What an H100 costs per hour in October 2026, and what the price leaves out

We read eleven price lists on the same day. The spread is real, but a good part of it pays for things an inference server doesn't use.

Five clouds drawn as lines that join into one route, ending at a single chosen setup marked in vermilion

H100 prices on 5 October 2026#

We read each provider's public price list or pricing API on the same day. Where a provider only sells eight-GPU machines, we divided the machine's price by eight.

ProviderWhat you rentPer GPU-hourNote
Vast.aisingle GPUs from independent hosts$1.80marketplace median; lowest $1.73
RunPod Community Cloudone GPU or more$2.69
Hyperstackone GPU or more$3.20
RunPod Secure Cloudone GPU or more$3.49
Verda1, 2, 4 or 8 GPUs$3.77$3.37 on 22 September
Lambda8-GPU instance$3.99$4.29 for a single GPU
Nebiusone GPU or more$4.50$3.85 until 1 October
CoreWeave8-GPU node$6.16North America
AWSp5.48xlarge (8 GPUs) or p5.4xlarge (1 GPU)$6.88us-east-1
Google Clouda3-highgpu-8g (8 GPUs)$11.06us-central1 price table
AzureND96isr H100 v5 (8 GPUs)$12.29East US

H100 80GB SXM, on-demand list price per GPU-hour, 5 October 2026

H100 80GB SXM, on-demand list price per GPU-hour, 5 October 2026
ProviderBarUSD per GPU-hour
Vast.ai marketplace median$1.80
RunPod Community$2.69
Hyperstack$3.20
RunPod Secure$3.49
Verda$3.77
Lambda 8-GPU instance$3.99
Nebius$4.50
CoreWeave 8-GPU node$6.16
AWS us-east-1$6.88
Google Cloud us-central1$11.06
Azure East US$12.29
Blue: specialist GPU clouds. Grey: hyperscalers. Light blue: Vast.ai marketplace median. Eight-GPU instance prices divided by eight. Sources are listed at the end of the post.

Azure's rate is 4.6 times RunPod Community's. Even the cheapest hyperscaler, AWS, charges more than every specialist cloud we checked. Every row rents the same NVIDIA H100 SXM, so the gap is in what surrounds the chip: the machine it comes in, the network, the contract and the support. Some of that is worth paying for. For serving one model, much of it isn't.

Why the hyperscalers charge two to three times more#

AWS, Google Cloud and Azure sell their H100s mainly as eight-GPU machines designed for training across many machines at once. The price covers high-bandwidth networking between those machines, plus the rest of the cloud: identity and access controls, private networking, compliance programmes and the support contract you may already have.

A model served from one machine never uses the network between machines. Two H100s in the same server talk over NVLink inside the box.

Hyperscaler list prices also assume you will commit. One year takes 31 to 37% off; three years takes about 56%:

ProviderOn-demand1-year commitment3-year commitment
AWS (EC2 Instance Savings Plan, no upfront)$6.88$4.33$2.97
Google Cloud (resource commitment)$11.06$7.67$4.86
Azure (reserved VM instance)$12.29$7.87$5.40

A three-year AWS commitment lands within 28 cents of the cheapest on-demand H100 we found. That is a good deal if your load is steady, you already spend with AWS, and you are confident an H100 will still be the right GPU for your model in 2029. AWS also cut on-demand P5 prices by up to 45% in June 2025, so $6.88 is already the reduced rate.

SXM, PCIe and NVL are different products#

"H100" covers three cards with different memory and bandwidth:

H100 variantMemoryMemory bandwidthLowest on-demand price we found
SXM80 GB3.35 TB/s$2.69 (RunPod Community)
PCIe80 GB2.0 TB/s$1.99 (RunPod Community)
NVL94 GB3.9 TB/s$2.59 (RunPod Community)

Each generated token requires reading the model's weights from memory, so for a single stream of text the speed limit is memory bandwidth rather than compute. NVIDIA's inference guide walks through why. Per unit of bandwidth, the SXM card is the better buy: $2.69 for 3.35 TB/s works out at $0.80 per TB/s-hour, against $1.00 for the PCIe card at $1.99.

The NVL's extra 14 GB matters in one common case. A 70B model at FP8 loads on an 80 GB card with almost nothing left over for users' conversations; on 94 GB it has room to work. We did the arithmetic in how much GPU memory a 70B model needs.

Costs the hourly rate leaves out#

Egress#

ProviderInternet egress
AWS (us-east-1)first 100 GB a month free, then $0.09 per GB
Azure (East US)first 100 GB free, then $0.087 per GB
Google Cloud (Premium tier)first 1 GiB free, then $0.12 per GiB ($0.11 above 1 TiB)
Lambda, RunPod, CoreWeave, Nebius, Hyperstackfree

Sending 10 TB a month costs about $891 on AWS, $861 on Azure and $1,035 on Google Cloud's Premium tier, and nothing at the five specialist clouds above.

For a text endpoint, egress is usually small. Each streamed token arrives as a small JSON event of very roughly 100 to 200 bytes, so a billion streamed tokens is around 100 to 200 GB: $9 to $18 at AWS's rate. It adds up when you move other data out: embeddings, generated images or audio, logs shipped elsewhere, or traffic between an application on one cloud and GPUs on another.

Storage#

A 70B model at FP8 is about 73 GB on disk. At $0.07 to $0.10 per GB a month at most providers, and $0.20 at Lambda and Verda, keeping it costs $5 to $15 a month. It won't decide anything.

Billing increments#

  • Per second: AWS (60-second minimum), Google Cloud (1-minute minimum), RunPod, Nebius and Vast.ai.
  • Per minute: Azure, Lambda and Hyperstack.
  • Prepaid 10-minute blocks: Verda, with unused time refunded.

This matters if you add and remove replicas through the day. For a server that runs around the clock, it doesn't.

The smallest unit you can rent#

Several offerings come only as whole eight-GPU machines: AWS's H200 and B200 instances, Google Cloud's A3 Ultra and A4, Azure's ND H100 v5 and H200 v5, and CoreWeave's on-demand nodes. If your model needs two GPUs and you rent eight at $6.88 each, you pay $55.04 an hour and six GPUs sit idle unless you pack other work onto them. AWS does sell a single H100 (p5.4xlarge) at the same per-GPU rate. Lambda, RunPod, Verda, Hyperstack and Vast.ai rent single GPUs.

Rent the smallest unit that holds the model and its cache.

Spot and preemptible prices#

ProviderSpot or preemptible H100Below on-demand by
AWS (p5.48xlarge, us-east-1, read at 16:26 UTC)$3.2054%
Google Cloud (a3-highgpu-8g)$6.2943%
Azure (ND96isr H100 v5, East US)$2.2782%
CoreWeave$2.4660%
Verda$1.8950%
Together AI (GPU clusters)$1.9950%

Spot capacity can be taken back at short notice. It suits batch work such as evaluations, embeddings and offline generation. For an endpoint people are waiting on, use it only behind a fallback that can absorb the traffic when machines disappear.

Prices rose this autumn#

  • Nebius raised on-demand prices on 1 October: H100 by 17% ($3.85 to $4.50), H200 by 20% and B200 by 19%.
  • AWS announced a 15% rise in EC2 Capacity Block prices from 7 October, taking a P5 H100 from $5.19 to $5.97 per GPU-hour.
  • Verda's H100 went from $3.37 on 22 September to $3.77 on 5 October, up 12% in 13 days, according to the Wayback Machine's captures of its price page.

Any price survey goes stale within weeks, this one included. For today's number, live trackers such as gpufinder.dev, which polls 22 vendors every hour, and SkyPilot's GPU Compass are better sources. A survey is more useful for explaining what the number buys.

What we would rent for inference this month#

  • One model on one or two GPUs, steady traffic: single or paired H100 SXM GPUs at a specialist cloud such as Hyperstack ($3.20), RunPod Secure ($3.49) or Verda ($3.77). Check capacity in your region first. A list price says nothing about whether the GPU is free to rent.
  • Already on a hyperscaler with credits or compliance requirements: stay, but commit. Three years on AWS is $2.97 per GPU-hour, and the single-GPU p5.4xlarge saves you from renting eight.
  • Experiments and batch jobs: Vast.ai or spot capacity, with checkpoints so a lost machine costs minutes instead of a whole run.
  • A model that needs more than 80 GB per GPU: price one H200 ($3.59 to $10.60 on-demand) against a pair of H100s before reaching for an eight-GPU machine.

The lowest rate on the list is rarely the cheapest deployment. A GPU that sits idle half the day costs twice its hourly rate per useful hour, which is the subject of whether renting GPUs beats paying per token.

This comparison is what our configurator runs for each workload: price and capacity across these providers for the GPU the model needs, ranked so you can choose where it runs. After it's deployed, we tell you when a faster or cheaper option appears, and whether to move is your call. We own no GPUs and favour no provider.

How we worked this out#

Sources#

All accessed 5 October 2026.

Frequently asked questions

How much does an H100 cost per hour in October 2026?
On 5 October 2026, on-demand list prices for one H100 80GB SXM ranged from $2.69 (RunPod Community Cloud) to $12.29 (Azure, East US) per GPU-hour. Five specialist GPU clouds charged between $3.20 and $4.50. AWS charged $6.88 and Google Cloud $11.06. The Vast.ai marketplace median was $1.80.
Why is an H100 on Azure or Google Cloud so much more expensive?
Their H100s are sold mainly as eight-GPU machines built for multi-node training, with high-bandwidth networking between machines, and their list prices assume you will commit. A three-year commitment takes about 56% off at all three hyperscalers, which brings AWS to $2.97 and Azure to $5.40 per GPU-hour.
Is a PCIe H100 as good as an SXM H100 for inference?
Not per dollar of memory bandwidth, which is what limits token generation. The PCIe card has 2.0 TB/s against 3.35 TB/s for the SXM card. At RunPod Community Cloud prices the SXM card costs $0.80 per TB/s-hour and the PCIe card $1.00.
Do GPU clouds charge for egress?
The hyperscalers do: $0.09 per GB on AWS, $0.087 per GB on Azure and $0.12 per GiB on Google Cloud's Premium tier, after a small free allowance. Lambda, RunPod, CoreWeave, Nebius and Hyperstack list internet egress as free.
Are GPU prices going down?
Not this autumn. Nebius raised on-demand prices on 1 October 2026 (H100 from $3.85 to $4.50), AWS announced a 15% rise in Capacity Block prices from 7 October, and Verda's H100 rose from $3.37 to $3.77 between 22 September and 5 October.