Deployments
Deployments promote installed assets to an environment (staging or production) and expose a runtime endpoint.
The Deployment Object
| Field | Type | Description |
|---|---|---|
| id | string | Unique deployment ID with prefix dep_ (e.g. dep_uti_prod_001) |
| installationId | string | ID of the asset installation being deployed |
| environment | string | Target environment: production | staging |
| endpoint | string | Fully-qualified HTTPS URL where the deployed asset accepts inference requests |
| status | string | One of: provisioning | healthy | degraded | stopped |
| replicas | integer | Number of replica pods running for this deployment |
| p50LatencyMs | integer | Median (P50) inference latency in milliseconds over the last hour |
| p99LatencyMs | integer | P99 inference latency in milliseconds over the last hour |
| createdAt | datetime | ISO 8601 UTC timestamp when the deployment was created |
Endpoints
Returns all active deployments in a project.
Parameters
| Parameter | In | Type | Required | Description |
|---|---|---|---|---|
| projectIde.g. proj_rpm_001 | query | string | required | Project ID |
| environmente.g. production | query | string | optional | production|staging |
Request
curl "https://api.healthcloud.ai/v1/deployments?projectId=proj_rpm_001&environment=production" \ -H "Authorization: Bearer hc_test_sk_demo_live_xxxxxx"
Response
Response200
{ "data": [ { "id": "dep_uti_prod_001", "installationId": "inst_uti_001", "environment": "production", "endpoint": "https://api.healthcloud.ai/v1/exec/dep_uti_prod_001", "status": "healthy", "p50LatencyMs": 43, "p99LatencyMs": 210 } ] }