the following models:

Qwen 32B (Default)
ID: qwen-32b-default

Advanced model with default reasoning. Ideal for complex tasks.

Cost: 0.50 credits per request

Qwen 32B (None)
ID: qwen-32b-none

Fast model without additional reasoning. Perfect for direct responses.

Cost: 0.50 credits per request

GPT OSS 20B (Low)
ID: gpt-oss-20b-low

Balanced model with low reasoning. Good quality-price ratio.

Cost: 0.50 credits per request

GPT OSS 20B (Tools)
ID: gpt-oss-20b-tools

Model with integrated tools (web search and code interpreter).

Cost: 0.50 credits per request

Moonshot AI Kimi K2 Instruct
ID: kimi-k2-instruct

Advanced conversational AI model with high-quality instruction following.

Cost: 0.50 credits per request

GPT OSS 120B (Low)
ID: gpt-oss-120b-low

Large-scale model with low reasoning effort for efficient processing.

Cost: 0.50 credits per request

GPT OSS 120B (Medium)
ID: gpt-oss-120b-medium

Large-scale model with medium reasoning effort for balanced performance.

Cost: 0.50 credits per request

GPT OSS 120B (High)
ID: gpt-oss-120b-high

Large-scale model with high reasoning effort for complex tasks.

Cost: 0.50 credits per request

Meta Llama 4 Scout 17B Instruct
ID: llama-4-scout-17b

Meta's latest Llama model optimized for instruction following and reasoning.

Cost: 0.50 credits per request

Endpoints

POST /chat/completions

Makes a chat completion request to an AI model.

Body Parameters

messages array (required)

Array of messages in OpenAI format.

Request Example

{
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ]
}

Response

{
  "response": "Hello! I'm doing great, thanks for asking. How can I help you today?"
}

GET /models

Gets the list of available models.

Response

[
  {
    "id": "qwen-32b-default",
    "name": "Qwen 32B (Default)",
    "cost_per_request": 0.50
  },
  {
    "id": "qwen-32b-none",
    "name": "Qwen 32B (None)",
    "cost_per_request": 0.50
  },
  {
    "id": "gpt-oss-20b-low",
    "name": "GPT OSS 20B (Low)",
    "cost_per_request": 0.50
  },
  {
    "id": "gpt-oss-20b-tools",
    "name": "GPT OSS 20B (Tools)",
    "cost_per_request": 0.50
  },
  {
    "id": "kimi-k2-instruct",
    "name": "Moonshot AI Kimi K2 Instruct",
    "cost_per_request": 0.50
  },
  {
    "id": "gpt-oss-120b-low",
    "name": "GPT OSS 120B (Low)",
    "cost_per_request": 0.50
  },
  {
    "id": "gpt-oss-120b-medium",
    "name": "GPT OSS 120B (Medium)",
    "cost_per_request": 0.50
  },
  {
    "id": "gpt-oss-120b-high",
    "name": "GPT OSS 120B (High)",
    "cost_per_request": 0.50
  },
  {
    "id": "llama-4-scout-17b",
    "name": "Meta Llama 4 Scout 17B Instruct",
    "cost_per_request": 0.50
  }
]

Usage Examples

JavaScript/Node.js

const response = await fetch('https://greathost.es/api/ai-api/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer gha_your_api_key_here'
  },
  body: JSON.stringify({
    messages: [
      {
        role: 'user',
        content: 'What is the capital of Spain?'
      }
    ]
  })
});

const data = await response.json();
console.log(data.response);

Python

import requests

url = "https://greathost.es/api/ai-api/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer gha_your_api_key_here"
}
data = {
    "messages": [
        {
            "role": "user",
            "content": "What is the capital of Spain?"
        }
    ]
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(result["response"])

cURL

curl -X POST https://greathost.es/api/ai-api/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer gha_your_api_key_here" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "What is the capital of Spain?"
      }
    ]
  }'

PHP

<?php
$url = "https://greathost.es/api/ai-api/chat/completions";
$headers = [
    "Content-Type: application/json",
    "Authorization: Bearer gha_your_api_key_here"
];
$data = [
    "messages" => [
        [
            "role" => "user",
            "content" => "What is the capital of Spain?"
        ]
    ]
];

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

$response = curl_exec($ch);
curl_close($ch);

$result = json_decode($response, true);
echo $result["response"];
?>

Error Codes

401 Unauthorized

Missing or invalid API key.

402 Payment Required

Insufficient balance to make the request.

429 Too Many Requests

Request limit reached.

400 Bad Request

Invalid request parameters.

500 Internal Server Error

Internal server error.

Limits and Costs

Costs

All models currently cost 0.005 credits per request.

Limits

  • You can set custom limits per API Key
  • Requests are processed in real time
  • Streaming is enabled by default
  • Maximum tokens per request: varies by model

API Key Management

From your control panel you can:

  • Create multiple API Keys
  • Set usage limits
  • Monitor usage in real time
  • View request history
  • Activate/deactivate API Keys

Need help?

If you have questions or need technical support, don't hesitate to contact us:

×

Create New API