H200 NVL GPU Rental
H200 NVL GPUs on Lium have a reference price of $2.90 per GPU-hour, built for large-scale AI training, inference, and HPC. Billed per second with no minimum, deployed in seconds from the browser or the CLI.
Price per GPU-hour
$2.90
Reference price, no pod available right now
Available now
0 pods
0 GPUs in total
Reference price
$2.90
Marketplace baseline per GPU-hour
About the H200 NVL
The H200 NVL is a Hopper-generation NVIDIA data center GPU, built for large-scale AI training, inference, and HPC. Released in 2024, it carries 141 GB of HBM3e at 4,800 GB/s, which sets how large a model fits on one card and how fast its weights stream. On Lium it is rented from independent providers by the second, with no minimum and no reservation, from the browser or the CLI.
What people run on it
- Training and fine-tuning language models
- High-throughput LLM inference
- Multi-GPU jobs in one node
- HPC and scientific computing
H200 NVL specifications
| VRAM | 141 GB HBM3e |
|---|---|
| Memory bandwidth | 4,800 GB/s |
| Architecture | Hopper |
| Released | 2024 |
What runs on one H200 NVL
With 141 GB of memory, one card holds roughly the following open models for inference, counting the weights plus about 20% for activations and cache. Rent several GPUs in one pod to go bigger.
| Precision | Largest model that fits |
|---|---|
| FP16 | 34B parameters |
| 8-bit | 70B parameters |
| 4-bit | 70B parameters |
Running one H200 NVL around the clock for a month (730 hours) costs about $2,117 at the reference price; you pay only for the seconds a pod runs.
Frequently asked questions
How much does it cost to rent an H200 NVL on Lium?
No H200 NVL pod is free at this moment. The marketplace reference price is $2.90 per GPU-hour; the page updates when a provider lists one.
Where is the cheapest place to rent an H200 NVL by the hour?
No H200 NVL pod is free on Lium at this moment; the reference price is $2.90 per GPU-hour, billed per second with no minimum once a provider lists one.
Is there a minimum rental period?
No. Lium bills per second with no minimum and no reservation: start the pod when you need it, delete it when the job is done, and pay for the seconds it ran.
How do I rent an H200 NVL pod?
Top up a balance by card or crypto, pick an H200 NVL pod on the marketplace, choose a Docker template, add your SSH key and deploy. From a script, run lium up with the node id after exporting LIUM_API_KEY.
Where do the machines run, and what happens to my data?
Providers run their own hardware in their own facilities, and every pod on the marketplace names its city and country, so you can pick a region before you start. Your data lives on the machine you rented and is released when you delete the pod; attach a volume if you need storage that outlives a single pod.
Compare with
| GPU | VRAM | Price per GPU-hour |
|---|---|---|
| H200 | 141 GB | from $4.90/hr |
| B200 | 180 GB | from $5.64/hr |
| H100 80GB HBM3 | 80 GB | from $2.00/hr |
For AI agents — CLI install, agent skill, headless signup: llms-full.txt