# 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: application/json (object)

- **gpu-count** (integer(int64))
  Number of GPUs (1-8)
- **inference-engine-version** (string)
  Inference engine version
- **name** (string)
  Deployment name
- **gpu-type** (string)
  GPU type family (e.g., gpua5000, gpu3080ti)
- **replicas** (integer(int64))
  Number of replicas (>=1)
- **inference-engine-parameters** (array[string])
  Optional extra inference engine server CLI args
- **model** (object)



## Responses
### 412
412

#### Body: application/json (object)
- **type** (string(uri-reference))

- **title** (string)

- **status** (integer)

- **detail** (string)

- **instance** (string(uri-reference))

- **errors** (array[object])


### 403
403

#### Body: application/json (object)
- **code** (string)
  Machine-readable forbidden error code
- **error** (string)
  Forbidden error message

### 200
200

#### Body: 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: application/json (object)
- **type** (string(uri-reference))

- **title** (string)

- **status** (integer)

- **detail** (string)

- **instance** (string(uri-reference))

- **errors** (array[object])



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