NVIDIA H200 NVL cloud GPU rental
Rent an NVIDIA H200 NVL cloud GPU from $4.09 per hour with 143 GB of HBM3e at 4.8 TB/s of memory bandwidth. FastInfra bills pods per minute with no commitment, so a one-hour experiment costs $4.09 and you stop paying the moment you delete the pod. Run 1 to 8 GPUs per pod, connect over SSH or JupyterLab, and see the exact price before you deploy.
Prices synced November 3, 2026 · billed per minute
H200 NVL specs and pricing
The NVIDIA H200 NVL is a datacenter Hopper GPU with 143 GB of HBM3e at 4.8 TB/s of memory bandwidth. On FastInfra it is a good fit for frontier-scale training, 200B+ inference, long-context serving. As a rule of thumb, one H200 NVL holds the weights of a model of about 57B parameters at 16-bit precision, or about 220B with 4-bit quantization, after leaving room for the KV cache.
The H200 NVL runs on the Secure tier in vetted datacenters at $4.09 per GPU-hour.
H200 NVL price per hour by GPU count
Live FastInfra prices per pod-hour. Pods bill per minute, so you pay only for the minutes a pod exists.
| Pod size | Total VRAM | Secure / hr | Month (730 h, lowest) |
|---|---|---|---|
| 1× H200 NVL | 143 GB | $4.09 | $2,989 |
| 2× H200 NVL | 286 GB | $8.19 | $5,977 |
| 4× H200 NVL | 572 GB | $16.38 | $11,954 |
| 8× H200 NVL | 1144 GB | $32.75 | $23,909 |
What an H200 NVL costs over time
One GPU at the lowest on-demand rate ($4.09/hr).
| Duration | On-demand |
|---|---|
| 1 hour | $4.09 |
| 8-hour working day | $32.75 |
| 24 hours | $98.26 |
| 1 week (168 hours) | $688 |
| 1 month (730 hours) | $2,989 |
Which LLMs fit on the H200 NVL?
GPUs needed to hold the model weights with about 20% of VRAM left for the KV cache. Rule of thumb only: long contexts and big batches need more.
| Model size | Examples | FP16 / BF16 | 8-bit | 4-bit |
|---|---|---|---|---|
| 7–8B | Llama 3.1 8B, Qwen3 8B, Mistral 7B | 1 GPU | 1 GPU | 1 GPU |
| 12–14B | Gemma 3 12B, Qwen3 14B, Phi-4 | 1 GPU | 1 GPU | 1 GPU |
| 27–32B | Gemma 3 27B, Qwen3 32B | 1 GPU | 1 GPU | 1 GPU |
| 70B | Llama 3.3 70B | 2 GPUs | 1 GPU | 1 GPU |
| 120B | GPT-OSS 120B | 4 GPUs | 2 GPUs | 1 GPU |
| 235B | Qwen3 235B-A22B | 8 GPUs | 4 GPUs | 2 GPUs |
| 405B | Llama 3.1 405B | 8 GPUs | 4 GPUs | 2 GPUs |
| 671B | DeepSeek V3 / R1 | Needs more GPUs | 8 GPUs | 4 GPUs |
Best for
Frontier-scale training, 200B+ inference, long-context serving.
About the Hopper architecture
Hopper introduced the Transformer Engine with FP8 precision and fourth-generation NVLink at up to 900 GB/s per GPU. It is the most widely deployed architecture for LLM training and serving, and vLLM, SGLang, TensorRT-LLM, FlashAttention 3 and PyTorch are all tuned for it, so most open-source training and inference code runs at full speed without changes.
Only need inference?
If you want to call an open model such as Llama, Qwen, DeepSeek or GPT-OSS rather than manage a server, the pay-per-token inference API is often cheaper than keeping a GPU busy around the clock. It is OpenAI-compatible and uses the same account and wallet as your pods. Browse every model with live prices.
H200 NVL vs similar GPUs
Live lowest on-demand price per GPU-hour, and price per GB of VRAM.
| GPU | VRAM | Architecture | From / hr | Per GB-hr |
|---|---|---|---|---|
| H200 NVL (this page) | 143 GB | Hopper | $4.09 | $0.029 |
| AMD Instinct MI300X | 192 GB | CDNA 3 | $2.58 | $0.013 |
| NVIDIA B200 | 180 GB | Blackwell | $6.46 | $0.036 |
| NVIDIA H200 SXM | 141 GB | Hopper | $3.88 | $0.028 |
| NVIDIA RTX PRO 6000 Max-Q | 96 GB | Blackwell | $1.77 | $0.018 |
| NVIDIA RTX PRO 6000 | 96 GB | Blackwell | $1.83 | $0.019 |
| NVIDIA RTX PRO 6000 Workstation | 96 GB | Blackwell | $1.83 | $0.019 |
H200 NVL rental — frequently asked questions
How much does it cost to rent an NVIDIA H200 NVL per hour?
$4.09 per GPU-hour on demand. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $2,989 per GPU at the lowest on-demand rate. Prices sync from live capacity and are shown before you deploy.
How much VRAM does the NVIDIA H200 NVL have?
143 GB of HBM3e at 4.8 TB/s of memory bandwidth. The chip is rated at up to 600 W. A pod with 8 GPUs gives 1,144 GB of combined VRAM for tensor- or pipeline-parallel workloads.
What size LLM can I run on an NVIDIA H200 NVL?
Roughly 57B parameters at FP16 or BF16, 110B at 8-bit and 220B at 4-bit on a single GPU, reserving about 20% of VRAM for the KV cache and activations. Mixture-of-experts models need memory for all experts, not only the active ones. Long contexts and large batches need more headroom.
Is the NVIDIA H200 NVL billed per hour or per minute?
Per minute. The hourly rate is divided by 60 and charged for every minute the pod exists. Attached volumes bill per GB-month and continue while a pod is stopped; delete the pod to stop all charges. There is no minimum term or reservation fee.
How do I rent an NVIDIA H200 NVL on FastInfra?
Create an account, add prepaid credit, open the GPU configurator and choose the H200 NVL, the tier, the GPU count, a container template and storage. The configurator shows the hourly and monthly price, then deploys a pod you reach over SSH or JupyterLab within minutes.
Can I rent multiple H200 NVL GPUs in one pod?
Yes, up to 8 per pod. The price scales linearly: 8 GPUs cost $32.75 per hour on Secure.
Is there a cheaper GPU than the H200 NVL with the same VRAM?
Yes. The AMD Instinct MI300X has 192 GB and starts at $2.58 per hour. It differs in architecture (CDNA 3), memory bandwidth and multi-GPU interconnect, so compare throughput for your workload before switching.
Deploy an H200 NVL in minutes
Price the exact pod, storage and template in the configurator, add credit, and connect over SSH or JupyterLab. Billed per minute, no commitment.