Documentation

APIEX.CLOUD gives you one OpenAI-compatible endpoint for dozens of AI models across every major provider. This guide covers authentication, the API reference, wallet & billing, API keys and rate limits.

Authentication

Every request must include your API key in the Authorization header, using the Bearer scheme.

Authorization: Bearer YOUR_API_KEY

Generate and manage keys from your panel: API Keys section

Quick start

Send your first request with the language of your choice. Replace YOUR_API_KEY with a key from your panel.

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

from openai import OpenAI

client = OpenAI(
    base_url="https://apiex.cloud/api/v1/",
    api_key="YOUR_API_KEY",
)

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

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

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://apiex.cloud/api/v1/",
  apiKey: "YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

$ch = curl_init( "https://apiex.cloud/api/v1/chat/completions" );

curl_setopt_array( $ch, array(
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST           => true,
    CURLOPT_HTTPHEADER     => array(
        'Authorization: Bearer YOUR_API_KEY',
        'Content-Type: application/json',
    ),
    CURLOPT_POSTFIELDS => json_encode( array(
        'model'    => 'gpt-4o-mini',
        'messages' => array(
            array( 'role' => 'user', 'content' => 'Hello!' ),
        ),
    ) ),
) );

$response = json_decode( curl_exec( $ch ), true );
echo $response['choices'][0]['message']['content'];

Errors

The API uses conventional HTTP status codes. Codes in the 2xx range indicate success; 4xx indicate a problem with the request; 5xx indicate an issue on our side.

Error responses share a consistent JSON shape:

{
  "error": {
    "type": "insufficient_balance",
    "message": "Wallet balance is too low to complete this request.",
    "code": 402
  }
}

Base URL & endpoints

All requests are made against this base URL:

https://apiex.cloud/api/v1/

Chat completions

Creates a model response for a given conversation. Request and response shapes match the OpenAI Chat Completions API.

Request parameters

Example response

{
  "id": "chatcmpl_8k2f...",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 10,
    "total_tokens": 19
  }
}

Streaming responses

Set "stream": true to receive the response incrementally as server-sent events, ideal for chat interfaces.

data: {"choices":[{"delta":{"content":"Hello"}}]}

data: {"choices":[{"delta":{"content":"!"}}]}

data: [DONE]

Rate limits

Rate limits protect the stability of the gateway for everyone. Limits depend on your active plan and are enforced per API key.

Every response includes headers describing your current limit status:

Wallet & billing

Every account has a prepaid wallet. Top it up once, then spend it across any supported model — usage is deducted per request based on tokens or units consumed.

API keys

API keys authenticate your requests and can be scoped to specific models or usage limits via key groups.

Best practices

• Create a separate key per application or environment (production, staging, local).
• Store keys in environment variables, never in source control.
• Use key groups to cap spend or restrict a key to specific models.
• Revoke a key immediately if you suspect it has been exposed.

Create an API key

Plans & subscriptions

Choose a plan for predictable monthly credit, or stay on pay-as-you-go and simply keep your wallet topped up.

Models & providers

The gateway currently routes to the following providers. Call GET /models with your API key for the exact, live model list.

OpenAI

Anthropic

Google AI

DeepSeek

Zhipu AI

Moonshot AI

Tencent

Meta

Frequently asked questions