NVIDIA® H200 SXM5
GPU Instances and Clusters
Premium service with flexible access starting at $2.35/h
H200 SXM5 with DataCrunch
Where flexibility meets performance and simplicityGPU Instances
Instant Clusters
Bare-metal Clusters
H200 SXM5 Pricing
Unmatched prices for H200 SXM5 with peak performance and expert support-
$3.13/h
On-demand fixed price -
$2.35/h
2-year contract -
$1.49/h
Spot instance
H200 SXM5 Specs
Optimal for long-context LLMs, long videos with high resolutions, and batch requests-
1.9x
Faster real-time LLM inference -
6x
Faster data access -
2x
Larger memory
H200 virtual dedicated servers are powered by:
Up to 8 NVIDIA H200 GPUs (141GB, 16896 CUDA cores, 528 Tensor Cores each) in SXM5 form-factor with 4.8TB/s memory bandwidth and 900GB/s P2P bandwidth.
Powered by 4th gen AMD Genoa processors with 384 threads at 3.7GHz boost clock.
The 8H200 VM maintains the same vCPU count as the 4H200 but delivers higher performance by using only physical cores instead of hyper-threads.
| Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
|---|---|---|---|---|---|---|---|---|---|
| 8H200.141S.176V | H200 SXM5 141GB | 8 | 176 | 1450 | 1128 | 900 GB/s | $25.07/h | $24.07/h | $18.80/h |
| 4H200.141S.176V | H200 SXM5 141GB | 4 | 176 | 740 | 564 | 900 GB/s | $12.54/h | $12.04/h | $9.40/h |
| 2H200.141S.88V | H200 SXM5 141GB | 2 | 88 | 370 | 282 | 900 GB/s | $6.27/h | $6.02/h | $4.70/h |
| 1H200.141S.44V | H200 SXM5 141GB | 1 | 44 | 185 | 141 | / | $3.13/h | $3.00/h | $2.35/h |
DataCrunch Cloud
Where speed meets simplicity in GPU solutionsCustomer feedback
What they say about us...
-
Having direct contact between our engineering teams enables us to move incredibly fast. Being able to deploy any model at scale is exactly what we need in this fast moving industry. DataCrunch enables us to deploy custom models quickly and effortlessly.
Iván de Prado Head of AI at Freepik
-
From deployment to training, our entire language model journey was powered by DataCrunch's clusters. Their high-performance servers and storage solutions allowed us to run smooth operations and maximum uptime, and to to focus on achieving exceptional results without worrying about hardware issues.
José Pombal AI Research Scientist at Unbabel
-
DataCrunch powers our entire monitoring and security infrastructure with exceptional reliability. We also enforce firewall restrictions to protect against unauthorized access. Thanks to DataCrunch, our training clusters run smoothly and securely.
Nicola Sosio ML Engineer at Prem AI
GPU clusters tailored to your needs
-
16x H200 Cluster
2x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200 Gbit InfiniBand
100 Gbit ethernet
Uplink 5 Gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
32x H200 Cluster
4x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200 Gbit InfiniBand
100 Gbit ethernet
Uplink 5 Gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
64x H200 Cluster
8x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200 Gbit InfiniBand
100 Gbit ethernet
Uplink 10 Gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
128x H200 Cluster
16x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200 Gbit InfiniBand
100 Gbit ethernet
Uplink 25 Gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s