Skip to content
Cloud GPU Prices

OVHcloud

Benchmarks JSON

32 offerings · 40 billing options

Products: AI Deploy · Public Cloud GPU

32 of 32 offerings verified recently

8 identified GPU models

View official pricing source →

How the service works

Hand-reviewed product behavior. Exact current prices and billing units remain in the tables below.

AI Deploy

Hand-reviewed 2026-07-18 · review after 2026-10-18

Setup: moderate

Deployment
A Docker image is deployed as a managed HTTP application with one or more GPU-backed replicas through the OVHcloud control panel or ovhai CLI.
managed container · synchronous http
Scale to zero
Scale-to-zero requires autoscaling with minimum replicas set to zero. The scale-down and scale-to-zero stabilization windows determine how long the last replica remains running.
conditional · requires configuration
Billing behavior
Compute is charged for each replica's lifetime with per-minute granularity, rather than per request. Registry and persistent storage costs are separate.
Startup behavior
OVHcloud documents a 30-second-to-several-minute cold-start delay from zero depending on image and volume weight, with an additional risk that a popular GPU flavor is temporarily unavailable.
Setup
Deployment requires an OVHcloud Public Cloud project, a compatible container image in a reachable registry, selected AI Deploy compute resources and explicit autoscaling configuration for scale-to-zero.
Requires: OVHcloud Public Cloud project · Container image and registry · AI Deploy application configuration · Autoscaling minimum zero for scale-to-zero
Important constraints
  • The product is an HTTP application platform rather than a native queued batch-job abstraction.
  • A request arriving at zero replicas waits through the complete cold start, and capacity is not reserved.

Serverless GPU prices

1× A10 · 24 GB VRAM/GPU
a10-1-gpu · Serverless · fixed
  • USD 1/hour
    compute time
≈ EUR 0.8707/hour
a10-1-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× A10 · 24 GB VRAM/GPU
a10-1-gpu · Serverless · fixed
  • USD 1/hour
    compute time
≈ EUR 0.8707/hour
a10-1-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× A100 · 80 GB VRAM/GPU
a100-1-gpu · Serverless · fixed
  • USD 3.35/hour
    compute time
≈ EUR 2.917/hour
a100-1-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× A100 · 80 GB VRAM/GPU
a100-1-gpu · Serverless · fixed
  • USD 3.35/hour
    compute time
≈ EUR 2.917/hour
a100-1-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× V100 · 32 GB VRAM/GPU
ai1-1-GPU · Serverless · fixed
  • USD 2.16/hour
    compute time
≈ EUR 1.881/hour
ai1-1-GPU always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× V100 · 32 GB VRAM/GPU
ai1-1-GPU · Serverless · fixed
  • USD 2.16/hour
    compute time
≈ EUR 1.881/hour
ai1-1-GPU scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× V100 · 32 GB VRAM/GPU
ai1-le-1-GPU · Serverless · fixed
  • USD 1.01/hour
    compute time
≈ EUR 0.8794/hour
ai1-le-1-GPU always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× V100 · 32 GB VRAM/GPU
ai1-le-1-GPU · Serverless · fixed
  • USD 1.01/hour
    compute time
≈ EUR 0.8794/hour
ai1-le-1-GPU scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× H100 · 80 GB VRAM/GPU
h100-1-gpu · Serverless · fixed
  • USD 3.39/hour
    compute time
≈ EUR 2.952/hour
h100-1-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× H100 · 80 GB VRAM/GPU
h100-1-gpu · Serverless · fixed
  • USD 3.39/hour
    compute time
≈ EUR 2.952/hour
h100-1-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
4× NVIDIA H200 · 131.25 GB VRAM/GPU
h200-4-gpu · Serverless · fixed
  • USD 27.28/hour
    compute time
≈ EUR 23.75/hour
h200-4-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
4× NVIDIA H200 · 131.25 GB VRAM/GPU
h200-4-gpu · Serverless · fixed
  • USD 27.28/hour
    compute time
≈ EUR 23.75/hour
h200-4-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× L4 · 24 GB VRAM/GPU
l4-1-gpu · Serverless · fixed
  • USD 0.91/hour
    compute time
≈ EUR 0.7923/hour
l4-1-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× L4 · 24 GB VRAM/GPU
l4-1-gpu · Serverless · fixed
  • USD 0.91/hour
    compute time
≈ EUR 0.7923/hour
l4-1-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× L40S · 48 GB VRAM/GPU
l40s-1-gpu · Serverless · fixed
  • USD 1.69/hour
    compute time
≈ EUR 1.471/hour
l40s-1-gpu always-on
always on · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)
1× L40S · 48 GB VRAM/GPU
l40s-1-gpu · Serverless · fixed
  • USD 1.69/hour
    compute time
≈ EUR 1.471/hour
l40s-1-gpu scale-to-zero
scale to zero · dedicated
1 minute increments · bills SCALING, RUNNING
Verified 1 Aug 2026 Official price source (opens in new tab)

GPU Instance Prices

rtx5000-28
1× NVIDIA Quadro RTX 5000
16 GB VRAM/GPU · 4 vCPUs · 28 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.36/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t1-le-45
1× V100
16 GB VRAM/GPU · 8 vCPUs · 45 GB RAM · 300 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.7/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
rtx5000-56
2× NVIDIA Quadro RTX 5000
16 GB VRAM/GPU · 8 vCPUs · 56 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.72/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
l4-90
1× L4
24 GB VRAM/GPU · 22 vCPUs · 90 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.75/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a10-45
1× A10
24 GB VRAM/GPU · 30 vCPUs · 42 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.76/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t2-le-45
1× V100
32 GB VRAM/GPU · 15 vCPUs · 45 GB RAM · 300 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 0.8/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
rtx5000-84
3× NVIDIA Quadro RTX 5000
16 GB VRAM/GPU · 16 vCPUs · 84 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.08/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
l40s-90
1× L40S
48 GB VRAM/GPU · 15 vCPUs · 90 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.4/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t1-le-90
2× V100
16 GB VRAM/GPU · 16 vCPUs · 90 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.4/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
l4-180
2× L4
24 GB VRAM/GPU · 45 vCPUs · 180 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.5/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a10-90
2× A10
24 GB VRAM/GPU · 60 vCPUs · 85 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.52/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t2-le-90
2× V100
32 GB VRAM/GPU · 30 vCPUs · 90 GB RAM · 500 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 1.6/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a100-180
1× A100
80 GB VRAM/GPU · 15 vCPUs · 180 GB RAM · 300 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 2.75/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
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
Verified 1 Aug 2026 Official price source (opens in new tab)
l40s-180
2× L40S
48 GB VRAM/GPU · 30 vCPUs · 180 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 2.8/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t1-le-180
4× V100
16 GB VRAM/GPU · 32 vCPUs · 180 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 2.8/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
l4-360
4× L4
24 GB VRAM/GPU · 90 vCPUs · 360 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 3/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a10-180
4× A10
24 GB VRAM/GPU · 120 vCPUs · 170 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 3.04/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
t2-le-180
4× V100
32 GB VRAM/GPU · 60 vCPUs · 180 GB RAM · 500 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 3.2/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a100-360
2× A100
80 GB VRAM/GPU · 30 vCPUs · 360 GB RAM · 500 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 5.5/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
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
Verified 1 Aug 2026 Official price source (opens in new tab)
l40s-360
4× L40S
48 GB VRAM/GPU · 60 vCPUs · 360 GB RAM · 400 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 5.6/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
a100-720
4× A100
80 GB VRAM/GPU · 60 vCPUs · 720 GB RAM · 500 GB storage
Region: Gravelines · FR · gra · EU
  • EUR 11/hour
    compute time
Gravelines on-demand
standard
Verified 1 Aug 2026 Official price source (opens in new tab)
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
Verified 1 Aug 2026 Official price source (opens in new tab)

Other GPU Providers

Amazon Web Services

2 offerings · 4 billing options

EC2 GPU Instances

Baseten.co

7 offerings · 7 billing options

Dedicated Deployments

Beam.cloud

9 offerings · 9 billing options

Serverless

Cerebrium

10 offerings · 10 billing options

Serverless

CoreWeave

10 offerings · 32 billing options

On-demand GPU Instances

Crusoe

9 offerings · 9 billing options

On-demand GPU Instances

DigitalOcean

9 offerings · 9 billing options

GPU Droplets

Fal.ai

5 offerings · 10 billing options

Serverless

Fireworks AI

4 offerings · 8 billing options

On-Demand Deployments

Google Cloud

15 offerings · 30 billing options

Cloud Run GPU Services · Compute Engine GPU VMs

Hugging Face

28 offerings · 56 billing options

Inference Endpoints

Inferless

6 offerings · 6 billing options

Serverless

Koyeb

22 offerings · 44 billing options

Serverless Compute

Lambda

22 offerings · 22 billing options

GPU Cloud Instances

Microsoft Azure

4 offerings · 8 billing options

Container Apps Serverless GPU · GPU Virtual Machines

Modal

11 offerings · 33 billing options

Serverless

Nebius

22 offerings · 56 billing options

GPU Virtual Machines

Paperspace

13 offerings · 27 billing options

GPU Machines

Replicate

26 offerings · 26 billing options

Private Models · Public Models

Runpod

13 offerings · 13 billing options

Serverless

Scaleway

16 offerings · 30 billing options

GPU Instances

Verda

14 offerings · 28 billing options

GPU Instances

Vultr

4 offerings · 24 billing options

Cloud GPU