← Back to all offerings

H200

141 GB VRAM989 FP16 TFLOPS700 W TDP6 providers77 offerings35 regions

The H200 is a cloud GPU with 141 GB of memory and 700 W TDP. It is currently available from 6 providers starting at $0.50/hr, with a market median of $4.00/hr across 77 offerings.

$0.50/hr
Cheapest
on HardwareHQ
$4.00/hr
Median
across 77 offerings
$83.78/hr
Most expensive
-47.0%
90-day trend

Best deal

Hardware specifications

Architecture
Hopper
VRAM
141 GB
Memory type
HBM3
Memory bandwidth
4,800 GB/s
FP16
989 TFLOPS
FP32
67 TFLOPS
TDP
700 W

Same across all providers.

Market comparison

$4.00/hr
Our median / hr
$3.99/hr
gpus.io median / hr
77
Our providers
9
gpus.io providers

View source on gpus.io

All-time price history

Offerings

All ×N×1×2×4×8In stock only · Partners only
ProviderCloudCountvCPURAMRegionPer GPU hrSPOTTotal/hr
HardwareHQ
0.0% 30dReferral link
×1$0.50/hr$0.50/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2$0.50/hr$1.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1New Jersey, US$1.98/hr$1.71/hr$1.98/hrLaunch ↗
GPU Finder
0.0% 30d
×1FI, IS$2.00/hr$2.00/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×4$0.50/hr$2.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1ap-east-2$2.10/hr$2.10/hrLaunch ↗
GPU Finder
0.0% 30d
×1it-fr2$2.60/hr$2.60/hrLaunch ↗
GPU Finder
0.0% 30d
×1Montana, US$2.61/hr$1.95/hr$2.61/hrLaunch ↗
GPU Finder
0.0% 30d
×1Georgia, US$2.63/hr$2.50/hr$2.63/hrLaunch ↗
GPU Finder
0.0% 30d
×1FI, FR, US$2.67/hr$2.67/hrLaunch ↗
GPU Finder
0.0% 30d
×1Russia$2.78/hr$2.78/hrLaunch ↗
GPU Finder
0.0% 30d
×1United States$3.00/hr$3.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1United States$3.00/hr$3.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1California, US$3.00/hr$1.00/hr$3.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1Georgia, US$3.30/hr$1.64/hr$3.30/hrLaunch ↗
GPU Finder
0.0% 30d
×1Global$3.59/hr$3.59/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×1$3.59/hr$3.59/hrLaunch ↗
GPU Finder
0.0% 30d
×1Global$3.59/hr$3.59/hrLaunch ↗
RunPodPromoted
0.0% 30dReferral link
Community×1$3.59/hr$3.59/hrLaunch ↗
GPU Finder
0.0% 30d
×1Japan, JP$3.60/hr$3.60/hrLaunch ↗
GPU Finder
0.0% 30d
×1Bulgaria, BG$3.60/hr$2.40/hr$3.60/hrLaunch ↗
GPU Finder
0.0% 30d
×1New York, US$3.61/hr$3.55/hr$3.61/hrLaunch ↗
GPU Finder
0.0% 30d
×1Singapore$3.65/hr$3.65/hrLaunch ↗
GPU Finder
0.0% 30d
×1Singapore$3.65/hr$3.65/hrLaunch ↗
GPU Finder
0.0% 30d
×1theta-cloud$3.69/hr$3.69/hrLaunch ↗
RunPodPromoted
0.0% 30dReferral link
Secure×1$3.79/hr$3.79/hrLaunch ↗
GPU Finder
0.0% 30d
×1Global$3.79/hr$3.79/hrLaunch ↗
GPU Finder
0.0% 30d
×1Mississippi, US$3.79/hr$1.47/hr$3.79/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×1504 GBJP$3.87/hr$3.87/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×1JP$3.87/hr$3.87/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×1SA$3.98/hr$3.98/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×1SA$3.98/hr$3.98/hrLaunch ↗
GPU Finder
0.0% 30d
×1Saudi Arabia, SA$3.98/hr$3.98/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×1378 GBSA$3.98/hr$3.98/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×1378 GBSA$3.98/hr$3.98/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×8$0.50/hr$4.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1FIN-02, FIN-03$4.00/hr$2.00/hr$4.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1FIN-02$4.00/hr$2.00/hr$4.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1Japan, JP$4.00/hr$3.47/hr$4.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1Texas, US$4.00/hr$4.00/hrLaunch ↗
GPU Finder
0.0% 30d
×1FIN-03$4.00/hr$4.00/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×1US$4.01/hr$4.01/hrLaunch ↗
GPU Finder
0.0% 30d
×1Washington, US$4.21/hr$4.21/hrLaunch ↗
GPU Finder
0.0% 30d
×1Finland$4.23/hr$4.23/hrLaunch ↗
GPU Finder
0.0% 30d
×1eu-north1, eu-west1, us-central1$4.50/hr$2.45/hr$4.50/hrLaunch ↗
GPU Finder
0.0% 30d
×1eu-north1, eu-west1, us-central1$4.50/hr$2.45/hr$4.50/hrLaunch ↗
RunPodPromoted
0.0% 30dReferral link
Secure×1$4.59/hr$4.59/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×1236 GBCZ$4.87/hr$4.87/hrLaunch ↗
GPU Finder
0.0% 30d
×1, US$5.00/hr$4.61/hr$5.00/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×1CZ$5.14/hr$5.14/hrLaunch ↗
GPU Finder
0.0% 30d
×1Czechia, CZ$5.86/hr$1.32/hr$5.86/hrLaunch ↗
YouGPU
0.0% 30dReferral link
×1ru$7.14/hr$7.14/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2$3.59/hr$7.18/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2504 GBJP$3.68/hr$7.35/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×2US$3.79/hr$7.58/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×2SA$3.98/hr$7.95/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2504 GBCZ$4.32/hr$8.64/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×2CA$4.35/hr$8.69/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2504 GBCA$4.35/hr$8.69/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×2CZ$4.52/hr$9.04/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×1ru$9.07/hr$9.07/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2504 GBCZ$5.13/hr$10.25/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×1ru$10.47/hr$10.47/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×2CZ$5.93/hr$11.85/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×4$3.59/hr$14.36/hrLaunch ↗
Vast.ai
0.0% 30dReferral link
×4SA$3.98/hr$15.90/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×41008 GBJP$4.08/hr$16.31/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×41008 GBCA$4.34/hr$17.37/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×2ru$9.07/hr$18.14/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×2ru$10.47/hr$20.94/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×8$3.59/hr$28.72/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×82015 GBIS$4.08/hr$32.64/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×82015 GBIT$4.48/hr$35.80/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×4ru$9.07/hr$36.27/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×4ru$10.47/hr$41.89/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×8ru$9.16/hr$73.28/hrLaunch ↗
CloudCompute
0.0% 30dReferral link
×8ru$10.47/hr$83.78/hrLaunch ↗

LLMs that fit

ModelParams16-bit8-bit4-bit
Kimi K2.5
Moonshot AI
1T 32B activeNot releasedNot released7× · 13.2% spare
GLM-5.2
Z.ai
753BNeeds >8 GPUsNeeds >8 GPUsBarely fits on 5×
DeepSeek R1
DeepSeek
671B 37B activeNot releasedBarely fits on 8×5× · 127.8 GB free
DeepSeek V4 Flash
DeepSeek
284BNot releasedNot released2× · 51.6 GB free
Solar Open2 250B
Upstage
250B 15B active6× · 14.8% spareBarely fits on 3×2× · 51.6 GB free
Qwen3 235B-A22B
Alibaba
235B 22B activeBarely fits on 5×Barely fits on 3×2× · 64.8 GB free
Laguna-S 2.1
Poolside
118B 8B active3× · 84.6 GB free2× · 96 GB free1× · 33 GB free
gpt-oss-120b
OpenAI
117B 5.1B activeNot releasedNot released1× · 47.4 GB free
Llama 3.1 70B
Meta
70B2× · 114 GB free1× · 49.2 GB free1× · 87 GB free
Qwen3.6 35B-A3B
Alibaba
35B 3B active1× · 37.8 GB free1× · 84.6 GB free1× · 107.4 GB free
Qwen3 32B
Alibaba
32.8B1× · 46.2 GB free1× · 89.4 GB free1× · 111 GB free
Qwen2.5 14B
Alibaba
14B1× · 105.6 GB free1× · 121.7 GB free1× · 129.6 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.

Similar GPUs

Frequently asked questions

How much does the H200 cost per hour?

The cheapest H200 offering starts at $0.50/hr, and the market median is $4.00/hr.

Which cloud providers offer the H200?

We track H200 offerings from HardwareHQ, GPU Finder, RunPod, Vast.ai, YouGPU, CloudCompute.

How much VRAM does the H200 have?

The H200 has 141 GB of VRAM.

What LLMs can run on the H200?

With 141 GB of VRAM, the H200 can run 15 of our tracked models in 4-bit quantization, including Kimi K2.5, GLM-5.2, DeepSeek R1. 10 models fit in 16-bit precision.

What's the biggest LLM I can run on multiple H200s?

With 8× H200 (1128 GB total), the largest tracked model that fits in 16-bit is Solar Open2 250B (250B params), which needs 6× GPUs.

Where is the H200 cheapest?

The cheapest H200 offering in our catalog is HardwareHQ at $0.50/hr per GPU-hour (×1).