# [BETA] Create Deployment

**POST /ai/deployment**

Deploy a model on an inference server


## Servers
- https://api-ch-gva-2.exoscale.com/v2: https://api-ch-gva-2.exoscale.com/v2 ()



## Parameters



## Body parameters
Content-type: application/json

- **model** (object)
  
- **name** (string)
  Deployment name
- **gpu-type** (string)
  GPU type family (e.g., gpua5000, gpu3080ti)
- **gpu-count** (integer(int64))
  Number of GPUs (1-8)
- **replicas** (integer(int64))
  Number of replicas (>=1)

## Responses
### 200: 200

#### Body Parameters: application/json (object)
- **id** (string(uuid))
  Operation ID
- **reason** (string)
  Operation failure reason
- **reference** (object)
  Related resource reference
- **message** (string)
  Operation message
- **state** (string)
  Operation status

### 400: 400

#### Body Parameters: application/json (object)
- **error** (string)
  Error description


[Powered by Bump.sh](https://bump.sh)