Extends the H100 with doubled memory for large-model inference and training.
Weekly median price per GPU per hour · Get the data
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One H200 has 141 GB of VRAM. In practice, that's enough memory for roughly 220B parameters at 4-bit or 58B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | H200s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
1
|
$4.76
|
$3,427
|
Gemma 4 31B
30.7B
|
22 GB
|
1
|
$4.76
|
$3,427
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
1
|
$4.76
|
$3,427
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
2
|
$9.52
|
$6,854
|
MiniMax-M3
428B · 23B active
|
239 GB
|
2
|
$9.52
|
$6,854
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
4
|
$19.04
|
$13,709
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
13
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia H200 · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 1,979 TFLOPS 3,958 with sparsity |
| FP16 / BF16 | 989.5 TFLOPS 1,979 with sparsity |
| INT8 | 1,979 TOPS 3,958 with sparsity |
| FP32 | 67 TFLOPS |
| FP64 | 34 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32FP64INT8 |
| Memory | |
|---|---|
| Capacity | 141 GB HBM3e |
| Bandwidth | 4,800 GB/s |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Hopper |
| Process | TSMC 4N |
| Transistors | 80 billion |
| Shader cores | 16,896 CUDA cores |
| Matrix cores | 528 Tensor cores |
| Compute units | 132 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 900 GB/s |
| Host interface | PCIe 5.0 x16 |
| Power | |
|---|---|
| Board power | 700 W |
| Platform | |
|---|---|
| Partitioning | MIG, up to 7 instances |
Source: official Nvidia H200 datasheet.
As of October 15, 2026, the median on-demand price is $4.76 per GPU per hour across 34 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 113 | $4.76 | $2.09 (not verified in stock, Beam) |
Reserved | 97 | $3.84 | $2.23 (1 mo, not verified in stock, Leaseweb) |
Spot | 27 | $3.54 | $2.29 (in stock, Lyceum) |
7 providers also quote the H200 on a custom contract, priced per deal.
The lowest listed on-demand price for the H200 is $2.09 per GPU per hour from Beam, though we haven't verified current stock. Cheapest verified in stock: on-demand $3.99 from Jarvislabs. Other billing types: reserved $2.23 (1 mo, not verified in stock) from Leaseweb and spot $2.29 (in stock) from Lyceum.
At 720 hours per month, one H200 costs an estimated $3,427 at the median on-demand price. Cheapest verified in stock: $2,873 per month on-demand, $2,938 reserved, $1,649 spot.
GetDeploying currently tracks H200 configs from 49 providers. The cheapest verified in-stock on-demand configs come from Jarvislabs, GPU.ai, Runcrate and Lyceum. See the full price comparison above for every provider and config.
As of October 15, 2026, the median on-demand price has risen about 3% over the past 90 days to $4.76 per GPU per hour, and about 27% over the past 12 months.
One H200 runs models up to roughly 220B parameters at 4-bit quantization or 58B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
141GB HBM3e doubles the memory of the H100 while maintaining NVLink 900 GB/s. Fits 70B+ models without sharding. Best for memory-bound workloads like long-context inference and large batch training.
Limited availability and premium pricing. If your model fits in 80GB or the workload isn't memory-bottlenecked, the H100 offers better price-per-GPU-hour.
Nvidia RTX PRO 6000
96 GB GDDR7 · 67% less bandwidth than the H200
Last updated
