> ## Documentation Index > Fetch the complete documentation index at: https://docs.together.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get the full configuration of a specific revision > Returns the deployment configuration defined by the specified revision. Only the 50 most recent revisions per deployment retain their configuration; older revisions return 404 even while they still appear in the revision history. The deployment's currently active revision is always available, regardless of age. ## OpenAPI ````yaml openapi.yaml GET /v1/deployments/{id}/revisions/{revisionIdentifier} openapi: 3.1.0 info: title: Together APIs description: The Together REST API. See https://docs.together.ai for more details. version: 2.0.0 termsOfService: https://www.together.ai/terms-of-service contact: name: Together Support url: https://www.together.ai/contact license: name: MIT url: https://github.com/togethercomputer/openapi/blob/main/LICENSE servers: - url: https://api.together.ai description: Default environment for APIs security: - bearerAuth: [] paths: /v1/deployments/{id}/revisions/{revisionIdentifier}: get: tags: - Deployments summary: Get the full configuration of a specific revision description: >- Returns the deployment configuration defined by the specified revision. Only the 50 most recent revisions per deployment retain their configuration; older revisions return 404 even while they still appear in the revision history. The deployment's currently active revision is always available, regardless of age. parameters: - name: id in: path required: true schema: description: Deployment ID or name. type: string - name: revisionIdentifier in: path required: true schema: description: Revision number or revision ID. type: string responses: '200': description: Configuration of the specified revision content: application/json: schema: $ref: '#/components/schemas/RevisionDetailResponse' '400': description: Invalid revision identifier content: application/json: schema: type: object '404': description: Deployment not found, or revision not found / no longer retained content: application/json: schema: type: object '500': description: Internal server error content: application/json: schema: type: object x-codeSamples: - lang: Python label: Together AI SDK (Python) source: > from together import Together client = Together() # Pass a revision number or a revision ID. revision = client.beta.jig.retrieve_revision("3", id="my-deployment") print(revision.image, revision.min_replicas, revision.max_replicas) - lang: TypeScript label: Together AI SDK (TypeScript) source: > import Together from "together-ai"; const client = new Together(); // Pass a revision number or a revision ID. const revision = await client.beta.jig.retrieveRevision("3", { id: "my-deployment", }); console.log(revision.image, revision.min_replicas, revision.max_replicas); - lang: JavaScript label: Together AI SDK (JavaScript) source: > import Together from "together-ai"; const client = new Together(); // Pass a revision number or a revision ID. const revision = await client.beta.jig.retrieveRevision("3", { id: "my-deployment", }); console.log(revision.image, revision.min_replicas, revision.max_replicas); components: schemas: RevisionDetailResponse: description: Deployment configuration captured for one retained revision. required: - object - revision_id - image - min_replicas - max_replicas - port - protocol - capacity_type - command - args - environment_variables - volumes - gpu_type - gpu_count - cpu - memory - storage - health_check_path - created_at properties: object: description: The object type, which is always `revision`. const: revision revision_id: description: Unique revision identifier. type: string image: description: Container image used by this revision. type: string min_replicas: description: Minimum number of replicas configured for this revision. type: integer max_replicas: description: Maximum number of replicas configured for this revision. type: integer port: description: Container port exposed by this revision. type: integer protocol: description: Network protocol served by the deployment revision. type: string capacity_type: description: Capacity behavior for replicas above reserved capacity. enum: - stable - preemptible type: string command: description: Entrypoint command run by the container. items: type: string type: array args: description: Arguments passed to the container command. items: type: string type: array environment_variables: description: Environment variables configured on this revision. items: $ref: '#/components/schemas/EnvironmentVariable' type: array volumes: description: Volume mounts attached to this revision. items: $ref: '#/components/schemas/VolumeMount' type: array gpu_type: description: GPU hardware type configured for this revision. type: string gpu_count: description: Number of GPUs allocated to each replica. type: integer cpu: description: CPU cores allocated to each replica. type: number memory: description: Memory allocated to each replica in GiB. type: number storage: description: Ephemeral storage allocated to each replica. type: integer health_check_path: description: HTTP path used for health checks. type: string autoscaling: description: Autoscaling configuration captured for this revision. oneOf: - $ref: '#/components/schemas/HTTPAutoscalingConfig' - $ref: '#/components/schemas/QueueAutoscalingConfig' - $ref: '#/components/schemas/CustomMetricAutoscalingConfig' termination_grace_period_seconds: description: >- Seconds to wait for graceful shutdown before forcefully terminating a replica. type: integer created_at: description: Time when this revision was created. type: string format: date-time type: object EnvironmentVariable: properties: name: description: >- Name is the environment variable name (e.g., "DATABASE_URL"). Must start with a letter or underscore, followed by letters, numbers, or underscores type: string value: description: >- Value is the plain text value for the environment variable. Use this for non-sensitive values. Either Value or ValueFromSecret must be set, but not both type: string value_from_secret: description: >- ValueFromSecret references a secret by name or ID to use as the value. Use this for sensitive values like API keys or passwords. Either Value or ValueFromSecret must be set, but not both type: string required: - name type: object VolumeMount: properties: mount_path: description: >- MountPath is the path in the container where the volume mounts (e.g., "/data"). type: string name: description: >- Name is the name of the volume to mount. Must reference an existing volume by name or ID type: string version: description: >- Version is the volume version to mount. On create, defaults to the latest version. On update, defaults to the currently mounted version. type: integer required: - mount_path - name type: object HTTPAutoscalingConfig: description: >- Autoscaling config for HTTPTotalRequests and HTTPAvgRequestDuration metrics properties: metric: description: Metric must be HTTPTotalRequests or HTTPAvgRequestDuration enum: - HTTPTotalRequests - HTTPAvgRequestDuration example: HTTPTotalRequests type: string target: description: >- Target is the threshold value. Default: 100 for HTTPTotalRequests, 500 (ms) for HTTPAvgRequestDuration example: 100 type: number time_interval_minutes: description: 'TimeIntervalMinutes is the rate window in minutes. Default: 10' example: 10 type: integer type: object QueueAutoscalingConfig: description: Autoscaling config for QueueBacklogPerWorker metric properties: metric: description: Metric must be QueueBacklogPerWorker enum: - QueueBacklogPerWorker example: QueueBacklogPerWorker type: string model: description: >- Model overrides the model name for queue status lookup. Defaults to the deployment app name type: string target: description: 'Target is the threshold value. Default: 1.01' example: 1.01 type: number type: object CustomMetricAutoscalingConfig: description: Autoscaling config for CustomMetric metric properties: custom_metric_name: description: >- CustomMetricName is the Prometheus metric name. Must match [a-zA-Z_:][a-zA-Z0-9_:]* example: my_custom_metric type: string metric: description: Metric must be CustomMetric enum: - CustomMetric example: CustomMetric type: string target: description: 'Target is the threshold value. Default: 500' example: 500 type: number type: object securitySchemes: bearerAuth: type: http scheme: bearer x-bearer-format: bearer x-default: default ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.