Skip to main content

AI Model API

Access a curated set of AI models through a simple API. Pay only for what you use. No GPU required - we handle the infrastructure.

Simple, Transparent Pricing

Text Models

$0.13 - $0.39

per 1M tokens

Image Models

$0.0026

per image

Audio Models

$0.0008

per minute

Simple API Integration

Get started in minutes with our REST API. Compatible with any programming language. Drop-in replacement for direct HuggingFace calls.

  • Single API key for all models
  • Automatic retries and rate limiting
  • Usage tracking and billing dashboard
  • Built on HuggingFace's managed inference infrastructure
curl -X POST https://api.gpu.fm/v1/inference \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "inputs": "Explain quantum computing",
    "parameters": {
      "max_new_tokens": 256,
      "temperature": 0.7
    }
  }'

Ready to Build?

Get your API key and start making requests in under a minute. Pay only for what you use, from your prepaid credit balance.