AI Inference
faster than you can type

Build real-time AI applications with lightning fast inference (under ~120ms).
No coldstarts. Pay only for what you use.

Pricing

Ship custom model endpoints with fine-grained control over idle timeout, max concurrency and autoscaling.

  • CPU: 10
  • Memory: 64GB
  • GPU: A100 (40GB VRAM)
  • Total Price: $0.00111/s

Unit Price

CPU
$0.00003/s
Memory
$0.000004/s
GPU A100
$0.001/s
GPU A10G
$0.0002/s
GPU T4
$0.00009/s
Storage
$1/GB/month

Join our community

Join the discussion around our product and help shape the future of AI.