Simple, Transparent Pricing
No hidden fees. No commitments. Pay only for what you use.
Technical Specifications
GPU Memory
192GB HBM3e
Memory Bandwidth
8000 GB/s
FP32 Performance
90 TFLOPS
FP16 Performance
180 TFLOPS
Tensor Cores
18,432
TDP
1000W
Architecture
Blackwell
Form Factor
Superchip
Release Year
2024
Perfect For
Large Language Models
AI Supercomputing
Enterprise AI
Multi-Modal Training
Compare Pricing
| GPU Model | VRAM | Performance | Price/Hour |
|---|---|---|---|
NVIDIA GB200Current | 192GB | 90 TFLOPS | $3.75 |
| NVIDIA B200 | 192GB | 90 TFLOPS | $3.40 |
| NVIDIA H200 | 141GB | 67 TFLOPS | $2.25 |
| NVIDIA H100 SXM | 80GB | 60 TFLOPS | $1.50 |
| NVIDIA H100 PCIe | 80GB | 51 TFLOPS | $1.40 |
Reserved Clusters
Enterprise-grade infrastructure
24h Quote
Need More? We've Got You Covered
Get a custom quote in 24 hours for reserved GPU clusters with high-speed interconnect, any region, any GPU model, and any number of GPUs you need.
Any GPU
Choose your hardware
Any Quantity
Scale as needed
Any Region
Global availability
Interconnect
High-speed networking
Why Choose Runcrate
Deploy in 60 Seconds
Get your GPU instance running in under a minute. No complex setup required.
Pay-As-You-Go
Only pay for what you use. No upfront costs or long-term commitments.
Enterprise Security
Your data is encrypted and isolated. SOC 2 compliant infrastructure.