@@ -12642,12 +12642,12 @@ components:
1264212642 "target": 1.01} to scale based on queue backlog. Omit or set to null to
1264312643 disable autoscaling'
1264412644 oneOf :
12645- - $ref : ' #/components/schemas/HTTPAutoscalingConfig'
12646- - $ref : ' #/components/schemas/QueueAutoscalingConfig'
12647- - $ref : ' #/components/schemas/CustomMetricAutoscalingConfig'
12645+ - $ref : " #/components/schemas/HTTPAutoscalingConfig"
12646+ - $ref : " #/components/schemas/QueueAutoscalingConfig"
12647+ - $ref : " #/components/schemas/CustomMetricAutoscalingConfig"
1264812648 command :
12649- description : Command overrides the container's ENTRYPOINT. Provide as an array
12650- (e.g., ["/bin/sh", "-c"])
12649+ description : Command overrides the container's ENTRYPOINT. Provide as an
12650+ array (e.g., ["/bin/sh", "-c"])
1265112651 items :
1265212652 type : string
1265312653 type : array
@@ -12661,9 +12661,8 @@ components:
1266112661 deployment
1266212662 type : string
1266312663 environment_variables :
12664- description : EnvironmentVariables is a list of environment variables to set in
12665- the container. Each must have a name and either a value or
12666- value_from_secret
12664+ description : EnvironmentVariables is a list of environment variables to
12665+ set in the container. Each must have a name and either a value or value_from_secret
1266712666 items :
1266812667 $ref : " #/components/schemas/EnvironmentVariable"
1266912668 type : array
@@ -12674,52 +12673,52 @@ components:
1267412673 gpu_type :
1267512674 description : GPUType specifies the GPU hardware to use (e.g., "h100-80gb").
1267612675 enum :
12677- - h100-80gb
12678- - a100-80gb
12676+ - h100-80gb
1267912677 type : string
1268012678 health_check_path :
12681- description : HealthCheckPath is the HTTP path for health checks (e.g.,
12682- " /health" ). If set, the platform will check this endpoint to
12683- determine container health
12679+ description : HealthCheckPath is the HTTP path for health checks (e.g., "/health").
12680+ If set, the platform will check this endpoint to determine container health
1268412681 type : string
1268512682 image :
1268612683 description : Image is the container image to deploy from registry.together.ai.
1268712684 type : string
1268812685 max_replicas :
12689- description : MaxReplicas is the maximum number of container instances that can
12690- be scaled up to. If not set, will be set to MinReplicas
12686+ description : MaxReplicas is the maximum number of container instances that
12687+ can be scaled up to. If not set, will be set to MinReplicas
1269112688 type : integer
1269212689 memory :
12693- description : Memory is the amount of RAM to allocate per container instance in
12694- GiB (e.g., 0.5 = 512MiB)
12695- minimum : 0.1
12690+ description : Memory is the amount of RAM to allocate per container instance
12691+ in GiB (e.g., 0.5 = 512MiB)
12692+ maximum : 1000
1269612693 type : number
1269712694 min_replicas :
12698- description : MinReplicas is the minimum number of container instances to run.
12699- Defaults to 1 if not specified
12695+ description : MinReplicas is the minimum number of container instances to
12696+ run. Defaults to 1 if not specified
1270012697 type : integer
1270112698 name :
1270212699 description : Name is the unique identifier for your deployment. Must contain
12703- only alphanumeric characters, underscores, or hyphens (1-100
12704- characters)
12700+ only alphanumeric characters, underscores, or hyphens (1-100 characters)
1270512701 maxLength : 100
1270612702 minLength : 1
1270712703 type : string
1270812704 port :
12709- description : Port is the container port your application listens on (e.g., 8080
12710- for web servers). Required if your application serves traffic
12705+ description : Port is the container port your application listens on (e.g.,
12706+ 8080 for web servers). Required if your application serves traffic
12707+ maximum : 65535
12708+ minimum : 1
1271112709 type : integer
1271212710 storage :
12713- description : Storage is the amount of ephemeral disk storage to allocate per
12714- container instance (e.g., 10 = 10GiB)
12711+ description : Storage is the amount of ephemeral disk storage to allocate
12712+ per container instance (e.g., 10 = 10GiB)
12713+ maximum : 400
1271512714 type : integer
1271612715 termination_grace_period_seconds :
12717- description : TerminationGracePeriodSeconds is the time in seconds to wait for
12718- graceful shutdown before forcefully terminating the replica
12716+ description : TerminationGracePeriodSeconds is the time in seconds to wait
12717+ for graceful shutdown before forcefully terminating the replica
1271912718 type : integer
1272012719 volumes :
12721- description : Volumes is a list of volume mounts to attach to the container. Each
12722- mount must reference an existing volume by name
12720+ description : Volumes is a list of volume mounts to attach to the container.
12721+ Each mount must reference an existing volume by name
1272312722 items :
1272412723 $ref : " #/components/schemas/VolumeMount"
1272512724 type : array
@@ -12817,6 +12816,7 @@ components:
1281712816 created_at :
1281812817 description : CreatedAt is the ISO8601 timestamp when this deployment was created
1281912818 type : string
12819+ format : date-time
1282012820 description :
1282112821 description : Description provides a human-readable explanation of the
1282212822 deployment's purpose or content
@@ -12901,6 +12901,7 @@ components:
1290112901 description : UpdatedAt is the ISO8601 timestamp when this deployment was last
1290212902 updated
1290312903 type : string
12904+ format : date-time
1290412905 volumes :
1290512906 description : Volumes is a list of volume mounts for this deployment
1290612907 items :
@@ -13116,15 +13117,15 @@ components:
1311613117 type : string
1311713118 type : array
1311813119 autoscaling :
13119- description : Autoscaling configuration for the deployment. Omit or set to
13120- null to disable autoscaling
13120+ description : Autoscaling configuration for the deployment. Set to {} to
13121+ disable autoscaling
1312113122 oneOf :
13122- - $ref : ' #/components/schemas/HTTPAutoscalingConfig'
13123- - $ref : ' #/components/schemas/QueueAutoscalingConfig'
13124- - $ref : ' #/components/schemas/CustomMetricAutoscalingConfig'
13123+ - $ref : " #/components/schemas/HTTPAutoscalingConfig"
13124+ - $ref : " #/components/schemas/QueueAutoscalingConfig"
13125+ - $ref : " #/components/schemas/CustomMetricAutoscalingConfig"
1312513126 command :
13126- description : Command overrides the container's ENTRYPOINT. Provide as an array
13127- (e.g., ["/bin/sh", "-c"])
13127+ description : Command overrides the container's ENTRYPOINT. Provide as an
13128+ array (e.g., ["/bin/sh", "-c"])
1312813129 items :
1312913130 type : string
1313013131 type : array
@@ -13138,8 +13139,8 @@ components:
1313813139 deployment
1313913140 type : string
1314013141 environment_variables :
13141- description : EnvironmentVariables is a list of environment variables to set in
13142- the container. This will replace all existing environment variables
13142+ description : EnvironmentVariables is a list of environment variables to
13143+ set in the container. This will replace all existing environment variables
1314313144 items :
1314413145 $ref : " #/components/schemas/EnvironmentVariable"
1314513146 type : array
@@ -13149,50 +13150,51 @@ components:
1314913150 gpu_type :
1315013151 description : GPUType specifies the GPU hardware to use (e.g., "h100-80gb")
1315113152 enum :
13152- - h100-80gb
13153- - " a100-80gb"
13153+ - h100-80gb
1315413154 type : string
1315513155 health_check_path :
13156- description : HealthCheckPath is the HTTP path for health checks (e.g.,
13157- " /health " ). Set to empty string to disable health checks
13156+ description : HealthCheckPath is the HTTP path for health checks (e.g., "/health").
13157+ Set to empty string to disable health checks
1315813158 type : string
1315913159 image :
1316013160 description : Image is the container image to deploy from registry.together.ai.
1316113161 type : string
1316213162 max_replicas :
13163- description : MaxReplicas is the maximum number of replicas that can be scaled up
13164- to.
13163+ description : MaxReplicas is the maximum number of replicas that can be scaled
13164+ up to.
1316513165 type : integer
1316613166 memory :
13167- description : Memory is the amount of RAM to allocate per container instance in
13168- GiB (e.g., 0.5 = 512MiB)
13169- minimum : 0.1
13167+ description : Memory is the amount of RAM to allocate per container instance
13168+ in GiB (e.g., 0.5 = 512MiB)
13169+ maximum : 1000
1317013170 type : number
1317113171 min_replicas :
1317213172 description : MinReplicas is the minimum number of replicas to run
1317313173 type : integer
1317413174 name :
13175- description : Name is the new unique identifier for your deployment. Must contain
13176- only alphanumeric characters, underscores, or hyphens (1-100
13177- characters)
13175+ description : Name is the new unique identifier for your deployment. Must
13176+ contain only alphanumeric characters, underscores, or hyphens (1-100 characters)
1317813177 maxLength : 100
1317913178 minLength : 1
1318013179 type : string
1318113180 port :
13182- description : Port is the container port your application listens on (e.g., 8080
13183- for web servers)
13181+ description : Port is the container port your application listens on (e.g.,
13182+ 8080 for web servers)
13183+ maximum : 65535
13184+ minimum : 1
1318413185 type : integer
1318513186 storage :
13186- description : Storage is the amount of ephemeral disk storage to allocate per
13187- container instance (e.g., 10 = 10GiB)
13187+ description : Storage is the amount of ephemeral disk storage to allocate
13188+ per container instance (e.g., 10 = 10GiB)
13189+ maximum : 400
1318813190 type : integer
1318913191 termination_grace_period_seconds :
13190- description : TerminationGracePeriodSeconds is the time in seconds to wait for
13191- graceful shutdown before forcefully terminating the replica
13192+ description : TerminationGracePeriodSeconds is the time in seconds to wait
13193+ for graceful shutdown before forcefully terminating the replica
1319213194 type : integer
1319313195 volumes :
13194- description : Volumes is a list of volume mounts to attach to the container. This
13195- will replace all existing volumes
13196+ description : Volumes is a list of volume mounts to attach to the container.
13197+ This will replace all existing volumes
1319613198 items :
1319713199 $ref : " #/components/schemas/VolumeMount"
1319813200 type : array
0 commit comments