H100 GPU
NVIDIA H100 Tensor Core GPU, the most advanced accelerator for AI and HPC workloads
Key Specifications
💾Memory
80GB VRAM
🏗️Architecture
Hopper
⚙️Compute Units
132
🧮Tensor Cores
456
Technical Specifications
Hardware Details
Memory & Performance
Performance
Computing Power
Computational Performance
ML Benchmark Scores
Benchmark Resources
Pros and Cons
Pros
- ✓Groundbreaking performance for AI workloads
- ✓Next-generation Tensor Cores with significant performance uplift
- ✓Transformer Engine for accelerating language models
- ✓New architectural features for advanced computing tasks
- ✓Support for HBM3 memory with massive bandwidth
Cons
- ✗Very high power consumption
- ✗Premium pricing
- ✗Requires specialized cooling and power infrastructure
- ✗Not suitable for most consumer or small business applications
Key Features
About H100
Common Use Cases
The H100 GPU is designed for the most demanding AI and HPC workloads, including training and inference for large language models (LLMs), foundation models, generative AI, healthcare research, scientific simulation, and financial modeling. It excels at large-scale machine learning tasks, natural language processing, computer vision, and computational chemistry.
Market Context
The H100 sits within NVIDIA’s Hopper architecture lineup, positioned in the ultra performance tier. It’s designed specifically for data center and enterprise use.
Cloud Availability
Available across 67 cloud providers with prices ranging from $0.49/hr. Pricing and availability may vary by region and provider.
Market Position
Released in 2022, this GPU launched at $30,000 for enterprise and data center workloads.
Cheapest H100 Pricing
The cheapest H100 is $0.49/hr on Amazon AWS, which is 90% below the average of $4.69/hr across 67 providers.
Current Pricing
| Provider | Hourly Price | Source |
|---|---|---|
Deep Infra | $1.69/hr | |
Nebius | $3.06/hr | |
Nebius | $3.00/hr | |
CoreWeave | $49.24/hr | |
CoreWeave | $0.72/hr | |
CoreWeave | $6.16/hr | |
CoreWeave | $49.24/hr | |
RunPod | $2.69/hr | |
RunPod | $2.69/hr | |
RunPod | $1.50/hr | |
Amazon AWS | $3.93/hr | |
Amazon AWS | $0.49/hr | |
Vast.ai | $1.55/hr | |
Vast.ai | $2.27/hr | |
Hyperstack | $1.90/hr | |
Hyperstack | $1.90/hr | |
Hyperstack | $1.90/hr | |
Hyperstack | $1.90/hr | |
Hyperstack | $1.90/hr | |
Hyperstack | $1.33/hr | |
Voltage Park | $1.99/hr | |
Voltage Park | $1.99/hr | |
Voltage Park | $1.99/hr | |
Voltage Park | $1.99/hr | |
Lambda Labs | $2.49/hr | |
Lambda Labs | $3.19/hr | |
Lambda Labs | $3.09/hr | |
Lambda Labs | $2.99/hr | |
Genesis Cloud | $2.19/hr | |
IO.NET | $1.19/hr | |
Jarvis Labs | $2.99/hr | |
Jarvis Labs | $2.99/hr | |
Seeweb | $2.17/hr | |
Seeweb | $2.21/hr | |
Fluidstack | $2.10/hr | |
Fluidstack | $2.89/hr | |
Hyperbolic | $1.50/hr | |
Scaleway | $3.08/hr | |
Scaleway | $3.04/hr | |
Scaleway | $2.90/hr | |
Scaleway | $2.88/hr | |
Vultr | $2.99/hr | |
Vultr | $2.99/hr | |
Vultr | $2.99/hr | |
Together AI | $3.49/hr | |
Together AI | $2.69/hr | |
Fireworks AI | $4.00/hr | |
Crusoe | $3.90/hr | |
Crusoe | $1.60/hr | |
Paperspace | $2.24/hr | |
Paperspace | $47.76/hr | |
Cudo Compute | $1.79/hr | |
Replicate | $5.49/hr | |
Replicate | $5.49/hr | |
Replicate | $5.49/hr | |
Replicate | $5.49/hr | |
Massed Compute | $2.70/hr | |
Latitude.sh | $1.66/hr | |
Latitude.sh | $2.98/hr | |
Latitude.sh | $2.24/hr | |
Latitude.sh | $1.79/hr | |
TensorDock | $2.25/hr | |
Verda | $2.29/hr | |
Verda | $2.29/hr | |
Verda | $2.29/hr | |
Verda | $2.29/hr | |
Verda | $2.19/hr |
Prices are updated regularly. Last updated: 3/27/2026
Where to Buy
*Some links are affiliate links. We may earn a commission if you make a purchase.