API Documentation

Table of Contents

Getting Started

GPU4AI provides a simple REST API compatible with OpenAI's API format. You can easily migrate from other GPU cloud providers by just changing the endpoint URL.

Base URL

https://api.gpu4ai.vip/v1

Quick Example

curl https://api.gpu4ai.vip/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available Models

  • gpt-4o
  • gpt-4o-mini
  • gpt-4-turbo
  • gpt-3.5-turbo
  • claude-3-opus
  • claude-3-sonnet
  • llama-3.1-70b
  • llama-3.1-405b
  • mixtral-8x22b

Authentication

All API requests require an API key. You can get your API key by contacting us at hello@gpu4ai.vip

Using Your API Key

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Pricing

We offer competitive pay-as-you-go pricing. No upfront costs, no commitments.

RTX 4090

$1.20
/ hour
POPULAR

A100 40GB

$2.50
/ hour

H100 80GB

$4.50
/ hour

💡 Tip: Contact us for volume discounts and enterprise pricing.

Frequently Asked Questions

How do I get started?

Simply email us at hello@gpu4ai.vipto request an API key. We'll get you set up within 24 hours.

What payment methods do you accept?

We accept Stripe and PayPal. No Chinese payment methods required.

Can I scale up or down anytime?

Yes! There's no commitment. Scale your GPU usage up or down based on your needs.

What if I need help?

We're here to help! Reach out to us at hello@gpu4ai.vip and we'll respond within 24 hours.

Is my data secure?

Yes. We use industry-standard encryption and don't store your data longer than necessary to provide the service. Your models and data remain yours.

Do you offer dedicated instances?

Yes, for enterprise customers we offer dedicated GPU instances. Contact us at hello@gpu4ai.vip for details.

Still Have Questions?

Can't find what you're looking for? We're happy to help!

Contact Us