NVIDIA / Hopper
H200
| Provider / plan | Price / GPU-hour | Rental type | Terms & configuration | Last checked | Provider pricing link |
|---|---|---|---|---|---|
| CloudRift3-month reservation | $2.38 | ReservedCommitment required | 1 GPU minimumSee provider3 months, upfrontView detailsPer-GPU published list rate; capacity and exact server configuration must be checked with the provider.
|
2026-10-03Auto-collected | View pricing ↗ |
| CloudRift1-month reservation | $2.50 | ReservedCommitment required | 1 GPU minimumSee provider1 month, upfrontView detailsPer-GPU published list rate; capacity and exact server configuration must be checked with the provider.
|
2026-10-03Auto-collected | View pricing ↗ |
| Vast.aiOn-demand offer 49998292 | $3.5556Lowest flexible rate | On-demandNo reservation | 1 GPU minimumGeorgia, USView detailsObserved marketplace offer, not a provider-wide list rate. Total hourly quote for one GPU with the API default disk allocation; bandwidth and additional storage can cost extra. Up to 5 cheapest matching offers per catalog GPU; availability can change.
|
2026-10-03Auto-collected | View pricing ↗ |
| ModalGPU Tasks | $4.5396GPU only · CPU/RAM extra | ServerlessActive GPU time | 1 GPU minimumSee providerView detailsGPU time only; CPU, RAM, storage, region and non-preemptible surcharges are extra.
|
2026-10-03Auto-collected | View pricing ↗ |
| RunpodSecure Cloud Pods | $4.59 | On-demandNo reservation | 1 GPU minimumSee providerView detailsSecure Cloud Pods published GPU-hour rate. CPU/RAM allocation varies; storage/networking extra. Not live capacity.
|
2026-10-03Auto-collected | View pricing ↗ |
| Vast.aiOn-demand offer 53594629 | $5.0044 | On-demandNo reservation | 1 GPU minimumGermany, DEView detailsObserved marketplace offer, not a provider-wide list rate. Total hourly quote for one GPU with the API default disk allocation; bandwidth and additional storage can cost extra. Up to 5 cheapest matching offers per catalog GPU; availability can change.
|
2026-10-03Auto-collected | View pricing ↗ |
| Vast.aiOn-demand offer 39605004 | $5.1213 | On-demandNo reservation | 1 GPU minimumSaudi Arabia, SAView detailsObserved marketplace offer, not a provider-wide list rate. Total hourly quote for one GPU with the API default disk allocation; bandwidth and additional storage can cost extra. Up to 5 cheapest matching offers per catalog GPU; availability can change.
|
2026-10-03Auto-collected | View pricing ↗ |
| Vast.aiOn-demand offer 40323389 | $5.1213 | On-demandNo reservation | 1 GPU minimumSaudi Arabia, SAView detailsObserved marketplace offer, not a provider-wide list rate. Total hourly quote for one GPU with the API default disk allocation; bandwidth and additional storage can cost extra. Up to 5 cheapest matching offers per catalog GPU; availability can change.
|
2026-10-03Auto-collected | View pricing ↗ |
| CloudRiftOn-demand quote | Contact sales | On-demandNo reservation | 1 GPU minimumSee providerView detailsNo public on-demand price. Contact provider.
|
2026-09-28Manually checked | Request quote ↗ |
Prices are dated listings, not live availability. Compare minimum GPU counts and commitments. Storage, networking and taxes may add charges; serverless rates cover GPU time only.
H200 SXM combines Hopper compute with 141 GB of HBM3e memory. It is worth comparing when H100 memory capacity limits model size, context length or batching. This listing describes the SXM edition, not H200 NVL.
CHOOSING THIS GPU
Is it right for your workload?
H200 SXM reference specifications. The PCIe H200 NVL has different power and compute specifications despite the same nominal memory capacity.
Best suited to
- LLM inference with substantial KV-cache memory needs
- Multi-GPU model training and fine-tuning
- Memory-intensive scientific and data-processing workloads
Strengths
- 141 GB of HBM3e
- 4.8 TB/s memory bandwidth
- Hopper Tensor Cores and NVLink connectivity
Things to consider
- Rental topology and power limits affect delivered performance
- More VRAM does not guarantee a proportional speed increase
- SXM modules require a supported server platform
HARDWARE DETAILS
Inside the GPU
- Manufacturer
- NVIDIA
- Architecture
- Hopper
- VRAM (GB)
- 141
- Memory type
- HBM3e
- Form factor
- SXM
- Memory bandwidth (GB/s)
- 4800
- Maximum board power (W)
- 700
- CUDA cores
- Not verified for this edition
- Tensor cores
- 4th generation
- Ray tracing cores
- Not verified for this edition
- CUDA capability
- 9.0
- Memory ECC
- Not verified for this edition
- Host interface
- PCIe Gen5
- GPU interconnect
- 4th generation; 900 GB/s aggregate bidirectional
- Hardware partitioning (MIG)
- Up to 7 hardware instances; provider must enable it
- Cooling
- Server platform dependent
Hardware capabilities are not a guarantee of access in a cloud instance. Check the exact edition, GPU allocation and server topology in the rental offer.
MODEL MEMORY
Plan your model size
70B FP16 weights alone are about 140 GB. Allow additional room for KV cache, activations and the runtime; 141 GB nominal memory is not enough evidence of a practical single-GPU fit. Use quantization or model sharding when needed.
| Example model class | Weight format | Raw weights ≈ | Minimum GPUs for weights only |
|---|---|---|---|
| Llama 3.1 8B ↗ | 4-bit | 4 GB | 1Runtime needs more memory |
| Llama 3.1 8B ↗ | FP16 | 16 GB | 1Runtime needs more memory |
| Qwen2.5 14B ↗ | 4-bit | 7 GB | 1Runtime needs more memory |
| Qwen2.5 32B ↗ | 4-bit | 16 GB | 1Runtime needs more memory |
| Llama 3.1 70B ↗ | 4-bit | 35 GB | 1Runtime needs more memory |
| Llama 3.1 70B ↗ | 8-bit | 70 GB | 1Runtime needs more memory |
| Llama 3.1 70B ↗ | FP16 | 140 GB | 1Runtime needs more memory |
Arithmetic lower bound: rounded parameter count × bits per weight ÷ 8, in decimal GB. Excludes quantization metadata, KV cache, activations, CUDA workspaces and training states. Actual model sizes differ from their rounded names. No context length, batch size or concurrency is guaranteed. GPU counts assume supported model sharding and can be higher in practice. Quantized checkpoints and compatible kernels are required for 4-bit/8-bit execution.
SOFTWARE & PERFORMANCE
Before you deploy
Software compatibility
Use an NVIDIA CUDA-enabled framework/container compatible with this GPU and the host driver. Check PyTorch build and inference-engine kernel requirements before deployment. vLLM documents NVIDIA compute capability 7.5+ as a baseline; support for each model and quantization method still needs checking.
Measured benchmarks
A reproducible, comparable application benchmark has not yet been recorded for this edition. Peak TFLOPS above are not measured tokens per second or image-generation speed.
Compare tests using the same model, precision, GPU count, engine version, input/output length and batch or concurrency. A provider’s server configuration can change the result.
COMPARE YOUR OPTIONS
Alternatives to consider
BUDGET YOUR RUN
GPU cost estimator
GPU compute only: hourly rate × billable hours × GPU count. CPU, RAM, storage, egress, taxes, billing increments and minimum terms may add charges. Serverless hours mean active GPU task time; spot capacity can be interrupted. Reserved commitments and quote-only offers are excluded from this simple hourly estimator.