NVIDIA H200: Specs, Pricing & Cloud Availability
Last updated: 2026-03-19
We earn commissions when you shop through the links on this page. Learn more
Technical Specifications
| Architecture | Hopper |
|---|---|
| VRAM | 141 GB HBM3e |
| Memory Bandwidth | 4.8 TB/s |
| FP16 Performance | 1,979 TFLOPS |
| FP8 Performance | 1,979 TFLOPS |
| TDP | 700W |
| Interconnect | NVLink 4.0 |
Cloud Pricing
| Provider | On-Demand $/hr | Spot $/hr | Availability |
|---|---|---|---|
| CoreWeave | $3.50-$5.50/hr | N/A | Available |
| Nebius | $3.50-$5.50/hr | N/A | Available |
Benchmarks
The NVIDIA H200 delivers 1,979 TFLOPS FP16 and 989 TFLOPS FP32 performance with 4.8 TB/s memory bandwidth.
Best Use Cases
The NVIDIA H200 is optimized for Memory-intensive LLM inference at scale.