G-A2X Guide — Quick Start & API Reference

1. Getting Your API Key

Follow these steps to purchase tokens and receive your API key. The entire process takes less than 5 minutes.

1

Choose a Plan

Select Starter ($50), Pro ($500), or Enterprise ($2,000+) on the Pricing page.

2

Send USDT

Transfer USDT (TRC-20) to the provided wallet address. Include the unique memo tag.

3

Receive API Key

Once confirmed, your API key is displayed on screen and sent to your email.

📷

Payment Flow Screenshot

[Screenshot: Select plan → Enter email → Scan QR → Receive API key]

2. Quick Start

Once you have your API key, you can start using G-A2X immediately. The API is OpenAI-compatible, so it works with any OpenAI client library.

curl

# Chat completion
curl https://glue.mdx.hk/v1/chat/completions   -H "Authorization: Bearer g-a2x-xxxxxxxxxxxxxxxxxxxx"   -H "Content-Type: application/json"   -d '{
    "model": "g-a2x-default",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
            

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://glue.mdx.hk/v1",
    api_key="g-a2x-xxxxxxxxxxxxxxxxxxxx"
)

response = client.chat.completions.create(
    model="g-a2x-default",
    messages=[{"role": "user", "content": "What is DeepSeek?"}]
)

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

JavaScript (Node.js)

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://glue.mdx.hk/v1",
    apiKey: "g-a2x-xxxxxxxxxxxxxxxxxxxx"
});

const response = await client.chat.completions.create({
    model: "g-a2x-default",
    messages: [{ role: "user", content: "Hello!" }]
});

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

Available Models

Replace g-a2x-default with any of these model IDs:

# Smart routing (recommended)
g-a2x-default     # Automatically selects best model for your task
g-a2x-fast        # Fast responses, economy tier
g-a2x-powerful    # Deep reasoning, quality tier

# Direct model access
deepseek-v4-flash
deepseek-v4-pro
qwen-plus
qwen-turbo
qwen-max
            

3. Models Available

G-A2X provides access to China's leading AI models through a single, unified API. All models are accessible via OpenAI-compatible endpoints.

Model ID	Provider	Tier	Best For
g-a2x-default	G-A2X Router	Auto	Smart routing — recommended for most use cases
g-a2x-fast	G-A2X Router	Economy	Low latency, high throughput tasks
g-a2x-powerful	G-A2X Router	Quality	Complex reasoning, code generation
deepseek-v4-flash	DeepSeek	Economy	Fast, cost-effective chat
deepseek-v4	DeepSeek	Balanced	General purpose, production workloads
deepseek-v4-pro	DeepSeek	Quality	Complex reasoning, deep analysis
qwen-turbo	Alibaba Cloud	Economy	Fast inference, high throughput
qwen-plus	Alibaba Cloud	Balanced	Balanced quality and speed
qwen-max	Alibaba Cloud	Quality	Highest quality, complex tasks

4. Pricing Details

G-A2X uses a smart routing system that automatically selects the most cost-effective model for each request. You only pay for the tokens consumed.

Retail Pricing

Pay-as-you-go rate: $0.99 / 1M tokens

Wholesale Plans

Plan	Prepay	Effective Rate	Savings
Starter	$50	$0.99 / M	Retail
Pro	$500	$0.55 / M	-45%
Enterprise	$2,000+	$0.50 / M	-50%

Model Tier Cost Breakdown

Tier	Cost per M Tokens	Models
Economy	$0.36	DeepSeek-V4-Flash, Qwen-Turbo
Balanced	$0.51	DeepSeek-V4, Qwen-Plus
Quality	$0.65	DeepSeek-V4-Pro, Qwen-Max

* For $5,000+ prepay, contact us for custom negotiated pricing.

5. FAQ

How do I pay with USDT? ▼

Select a plan on the Pricing page, enter your email, and you'll receive a unique USDT (TRC-20) wallet address with a memo tag. Send the exact amount to that address using any wallet or exchange that supports TRC-20 transfers. We recommend using Binance, OKX, or Bybit.

How long does it take to activate? ▼

Most payments are confirmed within 1-5 minutes after the USDT network confirms the transaction. API keys are issued automatically upon confirmation. During high network congestion, it may take up to 30 minutes.

What models do you support? ▼

We support DeepSeek (V4-Flash, V4, V4-Pro) and Alibaba Cloud Qwen (Turbo, Plus, Max) models. Our smart routing system (g-a2x-default) automatically selects the best model for your task. We're constantly adding new models — contact us for the latest list.

Can I use USDC instead of USDT? ▼

Yes! USDC is also accepted. Please contact us at cc88@coze.email for USDC payment instructions, as the wallet address may differ.

Is the API compatible with OpenAI? ▼

Yes! G-A2X provides an OpenAI-compatible API. You can use any OpenAI SDK (Python, Node.js, curl, etc.) by simply changing the base URL to https://glue.mdx.hk/v1 and using your G-A2X API key.

What if I need a custom plan? ▼

For custom volume, dedicated infrastructure, or enterprise-grade SLAs, contact us at cc88@coze.email. We offer negotiated pricing for $5,000+ prepay and can accommodate specific model requirements.

Is there a refund policy? ▼

Prepaid tokens are non-refundable but never expire. You can use them at any time, and your balance is always visible in your account dashboard. If you experience technical issues, contact us for assistance.