H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 0.1083/minute compute time
Component price — not a total
H100 standard
scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions
H100
45 offerings from 18 providers across serverless products and GPU instances.
60 complete comparable prices; incomplete and additive prices remain visible but are not ranked as totals.
12 of 16 serverless offerings include a scale-to-zero operating mode.
Published configurations: 80 GB
Serverless prices
All serverless GPUs →| GPU | Provider | Plan | Price | Location |
|---|---|---|---|---|
| H100 80 GB VRAM/GPU · fixed | Baseten.co H100 | H100 standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | ||||
| 1× H100 80 GB VRAM/GPU · fixed | Beam.cloud H100 | Standard serverless scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless section includes a “With committed spend” / “Book a call” option without a published amount; it was omitted. | ||||
| 1× H100 VRAM unknown · fixed | Cerebrium H100 | Standard scale-to-zero scale to zero 1 second increments |
Component price — not a total | unknown |
| Enterprise pricing is listed as Custom and was omitted. 1 geography evidence item
| ||||
| 1× H100 VRAM unknown · fixed | Cerebrium H100 | Standard scale to zero 1 second increments · bills active compute time |
Component price — not a total | EU compute EU-constrained Sweden |
| Enterprise pricing is listed as Custom and was omitted. 3 geography evidence items
| ||||
| 1× H100 80 GB VRAM/GPU · fixed | Fal.ai H100 | Always on always on 1 second increments · bills setup, idle, running, draining, terminating |
| unknown |
| Scale to zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
| |||
| The source lists discounted “As low as” prices, but those custom deployment prices are omitted because the terms require sales contact. | ||||
| 2× H100 80 GB VRAM/GPU · fixed | Koyeb 2x H100 | always-on always on 1 second increments · bills running |
| unknown |
| scale-to-zero scale to zero 1 second increments · bills running |
| |||
1 geography evidence item
| ||||
| 4× H100 80 GB VRAM/GPU · fixed | Koyeb 4x H100 | always-on always on 1 second increments · bills running |
| unknown |
| scale-to-zero scale to zero 1 second increments · bills running |
| |||
1 geography evidence item
| ||||
| 8× H100 80 GB VRAM/GPU · fixed | Koyeb 8x H100 | always-on always on 1 second increments · bills running |
| unknown |
| scale-to-zero scale to zero 1 second increments · bills running |
| |||
1 geography evidence item
| ||||
| 1× H100 80 GB VRAM/GPU · fixed | Koyeb H100 | always-on always on 1 second increments · bills running |
| unknown |
| scale-to-zero scale to zero 1 second increments · bills running |
| |||
1 geography evidence item
| ||||
| 1× H100 VRAM unknown · fixed | Modal Nvidia H100 SXM5 | Broad region scale to zero none minimum · bills running |
Component price — not a total | unknown |
| Narrow region scale to zero none minimum · bills running |
Component price — not a total | |||
| Standard scale to zero none minimum · bills running |
Component price — not a total | |||
5 geography evidence items
| ||||
| 1× H100 80 GB VRAM/GPU · fixed | OVHcloud h100-1-gpu | always-on always on · dedicated 1 minute increments · bills SCALING, RUNNING |
| unknown |
| scale-to-zero scale to zero · dedicated 1 minute increments · bills SCALING, RUNNING |
| |||
| | ||||
| 1× H100 80 GB VRAM/GPU · fixed | Replicate Nvidia H100 GPU | Public models request metered bills request execution time |
| unknown |
| | ||||
| 2× H100 80 GB VRAM/GPU · fixed | Replicate 2x Nvidia H100 GPU | Public models request metered · commitment bills request execution time |
| unknown |
| | ||||
| 4× H100 80 GB VRAM/GPU · fixed | Replicate 4x Nvidia H100 GPU | Public models request metered · commitment bills request execution time |
| unknown |
| | ||||
| 8× H100 80 GB VRAM/GPU · fixed | Replicate 8x Nvidia H100 GPU | Public models request metered · commitment bills request execution time |
| unknown |
| | ||||
| 1× H100 80 GB VRAM/GPU · fixed | Runpod H100 | Flex scale to zero 1 second increments · bills initialization, execution, idle timeout |
| unknown |
| Active workers have discounts available through sales inquiry; no public price is published, so Active variants were omitted. | ||||
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 0.0000125/core second cpu core time
- USD 0.000972/second gpu time
- USD 0.0000021/gib second memory time
Component price — not a total
Standard serverless
scale to zero 1 ms increments · bills code running
The Serverless section includes a “With committed spend” / “Book a call” option without a published amount; it was omitted.
1× H100 · VRAM unknown
H100 · Serverless · fixed
- USD 0.00000655/core second cpu core time
- USD 0.000944/second gpu time
- USD 0.00000222/gb second memory time
Component price — not a total
Standard scale-to-zero
scale to zero 1 second increments
Enterprise pricing is listed as Custom and was omitted.
1 geography evidence item
- compute · constrainable · supported Regions: eu-north-1Official geography evidence (opens in new tab)
1× H100 · VRAM unknown
H100 · Serverless · fixed
- USD 0.00000655/core second cpu core time
- USD 0.000944/second gpu time
- USD 0.00000222/gb second memory time
Component price — not a total
Standard
scale to zero 1 second increments · bills active compute time
EU compute EU-constrained
Sweden
Enterprise pricing is listed as Custom and was omitted.
3 geography evidence items
-
Accepted variant · Stockholm · Sweden (SE)
EU member · reviewed 2026-07-19Official region evidence (opens in new tab)
-
Offering availability · eu-north-1 · available The current GPU matrix lists HOPPER_H100 in Stockholm; capacity is not guaranteed.Official offering availability evidence (opens in new tab)
- compute · constrainable · supported Regions: eu-north-1Official geography evidence (opens in new tab)
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 4.5/hour compute time
Always on
always on 1 second increments · bills setup, idle, running, draining, terminating
The source lists discounted “As low as” prices, but those custom deployment prices are omitted because the terms require sales contact.
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 4.5/hour compute time
Scale to zero
scale to zero 1 second increments · bills setup, idle, running, draining, terminating
The source lists discounted “As low as” prices, but those custom deployment prices are omitted because the terms require sales contact.
2× H100 · 80 GB VRAM/GPU
2x H100 · Serverless · fixed
- USD 5/hour compute time
always-on
always on 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
2× H100 · 80 GB VRAM/GPU
2x H100 · Serverless · fixed
- USD 5/hour compute time
scale-to-zero
scale to zero 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
4× H100 · 80 GB VRAM/GPU
4x H100 · Serverless · fixed
- USD 10/hour compute time
always-on
always on 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
4× H100 · 80 GB VRAM/GPU
4x H100 · Serverless · fixed
- USD 10/hour compute time
scale-to-zero
scale to zero 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
8× H100 · 80 GB VRAM/GPU
8x H100 · Serverless · fixed
- USD 20/hour compute time
always-on
always on 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
8× H100 · 80 GB VRAM/GPU
8x H100 · Serverless · fixed
- USD 20/hour compute time
scale-to-zero
scale to zero 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 2.5/hour compute time
always-on
always on 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 2.5/hour compute time
scale-to-zero
scale to zero 1 second increments · bills running
1 geography evidence item
- compute · constrainable · supported Regions: fraOfficial geography evidence (opens in new tab)
1× H100 · VRAM unknown
Nvidia H100 SXM5 · Serverless · fixed
- USD 0.0000131/core second → USD 0.00001507/core second effective cpu core time
- USD 0.001097/second → USD 0.001262/second effective gpu time
- USD 0.00000222/gib second → USD 0.000002553/gib second effective memory time
Component price — not a total
Broad region
scale to zero none minimum · bills running
5 geography evidence items
- compute · available · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- compute · constrainable · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- request routing · available · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- request routing · constrainable · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- transient object storage · constrainable · unsupported Official geography evidence (opens in new tab)
1× H100 · VRAM unknown
Nvidia H100 SXM5 · Serverless · fixed
- USD 0.0000131/core second → USD 0.00002293/core second effective cpu core time
- USD 0.001097/second → USD 0.00192/second effective gpu time
- USD 0.00000222/gib second → USD 0.000003885/gib second effective memory time
Component price — not a total
Narrow region
scale to zero none minimum · bills running
5 geography evidence items
- compute · available · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- compute · constrainable · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- request routing · available · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- request routing · constrainable · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- transient object storage · constrainable · unsupported Official geography evidence (opens in new tab)
1× H100 · VRAM unknown
Nvidia H100 SXM5 · Serverless · fixed
- USD 0.0000131/core second cpu core time
- USD 0.001097/second gpu time
- USD 0.00000222/gib second memory time
Component price — not a total
Standard
scale to zero none minimum · bills running
5 geography evidence items
- compute · available · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- compute · constrainable · supported Regions: eu, eu-west, eu-north, eu-southOfficial geography evidence (opens in new tab)
- request routing · available · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- request routing · constrainable · supported Regions: eu-westOfficial geography evidence (opens in new tab)
- transient object storage · constrainable · unsupported Official geography evidence (opens in new tab)
1× H100 · 80 GB VRAM/GPU
h100-1-gpu · Serverless · fixed
- USD 3.39/hour compute time
always-on
always on · dedicated 1 minute increments · bills SCALING, RUNNING
1× H100 · 80 GB VRAM/GPU
h100-1-gpu · Serverless · fixed
- USD 3.39/hour compute time
scale-to-zero
scale to zero · dedicated 1 minute increments · bills SCALING, RUNNING
1× H100 · 80 GB VRAM/GPU
Nvidia H100 GPU · Serverless · fixed
- USD 0.001525/second compute time
Public models
request metered bills request execution time
2× H100 · 80 GB VRAM/GPU
2x Nvidia H100 GPU · Serverless · fixed
- USD 0.00305/second compute time
Public models
request metered · commitment bills request execution time
4× H100 · 80 GB VRAM/GPU
4x Nvidia H100 GPU · Serverless · fixed
- USD 0.0061/second compute time
Public models
request metered · commitment bills request execution time
8× H100 · 80 GB VRAM/GPU
8x Nvidia H100 GPU · Serverless · fixed
- USD 0.0122/second compute time
Public models
request metered · commitment bills request execution time
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
- USD 4.79/hour gpu time
Flex
scale to zero 1 second increments · bills initialization, execution, idle timeout
Active workers have discounts available through sales inquiry; no public price is published, so Active variants were omitted.
Instance prices
All GPU instances →| Provider | Instance | VRAM/GPU | vCPUs | RAM | Storage | Region | Variant | Price | Verified |
|---|---|---|---|---|---|---|---|---|---|
| OVHcloud | h100-380 H100 80 GB | 80 GB | 30 | 380 GB | 4040 GB | Gravelines FR · gra · EU | Gravelines on-demand standard |
| |
| Scaleway | H100-1-80G NVIDIA H100-PCIe | 80 GB | 24 | 240 GB | 3000 GB | Warsaw PL · pl-waw-2 · EU | PL-WAW-2 on-demand standard |
| |
| Scaleway | H100-1-80G NVIDIA H100-PCIe | 80 GB | 24 | 240 GB | 3000 GB | Paris FR · fr-par-2 · EU | FR-PAR-2 on-demand standard |
| |
| OVHcloud | h100-760 H100 80 GB | 80 GB | 60 | 760 GB | 4040 GB | Gravelines FR · gra · EU | Gravelines on-demand standard |
| |
| Scaleway | H100-2-80G NVIDIA H100-PCIe | 80 GB | 48 | 480 GB | 6000 GB | Warsaw PL · pl-waw-2 · EU | PL-WAW-2 on-demand standard |
| |
| Scaleway | H100-2-80G NVIDIA H100-PCIe | 80 GB | 48 | 480 GB | 6000 GB | Paris FR · fr-par-2 · EU | FR-PAR-2 on-demand standard |
| |
| Scaleway | H100-SXM-2-80G NVIDIA H100-SXM | 80 GB | 32 | 240 GB | 3200 GB | Paris FR · fr-par-2 · EU | FR-PAR-2 on-demand standard |
| |
| OVHcloud | h100-1520 H100 80 GB | 80 GB | 120 | 1520 GB | 4040 GB | Gravelines FR · gra · EU | Gravelines on-demand standard |
| |
| Scaleway | H100-SXM-4-80G NVIDIA H100-SXM | 80 GB | 64 | 480 GB | 6400 GB | Paris FR · fr-par-2 · EU | FR-PAR-2 on-demand standard |
| |
| Verda | 1× H100 SXM5 · 80 GB/GPU · 30 vCPU / 120 GB RAM H100 SXM5 | 80 GB | 30 | 120 GB | unknown | unknown | Spot spot |
| |
| Verda | 1× H100 SXM5 · 80 GB/GPU · 32 vCPU / 170 GB RAM H100 SXM5 | 80 GB | 32 | 170 GB | unknown | unknown | Spot spot |
| |
| Nebius | NVIDIA H100 · 1 GPU / 16 vCPU / 200 GiB NVIDIA H100 | 80 GB | 16 | 200 GB | unknown | Finland FI · eu-north1 · EU | eu-north1 preemptible spot |
| |
| Lambda | 1× NVIDIA H100 PCIe NVIDIA H100 PCIe | 80 GB | 26 | 225 GB | 1024 GB | unknown | On-demand standard |
| |
| Verda | 1× H100 SXM5 · 80 GB/GPU · 30 vCPU / 120 GB RAM H100 SXM5 | 80 GB | 30 | 120 GB | unknown | unknown | On-demand standard |
| |
| Verda | 1× H100 SXM5 · 80 GB/GPU · 32 vCPU / 170 GB RAM H100 SXM5 | 80 GB | 32 | 170 GB | unknown | unknown | On-demand standard |
| |
| Nebius | NVIDIA H100 · 1 GPU / 16 vCPU / 200 GiB NVIDIA H100 | 80 GB | 16 | 200 GB | unknown | Finland FI · eu-north1 · EU | eu-north1 on-demand standard |
| |
| Lambda | 1× NVIDIA H100 SXM NVIDIA H100 SXM | 80 GB | 26 | 225 GB | 2816 GB | unknown | On-demand standard |
| |
| DigitalOcean | NVIDIA H100 | 80 GB | 20 | 240 GB | 5120 GB | unknown | On-demand standard |
| |
| Paperspace | H100 NVIDIA HGX H100 | 80 GB | 20 | 250 GB | unknown | New York City, New York US · ny2 | NY2 on-demand standard |
| |
| Lambda | 2× NVIDIA H100 SXM NVIDIA H100 SXM | 80 GB | 52 | 450 GB | 5632 GB | unknown | On-demand standard |
| |
| Lambda | 4× NVIDIA H100 SXM NVIDIA H100 SXM | 80 GB | 104 | 900 GB | 11264 GB | unknown | On-demand standard |
| |
| Nebius | NVIDIA H100 · 8 GPU / 128 vCPU / 1600 GiB NVIDIA H100 | 80 GB | 128 | 1600 GB | unknown | Finland FI · eu-north1 · EU | eu-north1 preemptible spot |
| |
| CoreWeave | NVIDIA HGX H100 | 80 GB | 128 | 2048 GB | 62914.56 GB | europe | Europe spot spot |
| |
| CoreWeave | NVIDIA HGX H100 | 80 GB | 128 | 2048 GB | 62914.56 GB | north-america | North America spot spot |
| |
| Nebius | NVIDIA H100 · 8 GPU / 128 vCPU / 1600 GiB NVIDIA H100 | 80 GB | 128 | 1600 GB | unknown | Finland FI · eu-north1 · EU | eu-north1 on-demand standard |
| |
| Lambda | 8× NVIDIA H100 SXM NVIDIA H100 SXM | 80 GB | 208 | 1800 GB | 22528 GB | unknown | On-demand standard |
| |
| DigitalOcean | NVIDIA H100 · 8 GPU NVIDIA H100 | 80 GB | 160 | 1920 GB | 40960 GB | unknown | On-demand standard |
| |
| CoreWeave | NVIDIA HGX H100 | 80 GB | 128 | 2048 GB | 62914.56 GB | north-america | North America on-demand standard |
| |
| CoreWeave | NVIDIA HGX H100 | 80 GB | 128 | 2048 GB | 62914.56 GB | europe | Europe on-demand standard |
|
h100-380
1× H100
80 GB VRAM/GPU · 30 vCPUs · 380 GB RAM · 4040 GB storage
Region: Gravelines · FR · gra · EU
- EUR 2.8/hour compute time
Gravelines on-demand
standard H100-1-80G
1× H100
80 GB VRAM/GPU · 24 vCPUs · 240 GB RAM · 3000 GB storage
Region: Warsaw · PL · pl-waw-2 · EU
- EUR 2.867/hour compute time
PL-WAW-2 on-demand
standard H100-1-80G
1× H100
80 GB VRAM/GPU · 24 vCPUs · 240 GB RAM · 3000 GB storage
Region: Paris · FR · fr-par-2 · EU
- EUR 2.867/hour compute time
FR-PAR-2 on-demand
standard h100-760
2× H100
80 GB VRAM/GPU · 60 vCPUs · 760 GB RAM · 4040 GB storage
Region: Gravelines · FR · gra · EU
- EUR 5.6/hour compute time
Gravelines on-demand
standard H100-2-80G
2× H100
80 GB VRAM/GPU · 48 vCPUs · 480 GB RAM · 6000 GB storage
Region: Warsaw · PL · pl-waw-2 · EU
- EUR 5.733/hour compute time
PL-WAW-2 on-demand
standard H100-2-80G
2× H100
80 GB VRAM/GPU · 48 vCPUs · 480 GB RAM · 6000 GB storage
Region: Paris · FR · fr-par-2 · EU
- EUR 5.733/hour compute time
FR-PAR-2 on-demand
standard H100-SXM-2-80G
2× H100
80 GB VRAM/GPU · 32 vCPUs · 240 GB RAM · 3200 GB storage
Region: Paris · FR · fr-par-2 · EU
- EUR 6.62/hour compute time
FR-PAR-2 on-demand
standard h100-1520
4× H100
80 GB VRAM/GPU · 120 vCPUs · 1520 GB RAM · 4040 GB storage
Region: Gravelines · FR · gra · EU
- EUR 11.2/hour compute time
Gravelines on-demand
standard H100-SXM-4-80G
4× H100
80 GB VRAM/GPU · 64 vCPUs · 480 GB RAM · 6400 GB storage
Region: Paris · FR · fr-par-2 · EU
- EUR 12.77/hour compute time
FR-PAR-2 on-demand
standard 1× H100 SXM5 · 80 GB/GPU · 30 vCPU / 120 GB RAM
1× H100
80 GB VRAM/GPU · 30 vCPUs · 120 GB RAM · storage unknown
Region: unknown
- USD 1.81/hour compute time
Spot
spot 1× H100 SXM5 · 80 GB/GPU · 32 vCPU / 170 GB RAM
1× H100
80 GB VRAM/GPU · 32 vCPUs · 170 GB RAM · storage unknown
Region: unknown
- USD 1.81/hour compute time
Spot
spot NVIDIA H100 · 1 GPU / 16 vCPU / 200 GiB
1× H100
80 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
- USD 2.15/hour compute time
eu-north1 preemptible
spot 1× NVIDIA H100 PCIe
1× H100
80 GB VRAM/GPU · 26 vCPUs · 225 GB RAM · 1024 GB storage
Region: unknown
- USD 3.29/hour compute time
On-demand
standard 1× H100 SXM5 · 80 GB/GPU · 30 vCPU / 120 GB RAM
1× H100
80 GB VRAM/GPU · 30 vCPUs · 120 GB RAM · storage unknown
Region: unknown
- USD 3.63/hour compute time
On-demand
standard 1× H100 SXM5 · 80 GB/GPU · 32 vCPU / 170 GB RAM
1× H100
80 GB VRAM/GPU · 32 vCPUs · 170 GB RAM · storage unknown
Region: unknown
- USD 3.63/hour compute time
On-demand
standard NVIDIA H100 · 1 GPU / 16 vCPU / 200 GiB
1× H100
80 GB VRAM/GPU · 16 vCPUs · 200 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
- USD 3.85/hour compute time
eu-north1 on-demand
standard 1× NVIDIA H100 SXM
1× H100
80 GB VRAM/GPU · 26 vCPUs · 225 GB RAM · 2816 GB storage
Region: unknown
- USD 4.29/hour compute time
On-demand
standard NVIDIA H100
1× H100
80 GB VRAM/GPU · 20 vCPUs · 240 GB RAM · 5120 GB storage
Region: unknown
- USD 4.41/hour compute time
On-demand
standard H100
1× H100
80 GB VRAM/GPU · 20 vCPUs · 250 GB RAM · storage unknown
Region: New York City, New York · US · ny2
- USD 5.95/hour compute time
NY2 on-demand
standard 2× NVIDIA H100 SXM
2× H100
80 GB VRAM/GPU · 52 vCPUs · 450 GB RAM · 5632 GB storage
Region: unknown
- USD 4.19/hour → USD 8.38/hour effective compute time
On-demand
standard 4× NVIDIA H100 SXM
4× H100
80 GB VRAM/GPU · 104 vCPUs · 900 GB RAM · 11264 GB storage
Region: unknown
- USD 4.09/hour → USD 16.36/hour effective compute time
On-demand
standard NVIDIA H100 · 8 GPU / 128 vCPU / 1600 GiB
8× H100
80 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
- USD 17.2/hour compute time
eu-north1 preemptible
spot NVIDIA HGX H100
8× H100
80 GB VRAM/GPU · 128 vCPUs · 2048 GB RAM · 62914.56 GB storage
Region: europe
- USD 19.51/hour compute time
Europe spot
spot NVIDIA HGX H100
8× H100
80 GB VRAM/GPU · 128 vCPUs · 2048 GB RAM · 62914.56 GB storage
Region: north-america
- USD 19.71/hour compute time
North America spot
spot NVIDIA H100 · 8 GPU / 128 vCPU / 1600 GiB
8× H100
80 GB VRAM/GPU · 128 vCPUs · 1600 GB RAM · storage unknown
Region: Finland · FI · eu-north1 · EU
- USD 30.8/hour compute time
eu-north1 on-demand
standard 8× NVIDIA H100 SXM
8× H100
80 GB VRAM/GPU · 208 vCPUs · 1800 GB RAM · 22528 GB storage
Region: unknown
- USD 3.99/hour → USD 31.92/hour effective compute time
On-demand
standard NVIDIA H100 · 8 GPU
8× H100
80 GB VRAM/GPU · 160 vCPUs · 1920 GB RAM · 40960 GB storage
Region: unknown
- USD 35.28/hour compute time
On-demand
standard NVIDIA HGX H100
8× H100
80 GB VRAM/GPU · 128 vCPUs · 2048 GB RAM · 62914.56 GB storage
Region: north-america
- USD 49.24/hour compute time
North America on-demand
standard NVIDIA HGX H100
8× H100
80 GB VRAM/GPU · 128 vCPUs · 2048 GB RAM · 62914.56 GB storage
Region: europe
- USD 49.24/hour compute time
Europe on-demand
standard Available Providers
Baseten.co
1 offering · 1 billing option
Dedicated Deployments
Beam.cloud
1 offering · 1 billing option
Serverless
Cerebrium
2 offerings · 2 billing options
Serverless
CoreWeave
1 offering · 4 billing options
On-demand GPU Instances
DigitalOcean
2 offerings · 2 billing options
GPU Droplets
Fal.ai
1 offering · 2 billing options
Serverless
Fireworks AI
1 offering · 2 billing options
On-Demand Deployments
Hugging Face
4 offerings · 8 billing options
Inference Endpoints
Koyeb
4 offerings · 8 billing options
Serverless Compute
Lambda
5 offerings · 5 billing options
GPU Cloud Instances
Modal
1 offering · 3 billing options
Serverless
Nebius
2 offerings · 4 billing options
GPU Virtual Machines
OVHcloud
4 offerings · 5 billing options
AI Deploy · Public Cloud GPU
Paperspace
1 offering · 1 billing option
GPU Machines
Replicate
8 offerings · 8 billing options
Private Models · Public Models
Runpod
1 offering · 1 billing option
Serverless
Scaleway
4 offerings · 6 billing options
GPU Instances
Verda
2 offerings · 4 billing options
GPU Instances