a10-1-gpu
AI Deploy
A10 · fixed · 1 GPU · 24 GB VRAM
- USD 1/hour compute time
a10-1-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
OVHcloud
8 accepted offerings · 16 commercial variants
Products: AI Deploy
Freshness: 8 current · 0 aging · 0 stale
Serverless GPU Prices
| Offering | Commercial variant | Price | Geography & evidence |
|---|---|---|---|
| a10-1-gpu AI Deploy A10 · fixed · 1 GPU · 24 GB VRAM | a10-1-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| a10-1-gpu AI Deploy A10 · fixed · 1 GPU · 24 GB VRAM | a10-1-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| a100-1-gpu AI Deploy A100 · fixed · 1 GPU · 80 GB VRAM | a100-1-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| a100-1-gpu AI Deploy A100 · fixed · 1 GPU · 80 GB VRAM | a100-1-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| ai1-1-GPU AI Deploy V100 · fixed · 1 GPU · 32 GB VRAM | ai1-1-GPU always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| ai1-1-GPU AI Deploy V100 · fixed · 1 GPU · 32 GB VRAM | ai1-1-GPU scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| ai1-le-1-GPU AI Deploy V100 · fixed · 1 GPU · 32 GB VRAM | ai1-le-1-GPU always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| ai1-le-1-GPU AI Deploy V100 · fixed · 1 GPU · 32 GB VRAM | ai1-le-1-GPU scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| h100-1-gpu AI Deploy H100 · fixed · 1 GPU · 80 GB VRAM | h100-1-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| h100-1-gpu AI Deploy H100 · fixed · 1 GPU · 80 GB VRAM | h100-1-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| h200-4-gpu AI Deploy NVIDIA H200 · fixed · 4 GPU · 525 GB VRAM | h200-4-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| h200-4-gpu AI Deploy NVIDIA H200 · fixed · 4 GPU · 525 GB VRAM | h200-4-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| l4-1-gpu AI Deploy L4 · fixed · 1 GPU · 24 GB VRAM | l4-1-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| l4-1-gpu AI Deploy L4 · fixed · 1 GPU · 24 GB VRAM | l4-1-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| l40s-1-gpu AI Deploy L40S · fixed · 1 GPU · 48 GB VRAM | l40s-1-gpu always-on always on · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
| l40s-1-gpu AI Deploy L40S · fixed · 1 GPU · 48 GB VRAM | l40s-1-gpu scale-to-zero scale to zero · standard · dedicated · inclusive total |
| EU compute: unknown EU-constrained: unknown EU-only: unknown |
a10-1-gpu
AI Deploy
A10 · fixed · 1 GPU · 24 GB VRAM
- USD 1/hour compute time
a10-1-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
a100-1-gpu
AI Deploy
A100 · fixed · 1 GPU · 80 GB VRAM
- USD 3.35/hour compute time
a100-1-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
a100-1-gpu
AI Deploy
A100 · fixed · 1 GPU · 80 GB VRAM
- USD 3.35/hour compute time
a100-1-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
ai1-1-GPU
AI Deploy
V100 · fixed · 1 GPU · 32 GB VRAM
- USD 2.16/hour compute time
ai1-1-GPU always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
ai1-1-GPU
AI Deploy
V100 · fixed · 1 GPU · 32 GB VRAM
- USD 2.16/hour compute time
ai1-1-GPU scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
ai1-le-1-GPU
AI Deploy
V100 · fixed · 1 GPU · 32 GB VRAM
- USD 1.01/hour compute time
ai1-le-1-GPU always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
ai1-le-1-GPU
AI Deploy
V100 · fixed · 1 GPU · 32 GB VRAM
- USD 1.01/hour compute time
ai1-le-1-GPU scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
h100-1-gpu
AI Deploy
H100 · fixed · 1 GPU · 80 GB VRAM
- USD 3.39/hour compute time
h100-1-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
h100-1-gpu
AI Deploy
H100 · fixed · 1 GPU · 80 GB VRAM
- USD 3.39/hour compute time
h100-1-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
h200-4-gpu
AI Deploy
NVIDIA H200 · fixed · 4 GPU · 525 GB VRAM
- USD 27.28/hour compute time
h200-4-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
h200-4-gpu
AI Deploy
NVIDIA H200 · fixed · 4 GPU · 525 GB VRAM
- USD 27.28/hour compute time
h200-4-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
l4-1-gpu
AI Deploy
L4 · fixed · 1 GPU · 24 GB VRAM
- USD 0.91/hour compute time
l4-1-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
l4-1-gpu
AI Deploy
L4 · fixed · 1 GPU · 24 GB VRAM
- USD 0.91/hour compute time
l4-1-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
l40s-1-gpu
AI Deploy
L40S · fixed · 1 GPU · 48 GB VRAM
- USD 1.69/hour compute time
l40s-1-gpu always-on
always on · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
l40s-1-gpu
AI Deploy
L40S · fixed · 1 GPU · 48 GB VRAM
- USD 1.69/hour compute time
l40s-1-gpu scale-to-zero
scale to zero · standard · dedicated · inclusive total EU compute: unknown EU-constrained: unknown EU-only: unknown
Other GPU Providers
Baseten.co
7 offerings · 7 commercial variants
Dedicated Deployments
Beam.cloud
9 offerings · 9 commercial variants
Serverless
Cerebrium
10 offerings · 10 commercial variants
Serverless
Fireworks AI
4 offerings · 8 commercial variants
On-Demand Deployments
Google Cloud
2 offerings · 4 commercial variants
Cloud Run GPU Services
Hugging Face
28 offerings · 56 commercial variants
Inference Endpoints
Inferless
6 offerings · 6 commercial variants
Serverless
Koyeb
22 offerings · 44 commercial variants
Serverless Compute
Microsoft Azure
2 offerings · 4 commercial variants
Container Apps Serverless GPU
Modal
11 offerings · 33 commercial variants
Serverless
Replicate
26 offerings · 26 commercial variants
Private Models · Public Models
Runpod
13 offerings · 13 commercial variants
Serverless