> ## Documentation Index > Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt > Use this file to discover all available pages before exploring further. # List All Model Deployments > TODO: Document ## OpenAPI ````yaml https://app.stainlessapi.com/api/spec/documented/sgp/openapi.yml get /v4/model-deployments openapi: 3.1.0 info: title: EGP API V4 description: >- This is the parent API for all EGP APIs. If you are looking for the EGP API, please go to https://api.egp.scale.com/docs. contact: name: Scale Generative AI Platform url: https://scale.com/genai-platform version: 0.1.0 servers: - url: https://api.egp.scale.com security: [] tags: - name: Models description: Model API. paths: /v4/model-deployments: get: tags: - Models summary: List All Model Deployments description: 'TODO: Document' operationId: GET-V4-/model-deployments parameters: - name: sort_by in: query required: false schema: anyOf: - type: array items: $ref: '#/components/schemas/SortByEnumForModelDeployment' - type: 'null' title: Sort By - name: page in: query required: false schema: type: integer minimum: 1 description: >- Page number for pagination to be returned by the given endpoint. Starts at page 1 default: 1 title: Page description: >- Page number for pagination to be returned by the given endpoint. Starts at page 1 - name: limit in: query required: false schema: type: integer maximum: 10000 minimum: 1 description: >- Maximum number of artifacts to be returned by the given endpoint. Defaults to 100 and cannot be greater than 10k. default: 100 title: Limit description: >- Maximum number of artifacts to be returned by the given endpoint. Defaults to 100 and cannot be greater than 10k. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedModelDeploymentResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: Python source: |- import os from scale_gp import SGPClient client = SGPClient( api_key=os.environ.get("SGP_API_KEY"), # This is the default and can be omitted ) page = client.models.deployments.list_all() page = page.items[0] print(page.id) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/stainless-sdks/sgp-go\"\n\t\"github.com/stainless-sdks/sgp-go/option\"\n)\n\nfunc main() {\n\tclient := sgp.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tpage, err := client.Models.Deployments.ListAll(context.TODO(), sgp.ModelDeploymentListAllParams{})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", page)\n}\n" components: schemas: SortByEnumForModelDeployment: type: string enum: - model_creation_parameters:asc - model_creation_parameters:desc - model_endpoint_id:asc - model_endpoint_id:desc - model_instance_id:asc - model_instance_id:desc - vendor_configuration:asc - vendor_configuration:desc - deployment_metadata:asc - deployment_metadata:desc - status:asc - status:desc - id:asc - id:desc - created_at:asc - created_at:desc - account_id:asc - account_id:desc - created_by_user_id:asc - created_by_user_id:desc - created_by_identity_type:asc - created_by_identity_type:desc - name:asc - name:desc title: SortByEnumForModelDeployment PaginatedModelDeploymentResponse: properties: items: items: $ref: '#/components/schemas/ModelDeploymentResponse' type: array title: Items description: The data returned for the current page. total_item_count: type: integer title: Total Item Count description: The total number of items of the query current_page: type: integer title: Current Page description: The current page number. items_per_page: type: integer title: Items Per Page description: The number of items per page. type: object required: - items - total_item_count - current_page - items_per_page title: PaginatedModelDeploymentResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ModelDeploymentResponse: properties: name: type: string title: Name model_creation_parameters: title: Model Creation Parameters additionalProperties: true type: object model_endpoint_id: title: Model Endpoint Id type: string model_instance_id: title: Model Instance Id type: string vendor_configuration: $ref: '#/components/schemas/DeploymentVendorConfiguration' deployment_metadata: title: Deployment Metadata additionalProperties: true type: object id: type: string title: Id description: The unique identifier of the entity. created_at: type: string format: date-time title: Created At description: The date and time when the entity was created in ISO format. account_id: title: Account Id description: The ID of the account that owns the given entity. can_patch: false optional_in_request: true type: string created_by_user_id: type: string title: Created By User Id description: The user who originally created the entity. created_by_identity_type: $ref: '#/components/schemas/IdentifierTypeEnum' description: The type of identity that created the entity. status: type: string title: Status description: Status of the model's deployment. type: object required: - name - id - created_at - account_id - created_by_user_id - created_by_identity_type - status title: ModelDeploymentResponse ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context additionalProperties: true type: object required: - loc - msg - type title: ValidationError DeploymentVendorConfiguration: oneOf: - $ref: '#/components/schemas/LaunchDeploymentVendorConfiguration' - $ref: '#/components/schemas/LLMEngineDeploymentVendorConfiguration' title: DeploymentVendorConfiguration discriminator: propertyName: vendor mapping: LAUNCH: $ref: '#/components/schemas/LaunchDeploymentVendorConfiguration' LLMENGINE: $ref: '#/components/schemas/LLMEngineDeploymentVendorConfiguration' IdentifierTypeEnum: type: string enum: - user - service_account title: IdentifierTypeEnum LaunchDeploymentVendorConfiguration: properties: min_workers: type: integer title: Min Workers default: 0 max_workers: type: integer title: Max Workers default: 1 per_worker: type: integer title: Per Worker description: >- The maximum number of concurrent requests that an individual worker can service. Launch automatically scales the number of workers for the endpoint so that each worker is processing ``per_worker`` requests, subject to the limits defined by ``min_workers`` and ``max_workers``. - If the average number of concurrent requests per worker is lower than ``per_worker``, then the number of workers will be reduced. - Otherwise, if the average number of concurrent requests per worker is higher than ``per_worker``, then the number of workers will be increased to meet the elevated traffic. Here is our recommendation for computing ``per_worker``: 1. Compute ``min_workers`` and ``max_workers`` per your minimum and maximum throughput requirements. 2. Determine a value for the maximum number of concurrent requests in the workload. Divide this number by ``max_workers``. Doing this ensures that the number of workers will "climb" to ``max_workers``. default: 10 vendor: type: string const: LAUNCH title: Vendor default: LAUNCH type: object title: LaunchDeploymentVendorConfiguration LLMEngineDeploymentVendorConfiguration: properties: cpus: type: integer title: Cpus default: 3 memory: type: string title: Memory default: 8Gi storage: type: string title: Storage default: 16Gi gpus: type: integer title: Gpus default: 0 gpu_type: $ref: '#/components/schemas/GPUType' min_workers: type: integer title: Min Workers default: 0 max_workers: type: integer title: Max Workers default: 1 per_worker: type: integer title: Per Worker description: >- The maximum number of concurrent requests that an individual worker can service. Launch automatically scales the number of workers for the endpoint so that each worker is processing ``per_worker`` requests, subject to the limits defined by ``min_workers`` and ``max_workers``. - If the average number of concurrent requests per worker is lower than ``per_worker``, then the number of workers will be reduced. - Otherwise, if the average number of concurrent requests per worker is higher than ``per_worker``, then the number of workers will be increased to meet the elevated traffic. Here is our recommendation for computing ``per_worker``: 1. Compute ``min_workers`` and ``max_workers`` per your minimum and maximum throughput requirements. 2. Determine a value for the maximum number of concurrent requests in the workload. Divide this number by ``max_workers``. Doing this ensures that the number of workers will "climb" to ``max_workers``. default: 10 vendor: type: string const: LLMENGINE title: Vendor default: LLMENGINE high_priority: title: High Priority default: false type: boolean num_shards: type: integer title: Num Shards default: 4 checkpoint_path: title: Checkpoint Path type: string model_name: title: Model Name type: string base_model_name: title: Base Model Name type: string inference_framework_image_tag: title: Inference Framework Image Tag type: string type: object title: LLMEngineDeploymentVendorConfiguration GPUType: type: string enum: - nvidia-tesla-t4 - nvidia-ampere-a10 - nvidia-ampere-a100 - nvidia-ampere-a100e - nvidia-hopper-h100 - nvidia-hopper-h100-1g20gb - nvidia-hopper-h100-3g40gb title: GPUType ````