← All hardware
NVIDIA H200 logo
hardware Data Center AI Accelerators

NVIDIA H200

by NVIDIA

The memory-upgraded Hopper GPU that remains the AI workhorse.

Pros

  • 76% more memory than H100 at similar power
  • Broad availability across every cloud
  • Strong price/performance for inference

Cons

  • Hopper generation now superseded by Blackwell
  • Lower FP4 capability than Blackwell
  • Still expensive ($30k-$40k) per GPU

✓ Where it shines / best for

  • Memory-bound LLM inference and serving
  • Large-context generative AI workloads
  • Enterprises upgrading from H100 for inference efficiency

✕ Not the best fit for

  • Frontier-scale training better served by Blackwell racks
  • Edge or on-device deployment
  • Small-budget projects

Features

  • ✓ AI inference
  • ✓ Data-center scale
  • ✓ HBM3E
  • ✓ NVLink
  • ✓ LLM Training
  • ✓ FP8
  • ✓ Transformer Engine
  • ✓ Mig

Pricing

PlanPriceBillingNotes
H200 141GB (street price)$30,000-$45,000one-timePer-GPU street price (SXM/NVL) via OEM systems and resellers; not retail
DGX H200 system (8x H200)$350,000-$500,000one-time8-GPU appliance, 1,128GB HBM3e total; via NVIDIA partners
Cloud rental (per H200)~$3.72-$10.60per hourOn-demand neocloud rate; lower with reserved commitments

Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.

Specifications

power700W TDP
memory141 GB HBM3e, 4.8 TB/s
nvlink4.0, 900 GB/s per GPU
cuda_cores16,896
architectureHopper (TSMC 4N)
tensor_cores528 (4th-gen)
fp8_performance3,958 TFLOPS
Sponsored

A full review is being generated for this product and will appear here shortly.

Compare with

Compare
Compare