Get Deployment Response
AI deployment
Properties
| Property | Type | Required | Description |
|---|---|---|---|
created-at | string | yes | Creation time ISO 8601 date-time. |
deployment-url | string | yes | Deployment inference endpoint URL |
gpu-count | integer | yes | Number of GPUs Min: 1. |
gpu-type | string | yes | GPU type family Min length: 1. |
id | string | yes | Deployment ID Must be a valid UUID. |
inference-engine-parameters | array[string] | yes | Optional extra inference engine server CLI args |
inference-engine-version | string | yes | Allowed values: 0.12.0, 0.15.1, 0.16.0, 0.17.0, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 0.20.0, 0.20.1, 0.20.2, 0.21.0, 0.22.0, 0.22.1.Default: 0.22.1. |
model | Model reference. Provide either id or name. | yes | |
name | string | yes | Deployment name Min length: 1. |
replicas | integer | yes | Number of replicas (>=0) Min: 0. |
service-level | string | yes | Service level Min length: 1. |
state | string | yes | Deployment state Allowed values: ready, creating, preparing, error, deploying, scaling, updating. |
state-details | string | yes | Deployment state details |
updated-at | string | yes | Update time ISO 8601 date-time. |
Last updated on