We may earn commissions when you shop through the links below. Learn more
The H200 pairs Hopper compute with 141 GB of HBM3e memory for large models and long contexts. Compare verified H200 offers by price type, billing and region.
Specifications come from the manufacturer's published data as recorded in our GPU catalog. Prices are USD per GPU-hour across the verified offers listed on this page.
| Figure | H200 141 GB |
|---|---|
| Memory | 141 GB HBM3e |
| FP16 tensor (dense) | 989.5 TFLOPS |
| Architecture · form factor | Hopper · SXM |
| Providers listing it here | 5 |
| Lowest listed price | $2.79≈ €2.49 (estimated conversion from $2.79) per GPU-hour |
| Median pay-as-you-go price | $4.51≈ €4.02 (estimated conversion from $4.51) per GPU-hour |
| Specification source | NVIDIA H200 SXM 141GB (opens in a new tab) |
Enter a purchase price per GPU from a quote you have; hardware prices are not in our data. We compare it with the median verified pay-as-you-go price on this page.
The H200 median on this page is $4.51 per GPU-hour. Enter a purchase price to see after how many rental hours buying would cost the same.
These 5 providers have no verified H200 offer in our data (full provider review ): Fly.io, Hetzner, Lambda, OVHcloud and Scaleway.
Filters match a provider when one of its listed offers meets every GPU, VRAM, region, price and billing-increment condition together. Spot, reserved and serverless billing list each provider that offers that pricing and show only prices on that basis, or “not verified” when we have none. Read the full methodology and our affiliate disclosure.
The H200 SXM 141GB has 141 GB of HBM3e at 4,800 GB/s and 989.5 dense FP16 TFLOPS. The H100 SXM 80GB has 80 GB of HBM3 at 3,350 GB/s and 989.5 dense FP16 TFLOPS. Figures come from NVIDIA's published specifications as recorded in our GPU catalog.
Verified pay-as-you-go H200 prices on this page start at $3.99 per GPU-hour (Hyperstack, on-demand, rented as 8 GPUs), with a median of $4.51 across 6 prices (checked 20 Oct 2026). Prices are per GPU; spot, reserved and marketplace prices are listed separately and can be lower. Amounts are in US dollars (USD), excluding VAT.
NVIDIA's specifications give the H200 SXM the same 989.5 dense FP16 TFLOPS as the H100 SXM, yet the H200 costs more: the median verified pay-as-you-go price in our data is $4.51 per GPU-hour for the H200 (6 prices) against $3.99 for the H100 SXM (15 prices), checked 20 Oct 2026. Its extra memory (141 GB of HBM3e at 4,800 GB/s against 80 GB at 3,350 GB/s) only pays off when a model, its context or its batch does not fit in 80 GB. Amounts are in US dollars (USD), excluding VAT.
Yes. The providers listed here offer H200 capacity on demand, as spot, serverless or marketplace offers, or under reservation; the price type on each row tells you which. Some sell it only as 8-GPU nodes.
Per GPU. Every GPU price is shown in USD per single GPU per hour; offers for multi-GPU nodes are divided by the number of GPUs, and a price you can only rent as a whole node says so (for example “rented as 8 GPUs”). Storage, data transfer and taxes are not included unless the provider includes them.
We only show a value when an official provider source confirms it. If we could not confirm a price or feature, the row says “Not verified” instead of showing an estimate, and the provider page lists the sources we did check.
