Domain names illustration

AI Deploy

Serve your AI model as an API on dedicated GPUs, from your container. Autoscaling down to zero for your metrics, charged by the minute.

Serve your models without managing infrastructure

  • Graphique de suivi des métriques

    No servers to manage

    OVHcloud manages servers, endpoints, autoscaling and Grafana. You manage your images and models.
  • Fusée symbolisant un démarrage rapide

    Quick start

    Drivers and CUDA ready to go: only your image and your model are loaded when you get started.
  • Piles de pièces symbolisant les coûts

    Custom autoscaling

    Scale based on your own metrics. Without traffic, the app stops and is no longer billed. Grafana included.
  • Bouclier avec coche de validation

    Compliant and secure

    ISO 27001, SOC 2 Type II, HDS (EU regions). Ensures the sovereignty of your data.

Your model live in 3 steps

1. Select your image
Deployment of an inference server, an API or an app.

2. Set GPU and scaling
The GPU, then autoscaling on your metric, from 0 replicas.

3. Call your endpoint
An HTTPS URL protected by token or by username and password.
Deployment of an AI model: from Docker image to HTTPS endpoint on GPU

Everything to serve a model in production

  • Autoscaling rules

    CPU, RAM or custom metric, adjustable delay before resetting to zero.
  • High availability

    Load balancing managed by OVHcloud, replicas recreated automatically.
  • Disruption-free updates

    New image deployed without downtime, on the same URL.
  • Grafana monitoring

    CPU, GPU and RAM metrics per app, without configuration.
  • Secure access

    Endpoint protected by token or password.
  • Object Storage volumes

    Your weights loaded from a bucket, not from the image.
  • Console, API or CLI

    From the customer control panel, the API, the CLI or the Python SDK.
  • Images from your registry

    From Docker Hub, GitHub or Managed Private Registry.

Use case examples

Three ways to serve your models with AI Deploy, each with a guide to get started.

AI Deploy: feedback

  • lector.ai

    500 M pages processed · 80% of processing time saved. Document processing for health insurers, after migration from a US cloud.
    Read the case study
  • moinAI

    Customer service chatbots: moinAI trains its models on AI Training and serves them on AI Deploy.
    Read the case study

AI Deploy or Cloud GPU?

Are you hesitating between AI Deploy and your own Cloud GPU instances for serving your models? Here's what changes.
OVHcloud AI Deploy
OVHcloud Cloud GPU
Type of service
Managed container (CaaS)
GPU instance to manage (IaaS)
No traffic
Automatic shutdown, €0
Billed even when switched off
VM, drivers and CUDA
Already ready
To be installed and maintained
Startup
Image loading only
Boot VM, GPU stack, CUDA, then image
HTTPS endpoint and autoscaling
Included
To be built
GPU monitoring
Grafana included
To be configured
L40S GPU price
€1.55 ex. VAT/hour
€1.40 ex. VAT/hour
Perfect for
Variable traffic, team without MLOps
Stable load 24/7, full control
A stopped or paused instance remains billed at the same rate; only manual shelving reduces the bill to the snapshot.

Choose the GPUs used for your AI Deploy service

Hourly price, billed by the minute. Traffic included, no commitment.
See all Public Cloud prices
  • L4

    Small models, embeddings

    €0.83ex. VAT/hour

    • NVIDIA L4, 24 GB
    • 1 to 8 GPUs per replica
    • Gravelines (France)
  • L40S

    Fine-tuned LLMs, images

    €1.55ex. VAT/hour

    • NVIDIA L40S, 48 GB
    • 1 to 8 GPUs per replica
    • Gravelines (France)
  • A100

    LLMs and vision, large batches

    €3ex. VAT/hour

    • NVIDIA A100, 80 GB
    • 1 to 8 GPUs per replica
    • Gravelines (France)
  • H100

    Large LLMs, high throughput

    €3.10ex. VAT/hour

    • NVIDIA H100, 80 GB
    • 1 to 8 GPUs per replica
    • Gravelines (France)
  • H200

    Very large LLMs, multi-GPU

    €23.12ex. VAT/hour

    • 4 × NVIDIA H200, 141 GB
    • NVLink between the 4 GPUs
  • A10

    Compact models, NLP

    €0.90ex. VAT/hour

    • NVIDIA A10, 24 GB
    • Gravelines (France)
  • V100S

    Also available in Canada

    €1.93ex. VAT/hour

    • NVIDIA V100S, 32 GB
    • GRA and BHS
  • CPU

    Lightweight apps, classic ML

    €0.03ex. VAT/hour/vCore

    • Up to 12 vCores per replica
    • GRA and BHS
Prices as of 14/10/2026. Storage billed separately.

Ready to deploy your model?

Create an account and launch your first app

€200 free on your first Public Cloud project

SPECIFICATIONS

Technical specifications

  • GPU

    H200, H100, A100, L40S, L4, A10, V100S
  • Resources per replica

    Up to 8 dedicated GPUs or 12 vCores
  • Scaling

    0 to 10 replicas, autoscaling included
  • Network

    HTTPS or gRPC, traffic included
  • Regions

    Gravelines (FR), Beauharnois (CA)
  • Availability

    99.95% SLA, HA from 2 replicas

Guides

  • Getting started with AI Deploy

    Your first app, from image to URL.
    Find out more
  • Configure scaling

    Autoscaling and scaling to zero replicas.
    Find out more
  • Monitor your app

    Grafana metrics and your app logs.
    Find out more

Your questions, answered

How is AI Deploy billed?

By the minute, only when your app is running. Network traffic included, no commitment. Only Object Storage is billed separately.

How does scale-to-zero work?

With a minimum of 0 replicas, your app goes into standby mode when there is no traffic. It restarts on the next request, in 30 seconds to a few minutes.

Where are my data and models hosted?

In the region that you've selected: in France (GRA, PAR) to keep your data in the EU, or in Canada (BHS). OVHcloud is a European company, not subject to the CLOUD Act, and it does not use your data for its services.

Can I move my model elsewhere if needed?

Yes. AI Deploy runs standard Docker images: the same image runs on Kubernetes or with another provider.

Can I connect AI Deploy to my private network?

Not yet: each app is exposed via HTTPS, public or protected by token. For a private network (vRack), use Cloud GPU or Managed Kubernetes.