datacenter
Louer Nvidia H200 NVL.
Hopper
141GB VRAM
From $0.50/hr
Per hour
$0.50
Per day
$12.00
Per week
$84.00
Per month
$360
Provider spread
3 providers ·
up to 90% cheaper at the low end
Cheapest · $0.50/hr on RunPod
Median $3.59/hr
Most expensive · $5.02/hr on AceCloud
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
AI models that fit
See all 12 →
Run these on this GPU.
- Seed-1.8 1× · int4
- NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 1× · fp16
- ByteDance Seed: Seed 1.6 1× · int4
Cloud instances
See all 18 →
Hyperscaler bundles.
Pre-configured on 1 clouds — from $5.02/hr total
($5.02/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia H200 NVL right now?
The cheapest current listing is $0.50/hr on RunPod, and the median across the 3 providers listing it is $3.59/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $365.
What AI models can the Nvidia H200 NVL run?
With 141 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia H200 NVL?
12 models in our catalog have a recommended configuration for this card, with the quantization that fits its 141 GB — see the AI models tab.
Why does the Nvidia H200 NVL cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia H200 NVL price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$5.02/hr
Lowest $/hr per GPU
$5.02/hr
Providers
1
Instance shapes
18
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| N.H200.16.128 | 1× | 16 | 128 GB | — | $5.02/hr | $5.02/hr | ||
| N.H200.16.128 | 1× | 16 | 128 GB | — | $5.02/hr | $5.02/hr | ||
| N.H200.16.128 | 1× | 16 | 128 GB | — | $5.02/hr | $5.02/hr | ||
| N.H200.24.192 | 1× | 24 | 192 GB | — | $5.42/hr | $5.42/hr | ||
| N.H200.24.192 | 1× | 24 | 192 GB | — | $5.42/hr | $5.42/hr | ||
| N.H200.24.192 | 1× | 24 | 192 GB | — | $5.42/hr | $5.42/hr | ||
| N.H200.28.282 | 1× | 28 | 282 GB | — | $5.97/hr | $5.97/hr | ||
| N.H200.28.282 | 1× | 28 | 282 GB | — | $5.97/hr | $5.97/hr | ||
| N.H200.28.282 | 1× | 28 | 282 GB | — | $5.97/hr | $5.97/hr | ||
| N.H200.48.384 | 2× | 48 | 384 GB | — | $10.83/hr | $5.42/hr | ||
| N.H200.48.384 | 2× | 48 | 384 GB | — | $10.83/hr | $5.42/hr | ||
| N.H200.48.384 | 2× | 48 | 384 GB | — | $10.83/hr | $5.42/hr | ||
| N.H200.56.564 | 2× | 56 | 564 GB | — | $11.93/hr | $5.96/hr | ||
| N.H200.56.564 | 2× | 56 | 564 GB | — | $11.93/hr | $5.96/hr | ||
| N.H200.56.564 | 2× | 56 | 564 GB | — | $11.93/hr | $5.96/hr | ||
| N.H200.96.768 | 4× | 96 | 768 GB | — | $21.66/hr | $5.42/hr | ||
| N.H200.96.768 | 4× | 96 | 768 GB | — | $21.66/hr | $5.42/hr | ||
| N.H200.96.768 | 4× | 96 | 768 GB | — | $21.66/hr | $5.42/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
How much does it cost to rent the Nvidia H200 NVL right now?
The cheapest current listing is $0.50/hr on RunPod, and the median across the 3 providers listing it is $3.59/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $365.
What AI models can the Nvidia H200 NVL run?
With 141 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia H200 NVL?
12 models in our catalog have a recommended configuration for this card, with the quantization that fits its 141 GB — see the AI models tab.
Why does the Nvidia H200 NVL cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia H200 NVL price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
AI models
FP16
INT4
INT4
INT4
INT4
FP8
FP8
FP8
FP8
FP8
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia H200 NVL.
?
INT4
Seed-1.8
by Bytedance
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
200B
Context
256K tokens
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
by Nvidia
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
49B
Context
131K tokens
?
INT4
ByteDance Seed: Seed 1.6
by Bytedance Seed
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
200B
Context
262K tokens
Mixtral 8x22B
by Mistral AI
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
141B (39B active)
Context
66K tokens
Mistral Large 2
by Mistral AI
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
123B
Context
128K tokens
Qwen3.5 122B A10b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
122B
Context
262K tokens
Qwen: Qwen3.5-122B-A10B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
122B
Context
262K tokens
Command R+
by Cohere
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
104B
Context
128K tokens
Llama 3.2 90B Vision
by Meta AI
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
90B
Context
128K tokens
GLM-4.5-Air
by Zhipu AI
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
106B (12B active)
Context
128K tokens
Qwen: Qwen3 Next 80B A3B Thinking
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
80B
Context
262K tokens
Qwen: Qwen3 Next 80B A3B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia H200 NVL
Total VRAM
141 GB
Parameters
80B
Context
262K tokens
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →
FAQ
AI models on this GPU.
How much does it cost to rent the Nvidia H200 NVL right now?
The cheapest current listing is $0.50/hr on RunPod, and the median across the 3 providers listing it is $3.59/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $365.
What AI models can the Nvidia H200 NVL run?
With 141 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia H200 NVL?
12 models in our catalog have a recommended configuration for this card, with the quantization that fits its 141 GB — see the AI models tab.
Why does the Nvidia H200 NVL cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia H200 NVL price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.