# Revisions

Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload.

## Get inference workload revisions by id. \[Experimental]

> Retrieve the details of inference workload revisions by workload id. Supported for clusters v2.21+.

```json
{"openapi":"3.0.3","info":{"title":"NVIDIA Run:ai","version":"2.22"},"tags":[{"name":"Revisions","description":"Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload."}],"servers":[{"url":"https://app.run.ai"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT","description":"Bearer authentication"}},"parameters":{"WorkloadId":{"name":"workloadId","in":"path","required":true,"description":"The  Universally Unique Identifier (UUID) of the workload.","schema":{"type":"string","format":"uuid"}},"Deleted":{"name":"deleted","in":"query","description":"Return only deleted resources when `true`.","schema":{"type":"boolean"}}},"schemas":{"Revision":{"type":"object","required":["type","name","id","workloadId","tenantId","clusterId","departmentId","projectId","createdAt","phase"],"properties":{"type":{"type":"string"},"name":{"type":"string"},"id":{"type":"string","format":"uuid"},"workloadId":{"type":"string","format":"uuid"},"tenantId":{"$ref":"#/components/schemas/TenantId"},"clusterId":{"$ref":"#/components/schemas/ClusterId"},"projectId":{"$ref":"#/components/schemas/ProjectId2"},"departmentId":{"$ref":"#/components/schemas/DepartmentId2"},"createdAt":{"type":"string","format":"date-time"},"deletedAt":{"type":"string","format":"date-time","nullable":true},"revisionRequestedResources":{"$ref":"#/components/schemas/WorkloadRequestResources"},"podsRequestedResources":{"$ref":"#/components/schemas/WorkloadRequestResources"},"requestedPods":{"$ref":"#/components/schemas/RequestedPods"},"requestedNodePools":{"type":"array","items":{"type":"string"}},"allocatedResources":{"$ref":"#/components/schemas/WorkloadAllocatedResources"},"currentNodePools":{"type":"array","items":{"type":"string"}},"runningPods":{"type":"integer","format":"int32"},"images":{"type":"array","items":{"type":"string"}},"environmentVariables":{"type":"object","additionalProperties":{"type":"string"}},"command":{"type":"string"},"arguments":{"type":"string"},"childrenIds":{"type":"array","writeOnly":true,"items":{"type":"object","required":["id"],"properties":{"id":{"type":"string","format":"uuid"},"type":{"type":"string"}}}},"conditions":{"$ref":"#/components/schemas/Conditions"},"phase":{"$ref":"#/components/schemas/Phase"},"phaseMessage":{"type":"string"},"phaseUpdatedAt":{"type":"string","format":"date-time"},"additionalFields":{"type":"object","additionalProperties":true}}},"TenantId":{"description":"The id of the tenant.","type":"integer","format":"int32"},"ClusterId":{"description":"The id of the cluster.","type":"string","format":"uuid"},"ProjectId2":{"description":"The id of the project.","type":"string"},"DepartmentId2":{"description":"The id of the department.","type":"string","minLength":1},"WorkloadRequestResources":{"type":"object","nullable":true,"properties":{"gpuRequestType":{"$ref":"#/components/schemas/GpuRequestType"},"gpu":{"$ref":"#/components/schemas/RequestResourceCores"},"gpuMemory":{"$ref":"#/components/schemas/RequestResourceQuantity"},"cpu":{"$ref":"#/components/schemas/RequestResourceCores"},"cpuMemory":{"$ref":"#/components/schemas/RequestResourceQuantity"},"migProfile":{"type":"array","nullable":true,"items":{"$ref":"#/components/schemas/MigProfile"}},"extendedResources":{"$ref":"#/components/schemas/WorkloadsExtendedResources"}}},"GpuRequestType":{"description":"Sets the unit type for GPU resources requests. Stated in terms of portion, memory or  mig profile [deprecated]. Sets the unit type for other GPU request fields. If `gpuDevicesRequest > 1`, only `portion` is supported. If `gpuDeviceRequest = 1`, the request type can be stated as `portion`, `memory` or `migProfile` [deprecated].","type":"string","minLength":1,"enum":["portion","memory","migProfile"],"nullable":true},"RequestResourceCores":{"type":"object","properties":{"limit":{"type":"number","nullable":true,"format":"double"},"request":{"type":"number","nullable":true,"format":"double"}},"nullable":true},"RequestResourceQuantity":{"type":"object","properties":{"limit":{"type":"string","nullable":true,"pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$"},"request":{"type":"string","nullable":true,"pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$"}},"nullable":true},"MigProfile":{"description":"Required only if `gpuRequestType` is `migProfile`. This states the memory profile to be used for the workload running NVIDIA Multi-Instance GPU (MIG) technology.","type":"string","deprecated":true,"minLength":1,"enum":["1g.5gb","1g.10gb","2g.10gb","2g.20gb","3g.20gb","3g.40gb","4g.20gb","4g.40gb","7g.40gb","7g.80gb"],"nullable":true},"WorkloadsExtendedResources":{"description":"Set of extended resources with their quantity","type":"array","items":{"$ref":"#/components/schemas/WorkloadsExtendedResource"},"nullable":true},"WorkloadsExtendedResource":{"description":"Quantity of an extended resource.","type":"object","properties":{"resource":{"description":"The name of the extended resource (mandatory)","type":"string","minLength":1,"nullable":true},"quantity":{"description":"The requested quantity for the given resource.","type":"string","minLength":1,"nullable":true},"exclude":{"description":"Whether to exclude this extended resource from the workload. This is necessary in case the extended resource is inherited from the policy defaults and it is desired not to include it in this workload.","type":"boolean","nullable":true}},"nullable":true},"RequestedPods":{"type":"object","properties":{"number":{"type":"integer","format":"int32","nullable":true},"min":{"type":"integer","format":"int32","nullable":true},"max":{"type":"integer","format":"int32","nullable":true},"parallelism":{"type":"integer","format":"int32","description":"specifies how many Pods can run in parallel","nullable":true},"completions":{"type":"integer","description":"specifies how many Pods should terminate successfully before the Workload is completed","format":"int32","nullable":true}}},"WorkloadAllocatedResources":{"type":"object","nullable":true,"properties":{"gpu":{"type":"number","nullable":true,"format":"double","description":"Required if and only if gpuRequestType is portion. States the number of GPUs allocated for the created workload. The default is no allocated GPUs."},"migProfile":{"type":"array","nullable":true,"items":{"$ref":"#/components/schemas/MigProfile"}},"gpuMemory":{"type":"string","pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$","nullable":true},"cpu":{"type":"number","nullable":true,"format":"double","description":"States the amount of CPU cores used by the workload running."},"cpuMemory":{"type":"string","pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$","nullable":true},"extendedResources":{"$ref":"#/components/schemas/WorkloadsExtendedResources"}}},"Conditions":{"type":"array","items":{"$ref":"#/components/schemas/Condition1"}},"Condition1":{"type":"object","required":["type","status"],"properties":{"type":{"description":"The type of the condition, such as Failed or Available. See Types of domain status conditions.","type":"string"},"status":{"type":"string","description":"The status of the condition, such as True, False or Unknown."},"message":{"type":"string","description":"An optional, human-readable message providing more details about the condition."},"reason":{"type":"string","description":"The reason for the Failed condition. Not applicable to other types of condition."},"lastTransitionTime":{"description":"A timestamp of when the condition was created or the last time time the condition transitioned from one status to another.","type":"string","nullable":true,"format":"date-time"}}},"Phase":{"type":"string","enum":["Creating","Initializing","Resuming","Pending","Deleting","Running","Updating","Stopped","Stopping","Degraded","Failed","Completed","Terminating","Unknown"]},"Error":{"required":["code","message"],"properties":{"code":{"type":"integer","minimum":100,"maximum":599},"message":{"type":"string"},"details":{"type":"string"}}}},"responses":{"401Unauthorized":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"403Forbidden":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"404NotFound":{"description":"The specified resource was not found","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"500InternalServerError":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"503ServiceUnavailable":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}},"paths":{"/api/v1/workloads/inferences/{workloadId}/revisions":{"get":{"summary":"Get inference workload revisions by id. [Experimental]","description":"Retrieve the details of inference workload revisions by workload id. Supported for clusters v2.21+.","operationId":"get_inference_workload_revisions","tags":["Revisions"],"parameters":[{"$ref":"#/components/parameters/WorkloadId"},{"$ref":"#/components/parameters/Deleted"}],"responses":{"200":{"description":"Executed successfully.","content":{"application/json":{"schema":{"type":"object","required":["revisions"],"properties":{"revisions":{"type":"array","items":{"$ref":"#/components/schemas/Revision"}}}}}}},"401":{"$ref":"#/components/responses/401Unauthorized"},"403":{"$ref":"#/components/responses/403Forbidden"},"404":{"$ref":"#/components/responses/404NotFound"},"500":{"$ref":"#/components/responses/500InternalServerError"},"503":{"$ref":"#/components/responses/503ServiceUnavailable"}}}}}}
```

## Get inference workload revisions count. \[Experimental]

> Retrieve the number of an inference workload revisions from a cluster. Supported for clusters v2.21+.

```json
{"openapi":"3.0.3","info":{"title":"NVIDIA Run:ai","version":"2.22"},"tags":[{"name":"Revisions","description":"Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload."}],"servers":[{"url":"https://app.run.ai"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT","description":"Bearer authentication"}},"parameters":{"WorkloadId":{"name":"workloadId","in":"path","required":true,"description":"The  Universally Unique Identifier (UUID) of the workload.","schema":{"type":"string","format":"uuid"}},"Deleted":{"name":"deleted","in":"query","description":"Return only deleted resources when `true`.","schema":{"type":"boolean"}}},"responses":{"401Unauthorized":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"403Forbidden":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"500InternalServerError":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"503ServiceUnavailable":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"schemas":{"Error":{"required":["code","message"],"properties":{"code":{"type":"integer","minimum":100,"maximum":599},"message":{"type":"string"},"details":{"type":"string"}}}}},"paths":{"/api/v1/workloads/inferences/{workloadId}/revisions/count":{"get":{"summary":"Get inference workload revisions count. [Experimental]","description":"Retrieve the number of an inference workload revisions from a cluster. Supported for clusters v2.21+.","operationId":"count_inference_workload_revisions","tags":["Revisions"],"parameters":[{"$ref":"#/components/parameters/WorkloadId"},{"$ref":"#/components/parameters/Deleted"}],"responses":{"200":{"description":"Executed successfully.","content":{"application/json":{"schema":{"type":"object","required":["count"],"properties":{"count":{"type":"integer","format":"int64"}}}}}},"401":{"$ref":"#/components/responses/401Unauthorized"},"403":{"$ref":"#/components/responses/403Forbidden"},"500":{"$ref":"#/components/responses/500InternalServerError"},"503":{"$ref":"#/components/responses/503ServiceUnavailable"}}}}}}
```

## Get revision data. \[Experimental]

> Retrieve revision details using a revision id. Supported for clusters v2.21+.

```json
{"openapi":"3.0.3","info":{"title":"NVIDIA Run:ai","version":"2.22"},"tags":[{"name":"Revisions","description":"Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload."}],"servers":[{"url":"https://app.run.ai"}],"security":[{"bearerAuth":[]}],"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer","bearerFormat":"JWT","description":"Bearer authentication"}},"parameters":{"RevisionId":{"name":"revisionId","in":"path","required":true,"description":"The  Universally Unique Identifier (UUID) of the revision.","schema":{"type":"string","format":"uuid"}}},"schemas":{"Revision":{"type":"object","required":["type","name","id","workloadId","tenantId","clusterId","departmentId","projectId","createdAt","phase"],"properties":{"type":{"type":"string"},"name":{"type":"string"},"id":{"type":"string","format":"uuid"},"workloadId":{"type":"string","format":"uuid"},"tenantId":{"$ref":"#/components/schemas/TenantId"},"clusterId":{"$ref":"#/components/schemas/ClusterId"},"projectId":{"$ref":"#/components/schemas/ProjectId2"},"departmentId":{"$ref":"#/components/schemas/DepartmentId2"},"createdAt":{"type":"string","format":"date-time"},"deletedAt":{"type":"string","format":"date-time","nullable":true},"revisionRequestedResources":{"$ref":"#/components/schemas/WorkloadRequestResources"},"podsRequestedResources":{"$ref":"#/components/schemas/WorkloadRequestResources"},"requestedPods":{"$ref":"#/components/schemas/RequestedPods"},"requestedNodePools":{"type":"array","items":{"type":"string"}},"allocatedResources":{"$ref":"#/components/schemas/WorkloadAllocatedResources"},"currentNodePools":{"type":"array","items":{"type":"string"}},"runningPods":{"type":"integer","format":"int32"},"images":{"type":"array","items":{"type":"string"}},"environmentVariables":{"type":"object","additionalProperties":{"type":"string"}},"command":{"type":"string"},"arguments":{"type":"string"},"childrenIds":{"type":"array","writeOnly":true,"items":{"type":"object","required":["id"],"properties":{"id":{"type":"string","format":"uuid"},"type":{"type":"string"}}}},"conditions":{"$ref":"#/components/schemas/Conditions"},"phase":{"$ref":"#/components/schemas/Phase"},"phaseMessage":{"type":"string"},"phaseUpdatedAt":{"type":"string","format":"date-time"},"additionalFields":{"type":"object","additionalProperties":true}}},"TenantId":{"description":"The id of the tenant.","type":"integer","format":"int32"},"ClusterId":{"description":"The id of the cluster.","type":"string","format":"uuid"},"ProjectId2":{"description":"The id of the project.","type":"string"},"DepartmentId2":{"description":"The id of the department.","type":"string","minLength":1},"WorkloadRequestResources":{"type":"object","nullable":true,"properties":{"gpuRequestType":{"$ref":"#/components/schemas/GpuRequestType"},"gpu":{"$ref":"#/components/schemas/RequestResourceCores"},"gpuMemory":{"$ref":"#/components/schemas/RequestResourceQuantity"},"cpu":{"$ref":"#/components/schemas/RequestResourceCores"},"cpuMemory":{"$ref":"#/components/schemas/RequestResourceQuantity"},"migProfile":{"type":"array","nullable":true,"items":{"$ref":"#/components/schemas/MigProfile"}},"extendedResources":{"$ref":"#/components/schemas/WorkloadsExtendedResources"}}},"GpuRequestType":{"description":"Sets the unit type for GPU resources requests. Stated in terms of portion, memory or  mig profile [deprecated]. Sets the unit type for other GPU request fields. If `gpuDevicesRequest > 1`, only `portion` is supported. If `gpuDeviceRequest = 1`, the request type can be stated as `portion`, `memory` or `migProfile` [deprecated].","type":"string","minLength":1,"enum":["portion","memory","migProfile"],"nullable":true},"RequestResourceCores":{"type":"object","properties":{"limit":{"type":"number","nullable":true,"format":"double"},"request":{"type":"number","nullable":true,"format":"double"}},"nullable":true},"RequestResourceQuantity":{"type":"object","properties":{"limit":{"type":"string","nullable":true,"pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$"},"request":{"type":"string","nullable":true,"pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$"}},"nullable":true},"MigProfile":{"description":"Required only if `gpuRequestType` is `migProfile`. This states the memory profile to be used for the workload running NVIDIA Multi-Instance GPU (MIG) technology.","type":"string","deprecated":true,"minLength":1,"enum":["1g.5gb","1g.10gb","2g.10gb","2g.20gb","3g.20gb","3g.40gb","4g.20gb","4g.40gb","7g.40gb","7g.80gb"],"nullable":true},"WorkloadsExtendedResources":{"description":"Set of extended resources with their quantity","type":"array","items":{"$ref":"#/components/schemas/WorkloadsExtendedResource"},"nullable":true},"WorkloadsExtendedResource":{"description":"Quantity of an extended resource.","type":"object","properties":{"resource":{"description":"The name of the extended resource (mandatory)","type":"string","minLength":1,"nullable":true},"quantity":{"description":"The requested quantity for the given resource.","type":"string","minLength":1,"nullable":true},"exclude":{"description":"Whether to exclude this extended resource from the workload. This is necessary in case the extended resource is inherited from the policy defaults and it is desired not to include it in this workload.","type":"boolean","nullable":true}},"nullable":true},"RequestedPods":{"type":"object","properties":{"number":{"type":"integer","format":"int32","nullable":true},"min":{"type":"integer","format":"int32","nullable":true},"max":{"type":"integer","format":"int32","nullable":true},"parallelism":{"type":"integer","format":"int32","description":"specifies how many Pods can run in parallel","nullable":true},"completions":{"type":"integer","description":"specifies how many Pods should terminate successfully before the Workload is completed","format":"int32","nullable":true}}},"WorkloadAllocatedResources":{"type":"object","nullable":true,"properties":{"gpu":{"type":"number","nullable":true,"format":"double","description":"Required if and only if gpuRequestType is portion. States the number of GPUs allocated for the created workload. The default is no allocated GPUs."},"migProfile":{"type":"array","nullable":true,"items":{"$ref":"#/components/schemas/MigProfile"}},"gpuMemory":{"type":"string","pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$","nullable":true},"cpu":{"type":"number","nullable":true,"format":"double","description":"States the amount of CPU cores used by the workload running."},"cpuMemory":{"type":"string","pattern":"^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$","nullable":true},"extendedResources":{"$ref":"#/components/schemas/WorkloadsExtendedResources"}}},"Conditions":{"type":"array","items":{"$ref":"#/components/schemas/Condition1"}},"Condition1":{"type":"object","required":["type","status"],"properties":{"type":{"description":"The type of the condition, such as Failed or Available. See Types of domain status conditions.","type":"string"},"status":{"type":"string","description":"The status of the condition, such as True, False or Unknown."},"message":{"type":"string","description":"An optional, human-readable message providing more details about the condition."},"reason":{"type":"string","description":"The reason for the Failed condition. Not applicable to other types of condition."},"lastTransitionTime":{"description":"A timestamp of when the condition was created or the last time time the condition transitioned from one status to another.","type":"string","nullable":true,"format":"date-time"}}},"Phase":{"type":"string","enum":["Creating","Initializing","Resuming","Pending","Deleting","Running","Updating","Stopped","Stopping","Degraded","Failed","Completed","Terminating","Unknown"]},"Error":{"required":["code","message"],"properties":{"code":{"type":"integer","minimum":100,"maximum":599},"message":{"type":"string"},"details":{"type":"string"}}}},"responses":{"401Unauthorized":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"403Forbidden":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"404NotFound":{"description":"The specified resource was not found","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"500InternalServerError":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"503ServiceUnavailable":{"description":"unexpected error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}}},"paths":{"/api/v1/workloads/inferences/revisions/{revisionId}":{"get":{"summary":"Get revision data. [Experimental]","operationId":"get_revision","description":"Retrieve revision details using a revision id. Supported for clusters v2.21+.","tags":["Revisions"],"parameters":[{"$ref":"#/components/parameters/RevisionId"}],"responses":{"200":{"description":"Executed successfully.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Revision"}}}},"401":{"$ref":"#/components/responses/401Unauthorized"},"403":{"$ref":"#/components/responses/403Forbidden"},"404":{"$ref":"#/components/responses/404NotFound"},"500":{"$ref":"#/components/responses/500InternalServerError"},"503":{"$ref":"#/components/responses/503ServiceUnavailable"}}}}}}
```