NVIDIA · Hopper · Layer 2
NVIDIA H200
The value tier now that Blackwell is shipping. Widely available on every GPU cloud, which H100 scarcity once made untrue.
rent Rentable by the hour from multiple clouds; purchasable at scale.
Specifications
- Memory
- 141 GB HBM3E
- Bandwidth
- 4.8 TB/s
- Compute
- Hopper-generation FP8
- Power
- 700 W
- Interconnect
- NVLink 4
- Software
- CUDA
- Form factor
- accelerator
- Workload
- both
Verified 2026-09-09. Fields reading “not published” are exactly that — we do not estimate a figure a vendor withholds.
The catch
A generation behind on throughput per watt, which matters more every quarter as power becomes the constraint rather than capital.
The economics
The price per GPU-hour has fallen hard as Blackwell landed. For inference on models that fit in 141 GB this is often the cheapest sane option.
Cost per million tokens is the metric that decides most real purchases, and there is no neutral benchmark for it — every published figure comes from a company selling one side of the comparison. Read all of them, ours included, as claims rather than measurements.
The power question underneath this
A rack of frontier accelerators draws 120–200 kW against a 2026 average of about 27 kW, and the US grid interconnection queue exceeds 2,600 GW with waits approaching five years. Whether you can energise this part is now a harder question than whether you can buy it.
Layer 1 — Energy · The interconnection queue · Rack power density · Tokens per watt
Where you actually rent this
Choosing the part is the easy half. The same accelerator rents for wildly different money depending only on who you rent it from — the cheapest and dearest published on-demand price for an H100 sit 5.6× apart — and the provider, not the chip, is what decides whether you can leave later.
Layer 2.5 — Compute providers · The GPU cost calculator · H200 rental prices, every company
Compared against
- NVIDIA H100 vs NVIDIA H200 — The same architecture with 61 GB and 1.45 TB/s more. Whether that matters is decided entirely by your model size.Compare with NVIDIA H100
- Qualcomm Cloud AI 100 Ultra vs NVIDIA H200 — 150 W against 700 W. Tokens per watt is a different contest from tokens per second.Compare with Qualcomm Cloud AI 100 Ultra
Related silicon
- NVIDIA B200 — 192 GB HBM3E, rent
- NVIDIA GB200 NVL72 — 13.5 TB HBM3E across the rack, rent
- NVIDIA GB300 NVL72 — Higher HBM3E capacity than GB200; per-rack figure not consistently published, rent
- NVIDIA H100 — 80 GB HBM3, rent
- NVIDIA Vera Rubin VR200 NVL144 — HBM4. NVIDIA quotes 20.7 TB per rack at NVL72 scale; the NVL144 CPX configuration is quoted at 100 TB of fast memory per rack., rent
- NVIDIA RTX PRO 6000 Blackwell — 96 GB GDDR7, buy
Want this whole layer as one table?
The accelerators on these pages as a single CSV — memory, bandwidth, compute, power, interconnect, software stack, availability, who each part is for and the catch — ready to sort, filter or load into a notebook.
Get the silicon table — free for research and evaluation
Four short lines and the download starts at once (CC-BY-NC-4.0, built from these pages the moment you ask). What you type is used only to answer the request and is never sold. Prefer Hugging Face? Request it there.
Using it inside a product, a client report or anything you sell? That needs a commercial licence.