Skip to main content
POST
Deploy

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
modelCatalogId
string
required
Minimum string length: 1
teamId
string | null
Minimum string length: 1
deploymentName
string | null
Maximum string length: 29
Pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
replicas
integer
default:1
Required range: 1 <= x <= 4
primeClusterId
string | null
Minimum string length: 1

Response

Successful Response

id
string
required
deploymentName
string
required
status
enum<string>
required
Available options:
PENDING,
DEPLOYING,
RUNNING,
TERMINATING,
COMPLETED,
FAILED,
STOPPED,
UNKNOWN,
TOMBSTONED
servedModelAlias
string
required
isOnDemand
boolean
required
createdAt
string<date-time>
required
dashboardUrl
string
required
statusPhase
string | null
errorMessage
string | null
endpointUrl
string | null
checkpoint
CheckpointRef · object | null

Step step of training run run_id.

replicas
integer | null
gpusPerReplica
integer | null
maxReplicas
integer | null
scaleState
string | null