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?

The median on-demand price across providers has risen about 12% over the past 90 days, from about $3.02 to $3.39 per GPU per hour.

How much does the H100 cost per month?

At 720 hours per month, one H100 costs about $2,441 at the median on-demand price. Cheapest verified in stock: $1,296 per month on-demand, $1,102 reserved (1 mo), $205 spot.

Which cloud providers offer the H100?

The H100 is listed by 54 providers. Cheapest verified in stock: HyperAI, UpCloud, GPU.ai and Vast.ai.

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. 900 GB/s bidirectional on the SXM, 600 GB/s on the PCIe and NVL.

How much does the H100 cost per hour?

As of August 28, 2026, the median on-demand price is $3.39 per GPU per hour across 39 providers with a priced on-demand listing. On-demand: 157 listings, median $3.39, cheapest in stock $1.80 (HyperAI) Reserved: 166 listings, median $3.03, cheapest in stock $1.53 (1 mo, HyperAI) Spot: 58 listings, median $1.94, cheapest in stock $0.28 (Vast.ai) Custom contract: 8 listings

What H100 variants are there?

The H100 ships in 3 versions with different memory, bandwidth or interconnect. The figures at the top of this page are for the H100 SXM. H100 SXM: 80 GB, 3,350 GB/s, NVLink 900 GB/s H100 PCIe: 80 GB, 2,000 GB/s, NVLink 600 GB/s H100 NVL: 94 GB, 3,900 GB/s, NVLink 600 GB/s

Nvidia H100

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

Last update 11 minutes ago

Compare vs other GPUs →

Jump to: Specs Pricing AI models FAQ Alternatives

Aggregating historical prices...

Key Specifications

Architecture: Hopper
Memory per GPU: 80 GB HBM3 SXM
Memory bandwidth: 3,350 GB/s SXM
GPU interconnect: NVLink 900 GB/s SXM
Release date: Q3 2022

H100 Pricing and Availability

Of 389 listings across 54 cloud providers, 160 are verified in stock. Cheapest of those: on-demand from $1.80 per GPU per hour, spot from $0.28, reservations from $1.53 (1 mo). The median on-demand price is $3.39, up 12% over the past 90 days.

54 providers

How this list works

The two views

By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.

Order

What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.

Within a group, five factors set the order:

Location: datacenter proximity, blended with provider HQ.
Price: hourly price, per GPU and in total.
Billing type: reserved ahead of spot, spot ahead of quote-only.
Specs: more VRAM, vCPUs and RAM.
Provider diversity: a provider's repeat rows rank slightly lower, so one company can't take all the top spots.

Search

We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Lyceum Our sponsor

Germany 9 configs 1x-8x

On-Demand from $2.79 Reserved on request Spot from $1.10

From $2.79 / GPU / hr On-Demand Visit website


1x H100	80GB	20	180GB	Spot	$1.10	$1.10	Out of stock
2x H100	160GB	40	360GB	Spot	$1.10	$2.20	Out of stock
1x H100	80GB	20	180GB	On-Demand	$2.79	$2.79	In stock
4x H100	320GB	80	720GB	Spot	$1.10	$4.40	Out of stock
2x H100	160GB	40	360GB	On-Demand	$2.79	$5.58	Out of stock
8x H100	640GB	160	1.4TB	Spot	$1.10	$8.80	Out of stock
4x H100	320GB	80	720GB	On-Demand	$2.79	$11.16	Out of stock
8x H100	640GB	160	1.4TB	On-Demand	$2.79	$22.32	Out of stock
8x H100	640GB	160	1.4TB	Reservation	Custom	Custom	Not reported

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Runpod In stock

USA 13 configs 1x-8x

On-Demand from $2.59 Reserved on request

From $2.59 / GPU / hr On-Demand NVL Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 NVL Community Cloud	94GB	26	120GB	On-Demand	$2.59	$2.59	In stock
8x H100 SXM Secure Cloud	640GB	208	960GB	Reservation	Custom	Custom	Not reported

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 11 more configs...

Vast.ai In stock

USA 36 configs 1x-8x

On-Demand from $2.27 Reserved from $2.91 Spot from $0.28

From $2.27 / GPU / hr On-Demand SXM Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM JP	80GB	28	252GB	Spot	$0.28	$0.28	In stock
1x H100 SXM CZ	80GB	32	126GB	On-Demand	$2.27	$2.27	In stock
2x H100 SXM CZ	160GB	48	220GB	Reserved (12mo)	$2.91	$5.83	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 33 more configs...

Theta EdgeCloud In stock

USA 3 configs 1x-4x

On-Demand from $2.29

From $2.29 / GPU / hr On-Demand Visit website


1x H100 vm_gh1	80GB	10	80GB	On-Demand	$2.29	$2.29	In stock
2x H100 vm_gh2	160GB	20	160GB	On-Demand	$2.29	$4.58	In stock
4x H100 vm_gh4	320GB	40	320GB	On-Demand	$2.29	$9.16	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Runcrate In stock

USA 1 config 1x

On-Demand from $2.75

From $2.75 / GPU / hr On-Demand SXM Visit website


1x H100 SXM5	80GB	28	180GB	On-Demand	$2.75	$2.75	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Massed Compute In stock

USA 15 configs 1x-8x

On-Demand from $2.73 Spot from $2.45

From $2.73 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 gpu_1x_h100_spot	80GB	20	128GB	Spot	$2.45	$2.45	In stock
1x H100 gpu_1x_h100	80GB	20	128GB	On-Demand	$2.73	$2.73	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 13 more configs...

Novita In stock

USA 20 configs 1x-8x

On-Demand from $3.39 Reserved from $2.79 Spot from $1.70

From $3.39 / GPU / hr On-Demand SXM Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM	80GB	22	150GB	Spot	$1.70	$1.70	In stock
1x H100 SXM	80GB	22	150GB	Reserved (12mo)	$2.79	$2.79	In stock
1x H100 SXM	80GB	22	150GB	On-Demand	$3.39	$3.39	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 17 more configs...

Azure In stock

USA 16 configs 1x-8x

On-Demand from $6.98 Reserved from $4.31 Spot from $1.29

From $6.98 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 NCadsH100v5	80GB	40	320GB	Spot	$1.29	$1.29	In stock
1x H100 NCadsH100v5	80GB	40	320GB	On-Demand	$6.98	$6.98	In stock
2x H100 NCadsH100v5	160GB	80	640GB	Reserved (36mo)	$4.31	$8.61	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 13 more configs...

AWS In stock

USA 6 configs 1x-8x

On-Demand from $6.88 Reserved from $2.97

From $6.88 / GPU / hr On-Demand Visit website


1x H100 p5.4xlarge	80GB	16	256GB	Reserved (36mo)	$2.97	$2.97	In stock
1x H100 p5.4xlarge	80GB	16	256GB	Reserved (12mo)	$5.42	$5.42	In stock
1x H100 p5.4xlarge	80GB	16	256GB	On-Demand	$6.88	$6.88	In stock
8x H100 p5.48xlarge	640GB	192	2.0TB	Reserved (36mo)	$2.97	$23.78	In stock
8x H100 p5.48xlarge	640GB	192	2.0TB	Reserved (12mo)	$5.42	$43.34	In stock
8x H100 p5.48xlarge	640GB	192	2.0TB	On-Demand	$6.88	$55.04	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Thunder Compute In stock

USA 4 configs 1x-8x

On-Demand from $3.20

From $3.20 / GPU / hr On-Demand PCIe Visit website


1x H100 PCIe h100_x1	80GB	4	32GB	On-Demand	$3.20	$3.20	In stock
2x H100 PCIe h100_x2	160GB	8	64GB	On-Demand	$3.20	$6.40	In stock
4x H100 PCIe h100_x4	320GB	60	480GB	On-Demand	$3.20	$12.80	In stock
8x H100 PCIe h100_x8	640GB	120	960GB	On-Demand	$3.20	$25.60	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Oblivus In stock

USA 46 configs 1x-8x

On-Demand from $3.50 Reserved from $2.56

From $3.50 / GPU / hr On-Demand PCIe Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 PCIe H100_PCIE_80GB_x1	80GB	28	180GB	Reserved (36mo)	$2.56	$2.56	Not reported
1x H100 PCIe H100_PCIE_80GB_x1	80GB	28	180GB	On-Demand	$3.50	$3.50	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 44 more configs...

Koyeb In stock

France 4 configs 1x-8x

On-Demand from $2.50

From $2.50 / GPU / hr On-Demand Visit website


1x H100 gpu-nvidia-h100	80GB	15	180GB	On-Demand	$2.50	$2.50	In stock
2x H100 2-gpu-nvidia-h100	160GB	30	360GB	On-Demand	$2.50	$5.00	In stock
4x H100 4-gpu-nvidia-h100	320GB	60	720GB	On-Demand	$2.50	$10.00	In stock
8x H100 8-gpu-nvidia-h100	640GB	120	1.4TB	On-Demand	$2.50	$20.00	Waitlist

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Crusoe In stock

USA 3 configs 8x

On-Demand from $3.90 Reserved on request Spot on request

From $3.90 / GPU / hr On-Demand SXM Visit website


8x H100 SXM h100-80gb-sxm-ib.8x	640GB	176	960GB	On-Demand	$3.90	$31.20	In stock
8x H100 SXM h100-80gb-sxm-ib.8x	640GB	176	960GB	Spot	Custom	Custom	Not reported
8x H100 SXM h100-80gb-sxm-ib.8x	640GB	176	960GB	Reservation	Custom	Custom	Not reported

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Sesterce In stock

France 2 configs 1x

On-Demand from $2.75

From $2.75 / GPU / hr On-Demand Visit website


1x H100	80GB	28	180GB	On-Demand	$2.75	$2.75	In stock
1x H100	80GB	16	268GB	On-Demand	$6.59	$6.59	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Google Cloud In stock

USA 24 configs 1x-8x

On-Demand from $14.19 Reserved from $5.03 Spot from $1.52

From $14.19 / GPU / hr On-Demand SXM Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM a3-highgpu-1g	80GB	26	234GB	Spot	$1.52	$1.52	In stock
2x H100 SXM a3-highgpu-2g	160GB	52	468GB	On-Demand	$14.19	$28.38	In stock
8x H100 SXM a3-megagpu-8g	640GB	208	1.9TB	Reserved (36mo)	$5.03	$40.27	In stock

In stock and Out of stock reflect the last verification. Not reported means we could not confirm availability.

Loading 21 more configs...


1x H100 GPU-SPOT-12xCPU-240GB-1xH100	80GB	12	240GB	Spot	$1.88	$1.88	In stock
1x H100 GPU-12xCPU-240GB-1xH100	80GB	12	240GB	On-Demand	$1.89	$1.89	In stock
2x H100 GPU-SPOT-24xCPU-480GB-2xH100	160GB	24	480GB	Spot	$1.89	$3.77	Out of stock
2x H100 GPU-24xCPU-480GB-2xH100	160GB	24	480GB	On-Demand	$1.89	$3.78	Out of stock
4x H100 GPU-SPOT-48xCPU-960GB-4xH100	320GB	48	960GB	Spot	$1.89	$7.55	Out of stock
4x H100 GPU-48xCPU-960GB-4xH100	320GB	48	960GB	On-Demand	$1.89	$7.56	Out of stock
8x H100 GPU-SPOT-96xCPU-1920GB-8xH100	640GB	96	1.9TB	Spot	$1.89	$15.11	Out of stock
8x H100 GPU-96xCPU-1920GB-8xH100	640GB	96	1.9TB	On-Demand	$1.89	$15.12	Out of stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 PCIe H100-1-80G	80GB	24	240GB	On-Demand	$3.34	$3.34	In stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 PCIe	80GB	--	--	On-Demand	$1.98	$1.98	In stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 PCIe n3-H100x1-bigroot__CANADA-1	80GB	28	180GB	On-Demand	$2.65	$2.65	In stock
8x H100 PCIe n3-H100x8-bigroot-spot__CANADA-1	640GB	252	1.4TB	Spot	$2.20	$17.61	In stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 h100	80GB	16	80GB	Reserved (1mo)	$1.53	$1.53	In stock
1x H100 h100	80GB	16	80GB	On-Demand	$1.80	$1.80	In stock


8x H100 SXM5	640GB	--	2.0TB	Custom	Custom	Custom	In stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x H100 SXM nvidia-h100-8gpu-sxm-80gb-cluster	640GB	--	1.5TB	Custom	Custom	Custom	In stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x H100 SXM 233-H100-36mo	640GB	--	--	Reserved (36mo)	$2.26	$18.08	Waitlist


1x H100 PCIe	80GB	26	200GB	On-Demand	$1.74	$1.74	Not reported
8x H100 SXM	--	--	--	Custom	Custom	Custom	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 HOPPER_H100	80GB	--	--	On-Demand	$3.40	$3.40	Not reported


1x H100 SXM5	80GB	16	32GB	On-Demand	$2.36	$2.36	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM	80GB	--	--	Reserved (6mo)	$3.19	$3.19	Not reported
1x H100 SXM	80GB	--	--	On-Demand	$3.99	$3.99	Not reported


1x H100 PCIe	80GB	--	--	On-Demand	$4.00	$4.00	Not reported


1x H100	80GB	--	--	Custom	$1.89	$1.89	Not reported
1x H100	80GB	--	--	On-Demand	$4.50	$4.50	Not reported


1x H100	80GB	--	--	Reserved (12mo)	$3.26	$3.26	Not reported
1x H100 gpu-h100x1-80gb	80GB	20	240GB	On-Demand	$4.41	$4.41	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 gpu-h100	80GB	13	144GB	On-Demand	$5.49	$5.49	Not reported


1x H100 SXM H100	80GB	20	250GB	On-Demand	$5.95	$5.95	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100	80GB	--	--	Reservation	$1.75	$1.75	Not reported
1x H100 PCIe	80GB	--	--	Spot	$2.00	$2.00	Not reported
1x H100	80GB	28	180GB	On-Demand	$2.50	$2.50	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 h100-380	80GB	30	380GB	On-Demand	$2.99	$2.99	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM	80GB	23	184GB	Reserved (36mo)	$2.49	$2.49	Not reported
1x H100 SXM	80GB	23	184GB	On-Demand	$2.99	$2.99	Not reported


1x H100 SXM NVIDIA HGX H100	80GB	16	200GB	Spot	$2.15	$2.15	Not reported
1x H100 SXM NVIDIA HGX H100	80GB	16	200GB	On-Demand	$3.85	$3.85	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
2x H100 SXM5	160GB	40	400GB	On-Demand	$3.25	$6.50	Not reported


8x H100 SXM	640GB	224	2.0TB	On-Demand	$2.64	$21.15	Not reported


8x H100	640GB	128	2.0TB	Spot	$2.46	$19.71	Not reported
8x H100	640GB	128	2.0TB	On-Demand	$6.16	$49.24	Not reported


1x H100 SXM eg1.h100x1.V24_96	80GB	24	96GB	On-Demand	$4.80	$4.80	Not reported


8x H100 BM.GPU.H100.8	640GB	--	--	On-Demand	$10.00	$80.00	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x H100 SXM 8H100.128v.2048m SXM-12mo	640GB	128	1.5TB	Reserved (12mo)	$2.15	$17.23	Not reported
8x H100 SXM 8H100.128v.2048m SXM	640GB	128	1.5TB	On-Demand	$3.34	$26.71	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100	80GB	36	256GB	Reserved (24mo)	$2.92	$2.92	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x H100	640GB	96	2TB	Reserved (12mo)	$3.47	$27.78	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
4x H100	320GB	128	426GB	Reserved (1mo)	$2.87	$11.48	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
3x H100 PREMIUM_DL385G11-9334-3xH100	240GB	64	128GB	Reserved (1mo)	$1.94	$5.81	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100	80GB	26	250GB	Reserved (12mo)	$3.31	$3.31	Not reported


8x H100	640GB	--	--	Custom	Custom	Custom	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM H100 SXM	80GB	--	--	Custom	Custom	Custom	Not reported

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM gpu_1x_h100	80GB	20	128GB	On-Demand	$3.00	$3.00	Out of stock

Heads up: Prices are estimates from published rates for common setups and vary by region and usage; verify with the provider before provisioning.

What size AI models can the H100 run?

One H100 has 80 GB of HBM3 on the SXM variant. On one card it fits models up to about 113B parameters at 4-bit, and 31B at 16-bit, assuming one request at 32K context.

The table below shows the smallest node that fits. Prices are per month at the median on-demand rate of $3.39 per hour per GPU.

Model	4-bit	8-bit	16-bit
Qwen3.8-27B	1 GPU 25 GB · $2,441/mo	1 GPU 37 GB · $2,441/mo	1 GPU 64 GB · $2,441/mo
Gemma 4 31B	1 GPU 27 GB · $2,441/mo	1 GPU 41 GB · $2,441/mo	1 GPU 71 GB · $2,441/mo
GPT-OSS-120B	2 GPUs 74 GB · $4,882/mo	2 GPUs 127 GB · $4,882/mo	4 GPUs 244 GB · $9,763/mo
DeepSeek V4 Flash	3 GPUs 166 GB · $7,322/mo	8 GPUs 294 GB · $19,526/mo	Needs 9 GPUs 578 GB
GLM-5.3-Flash	3 GPUs 186 GB · $7,322/mo	8 GPUs 330 GB · $19,526/mo	Needs 10 GPUs 650 GB
MiniMax-M3	4 GPUs 245 GB · $9,763/mo	8 GPUs 438 GB · $19,526/mo	Needs 13 GPUs 866 GB
Kimi K3	Needs 22 GPUs 1,550 GB	Needs 40 GPUs 2,810 GB	Needs 78 GPUs 5,610 GB

Estimates, not quotes. Memory is weights plus KV cache at 32K context per request. How we estimate costs.

Lyceum

Our sponsor

NVIDIA H200 from $2.20/hr, B200 from $3.40/hr, B300 from $3.80/hr

Per-second billing with no minimum commitment or vendor lock-in

Scale to 8,000 GPUs over InfiniBand for distributed AI training

Start now

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?: The median on-demand price across providers has risen about 12% over the past 90 days, from about $3.02 to $3.39 per GPU per hour.
How much does the H100 cost per month?: At 720 hours per month, one H100 costs about $2,441 at the median on-demand price. Cheapest verified in stock: $1,296 per month on-demand, $1,102 reserved (1 mo), $205 spot.
Which cloud providers offer the H100?: The H100 is listed by 54 providers. Cheapest verified in stock: HyperAI, UpCloud, GPU.ai and Vast.ai.
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. 900 GB/s bidirectional on the SXM, 600 GB/s on the PCIe and NVL.
How much does the H100 cost per hour?: As of August 28, 2026, the median on-demand price is $3.39 per GPU per hour across 39 providers with a priced on-demand listing.

Billing type Listings Median / GPU / hr Cheapest in stock

On-demand 157 $3.39 $1.80 (HyperAI)

Reserved 166 $3.03 $1.53 (1 mo, HyperAI)

Spot 58 $1.94 $0.28 (Vast.ai)

Custom contract 8
What H100 variants are there?: The H100 ships in 3 versions with different memory, bandwidth or interconnect. The figures at the top of this page are for the H100 SXM.

Variant Memory Memory bandwidth Interconnect

H100 SXM 80 GB 3,350 GB/s NVLink 900 GB/s

H100 PCIe 80 GB 2,000 GB/s NVLink 600 GB/s

H100 NVL 94 GB 3,900 GB/s NVLink 600 GB/s

Technical Specifications

	H100 SXM	H100 PCIe	H100 NVL
FP64	34 TFLOPS	26 TFLOPS	34 TFLOPS
FP64 Tensor Core	67 TFLOPS	51 TFLOPS	67 TFLOPS
FP32	67 TFLOPS	51 TFLOPS	67 TFLOPS
TF32 Tensor Core	989 TFLOPS	756 TFLOPS	989 TFLOPS
BFLOAT16 Tensor Core	1,979 TFLOPS	1,513 TFLOPS	1,979 TFLOPS
FP16 Tensor Core	1,979 TFLOPS	1,513 TFLOPS	1,979 TFLOPS
FP8 Tensor Core	3,958 TFLOPS	3,026 TFLOPS	3,958 TFLOPS
INT8 Tensor Core	3,958 TOPS	3,026 TOPS	3,958 TOPS
GPU Memory	80GB	80GB	94GB
GPU Memory Bandwidth	3.35TB/s	2TB/s	3.9TB/s
Decoders	7 NVDEC, 7 JPEG	7 NVDEC, 7 JPEG	7 NVDEC, 7 JPEG
Max Thermal Design Power (TDP)	Up to 700W	300-350W	350-400W
Multi-Instance GPUs	Up to 7 MIGs @ 10GB each	Up to 7 MIGs @ 10GB each	Up to 7 MIGs @ 12GB each
Form Factor	SXM	PCIe, dual-slot, air-cooled	PCIe, dual-slot, air-cooled (sold as a pair)

Source: official Nvidia H100 datasheet.

Alternatives to Nvidia H100

Nvidia H200

Next generation with 76% more memory. From $1.99/hr per GPU across 38 providers.

Nvidia A100

Previous generation, more affordable. From $0.13/hr per GPU across 42 providers.

AMD MI300X

AMD alternative with 2.4x more memory. From $1.45/hr per GPU across 10 providers.

Nvidia RTX 5090

Consumer gaming GPU. From $0.11/hr per GPU across 18 providers.

Nvidia V100

Previous generation Volta GPU. From $0.10/hr per GPU across 21 providers.

Last updated Aug. 28, 2026

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 SXM5 1H100.80S.30V	80GB	30	120GB	Spot	$1.62	$1.62	Out of stock
1x H100 SXM5 1H100.80S.30V	80GB	30	120GB	Reserved (24mo)	$2.44	$2.44	Out of stock
1x H100 SXM5 1H100.80S.30V	80GB	30	120GB	On-Demand	$3.25	$3.25	Out of stock

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x H100 g3-h100-small-12mo	80GB	16	192GB	Reserved (12mo)	$1.18	$1.18	Out of stock
1x H100 g3-h100-small	80GB	16	192GB	On-Demand	$3.37	$3.37	Out of stock

Billing type	Listings	Median / GPU / hr	Cheapest in stock
On-demand	157	$3.39	$1.80 (HyperAI)
Reserved	166	$3.03	$1.53 (1 mo, HyperAI)
Spot	58	$1.94	$0.28 (Vast.ai)
Custom contract	8

Variant	Memory	Memory bandwidth	Interconnect
H100 SXM	80 GB	3,350 GB/s	NVLink 900 GB/s
H100 PCIe	80 GB	2,000 GB/s	NVLink 600 GB/s
H100 NVL	94 GB	3,900 GB/s	NVLink 600 GB/s

Key Specifications

H100 Pricing and Availability

How this list works

The two views

Order

Search

Transparency and funding

Lyceum Our sponsor

Runpod In stock

Vast.ai In stock

Theta EdgeCloud In stock

Runcrate In stock

Massed Compute In stock

Novita In stock

Azure In stock

AWS In stock

Thunder Compute In stock

Oblivus In stock

Koyeb In stock

Crusoe In stock

Sesterce In stock

Google Cloud In stock

UpCloud In stock

Scaleway In stock

GPU.ai In stock

Spheron In stock

HyperAI In stock

GPUaaS In stock

Packet·ai In stock

Impossible Cloud Waitlist

Geodd Out of stock

Lambda Labs Out of stock

Verda Out of stock

Latitude.sh Out of stock

Vultr Out of stock

What size AI models can the H100 run?

Frequently Asked Questions

Why choose the H100?

When is the H100 not a good fit?

Are H100 prices going up or down?

How much does the H100 cost per month?

Which cloud providers offer the H100?

What data types does the H100 support?

Does the H100 support NVLink?

How much does the H100 cost per hour?

What H100 variants are there?

Technical Specifications

Alternatives to Nvidia H100

Nvidia H200

Nvidia A100

AMD MI300X

Nvidia RTX 5090

Nvidia V100