80GB HBM3 with 900 GB/s NVLink for multi-node training. FP8 Transformer Engine for improved training throughput over A100 . The standard choice for large-scale AI training and high-throughput inference.

When is the H100 not a good fit?

May be more than needed for single-GPU inference on models under 30B parameters. Consider the L40S or A10 for cost-effective inference workloads.

Are H100 prices going up or down?

On-demand pricing has increased by about 18% since June 2025, from $3.25 to $3.84/hr per GPU.

What size AI models can the H100 run?

With 80GB of VRAM, the H100 is well suited to 30B-class models in FP16, and 70B-class models in 4-bit or 8-bit quantized form.

How much VRAM does the H100 have?

The H100 has 80GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the H100's memory bandwidth?

The H100 has 3,350 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the H100 support?

The H100 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8. Scientific: FP64.

Does the H100 support NVLink?

Yes. The H100 supports NVLink with 900 GB/s of bidirectional bandwidth. This helps accelerate multi-GPU communication.

How much does the H100 cost per hour?

H100 pricing currently ranges from $0.60/hr to $14.90/hr per GPU, depending on the provider, instance type, and billing model.

How much does the H100 cost per month?

At 720 hours per month, one H100 can cost between $433.58 to $10,730.24 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the H100?

The H100 is available from 45 cloud providers, including Runpod, Civo, Sesterce. Pricing and availability vary by region and billing model.

Can I rent the H100 in the cloud?

Yes. We currently track 263 H100 listings across 45 cloud providers: Billing type Listings Avg $/GPU/hr On-demand 135 $3.85/hr Reserved 96 $3.35/hr Spot 30 $2.08/hr Custom contract 2 $1.89/hr

Nvidia H100

The standard data center GPU for large-scale AI training and inference.

Compare vs other GPUs →

Aggregating historical prices...

Key Specifications

Architecture

Hopper

Memory

80GB HBM3

Memory Bandwidth

3,350GB/s

Release date

Q3 2022

Compare Cloud Provider Prices

We're tracking 45 cloud providers for the H100, and the pricing spread is significant. While the average sits at $3.45/hr, the lowest price is currently $0.60/hr per GPU (spot instance).

Billing

Max price/hr

Min GPUs

Min vCPUs

Min RAM (GB)

of shown

Default ranking

Our algorithm weighs five factors to find the most relevant matches for you:

Price: We blend total hourly price with price-per-GPU to balance affordability and value.
Specs: We favor offers with higher CPU, RAM, and GPU Memory.
Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.

Sorting and filtering

Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.

Transparency and funding

Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.

Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.

Provider	GPUs	Total VRAM	vCPUs	RAM	Billing	$/GPU/h	Total/h	Availability
Thunder Compute Our sponsor	1x H100 PCIe 1x H100 80GB PCIe (Prototyping)	80GB	4	32GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.38	$1.38	Available	View
Theta EdgeCloud	1x H100 1x H100 80GB (vm_gh1)	80GB	10	80GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.29	$2.29	Available	View
Runpod	1x H100 NVL 1x H100 80GB NVL (community-cloud)	80GB	26	120GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.59	$2.59	Available	View
Novita	1x H100 SXM 1x H100 80GB SXM	80GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$2.59	$2.59	Unknown	View
Lambda Labs	1x H100 PCIe 1x H100 80GB PCIe	80GB	26	225GB	On-Demand Pay-as-you-go pricing. No term commitments.	$3.29	$3.29	Unknown	View
DigitalOcean	1x H100 1x H100 80GB (gpu-h100x1-80gb)	80GB	20	240GB	On-Demand Pay-as-you-go pricing. No term commitments.	$3.39	$3.39	Available	View
Together	1x H100 1x H100 80GB	80GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$3.36	$3.36	Unknown	View
Paperspace	1x H100 1x H100 80GB	80GB	16	268GB	On-Demand Pay-as-you-go pricing. No term commitments.	$5.99	$5.99	Unknown	View
CoreWeave	1x H100 1x H100 80GB	80GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$6.16	$6.16	Available	View
Azure	1x H100 1x H100 80GB (NCadsH100v5)	80GB	40	320GB	On-Demand Pay-as-you-go pricing. No term commitments.	$6.98	$6.98	Available	View
AWS	1x H100 1x H100 80GB (p5.4xlarge)	80GB	16	256GB	On-Demand Pay-as-you-go pricing. No term commitments.	$6.88	$6.88	Available	View
Vultr	8x H100 8x H100 80GB	640GB	216	1.9TB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.99	$23.92	Unknown	View
CUDO	1x H100 1x H100 94GB	94GB	24	--	On-Demand Pay-as-you-go pricing. No term commitments.	$2.47	$2.47	Unknown	View
Runpod	1x H100 SXM 1x H100 80GB SXM (community-cloud)	80GB	26	120GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.69	$2.69	Available	View
Hyperstack	1x H100 1x H100 80GB	80GB	28	180GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.90	$1.90	Unknown	View
Sesterce	1x H100 1x H100 80GB	80GB	28	180GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.09	$2.09	Available	View
UpCloud	1x H100 1x H100 80GB	80GB	12	240GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.08	$2.08	Unknown	View
Civo	1x H100 PCIe 1x H100 80GB PCIe	80GB	32	192GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.49	$2.49	Unknown	View
Koyeb	1x H100 1x H100 80GB	80GB	15	180GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.50	$2.50	Available	View
OVH	1x H100 1x H100 80GB (h100-380)	80GB	30	380GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.99	$2.99	Unknown	View
No offerings matching your filters.

Heads up: We do our best to keep these prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates with the provider before provisioning.

Frequently Asked Questions

Why choose the H100?: 80GB HBM3 with 900 GB/s NVLink for multi-node training. FP8 Transformer Engine for improved training throughput over A100. The standard choice for large-scale AI training and high-throughput inference.
When is the H100 not a good fit?: May be more than needed for single-GPU inference on models under 30B parameters. Consider the L40S or A10 for cost-effective inference workloads.
Are H100 prices going up or down?: On-demand pricing has increased by about 18% since June 2025, from $3.25 to $3.84/hr per GPU.
What size AI models can the H100 run?: With 80GB of VRAM, the H100 is well suited to 30B-class models in FP16, and 70B-class models in 4-bit or 8-bit quantized form.
How much VRAM does the H100 have?: The H100 has 80GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the H100's memory bandwidth?: The H100 has 3,350 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the H100 support?: The H100 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8. Scientific: FP64.
Does the H100 support NVLink?: Yes. The H100 supports NVLink with 900 GB/s of bidirectional bandwidth. This helps accelerate multi-GPU communication.
How much does the H100 cost per hour?: H100 pricing currently ranges from $0.60/hr to $14.90/hr per GPU, depending on the provider, instance type, and billing model.
How much does the H100 cost per month?: At 720 hours per month, one H100 can cost between $433.58 to $10,730.24 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the H100?: The H100 is available from 45 cloud providers, including Runpod, Civo, Sesterce. Pricing and availability vary by region and billing model.
Can I rent the H100 in the cloud?: Yes. We currently track 263 H100 listings across 45 cloud providers:

Billing type Listings Avg $/GPU/hr

On-demand 135 $3.85/hr

Reserved 96 $3.35/hr

Spot 30 $2.08/hr

Custom contract 2 $1.89/hr

Billing type	Listings	Avg $/GPU/hr
On-demand	135	$3.85/hr
Reserved	96	$3.35/hr
Spot	30	$2.08/hr
Custom contract	2	$1.89/hr

Technical Specifications

	H100 SXM	H100 PCIe	H100 NVL
FP64	34 TFLOPS	26 TFLOPS	68 TFLOPS
FP64 Tensor Core	67 TFLOPS	51 TFLOPS	134 TFLOPS
FP32	67 TFLOPS	51 TFLOPS	134 TFLOPS
TF32 Tensor Core	989 TFLOPS	756 TFLOPS	1,979 TFLOPS
BFLOAT16 Tensor Core	1,979 TFLOPS	1,513 TFLOPS	3,958 TFLOPS
FP16 Tensor Core	1,979 TFLOPS	1,513 TFLOPS	3,958 TFLOPS
FP8 Tensor Core	3,958 TFLOPS	3,026 TFLOPS	7,916 TFLOPS
INT8 Tensor Core	3,958 TOPS	3,026 TOPS	7,916 TOPS
GPU Memory	80GB	80GB	188GB
GPU Memory Bandwidth	3.35TB/s	2TB/s	7.8TB/s
Decoders	7 NVDEC, 7 JPEG	7 NVDEC, 7 JPEG	14 NVDEC, 14 JPEG
Max Thermal Design Power (TDP)	Up to 700W	300-350W	2x 350-400W
Multi-Instance GPUs	Up to 7 MIGs @ 10GB each	Up to 7 MIGs @ 10GB each	Up to 14 MIGs @ 12GB each
Form Factor	SXM	PCIe, dual-slot, air-cooled	2x PCIe, dual-slot, air-cooled