> ## 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. # Get Model ## OpenAPI ````yaml https://api.dev-sgp.scale.com/openapi-versions/v5/openapi.json get /v5/models/{model_id} openapi: 3.1.0 info: title: EGP API V5 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: [] paths: /v5/models/{model_id}: get: tags: - Models summary: Get Model operationId: GET-V5-/v5/models/model_id parameters: - name: model_id in: path required: true schema: type: string title: Model Id - name: x-selected-account-id in: header required: false schema: anyOf: - type: string - type: 'null' title: Account ID Header responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/InferenceModel' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: InferenceModel: properties: id: type: string title: Id object: type: string const: model title: Object default: model name: type: string title: Name model_type: $ref: '#/components/schemas/InferenceModelType' model_vendor: $ref: '#/components/schemas/InferenceModelVendor' vendor_configuration: anyOf: - $ref: '#/components/schemas/LaunchVendorConfiguration' - $ref: '#/components/schemas/LLMEngineVendorConfiguration' title: Vendor Configuration status: $ref: '#/components/schemas/InferenceModelStatus' status_reason: title: Status Reason type: string model_metadata: title: Model Metadata additionalProperties: true type: object model_availability: $ref: '#/components/schemas/InferenceModelAvailability' created_at: type: string format: date-time title: Created At created_by_user_id: title: Created By User Id type: string created_by_identity_type: $ref: '#/components/schemas/IdentifierTypeEnum' type: object required: - name - model_type - model_vendor - status - id - created_at - created_by_user_id - created_by_identity_type HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError InferenceModelType: type: string enum: - generic - completion - chat_completion title: InferenceModelType InferenceModelVendor: type: string enum: - openai - cohere - vertex_ai - anthropic - azure - gemini - launch - llmengine - model_zoo - bedrock - xai - fireworks_ai title: InferenceModelVendor LaunchVendorConfiguration: properties: model_image: $ref: '#/components/schemas/LaunchModelBundleConfiguration' model_infra: $ref: '#/components/schemas/LaunchModelEndpointConfiguration' type: object required: - model_image - model_infra title: LaunchVendorConfiguration LLMEngineVendorConfiguration: properties: model: type: string title: Model inference_framework_image_tag: type: string title: Inference Framework Image Tag default: latest nodes_per_worker: type: integer title: Nodes Per Worker default: 1 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 default: 2 num_shards: type: integer title: Num Shards default: 1 labels: additionalProperties: type: string type: object title: Labels default: {} source: type: string title: Source default: hugging_face inference_framework: type: string title: Inference Framework default: vllm endpoint_type: type: string title: Endpoint Type default: streaming quantize: title: Quantize type: string checkpoint_path: title: Checkpoint Path type: string chat_template_override: title: Chat Template Override type: string post_inference_hooks: title: Post Inference Hooks items: type: string type: array cpus: title: Cpus type: integer gpus: title: Gpus type: integer memory: title: Memory type: string gpu_type: title: Gpu Type type: string storage: title: Storage type: string high_priority: title: High Priority default: false type: boolean default_callback_url: title: Default Callback Url type: string public_inference: title: Public Inference type: boolean additionalProperties: true type: object required: - model title: LLMEngineVendorConfiguration InferenceModelStatus: type: string enum: - failed - ready - deploying - deployment_timeout title: InferenceModelStatus InferenceModelAvailability: type: string enum: - unknown - available - unavailable title: InferenceModelAvailability IdentifierTypeEnum: type: string enum: - user - service_account title: IdentifierTypeEnum ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: title: Error Type type: string input: title: Input ctx: type: object title: Context additionalProperties: true type: object required: - loc - msg - type title: ValidationError LaunchModelBundleConfiguration: properties: registry: type: string title: Registry repository: type: string title: Repository tag: type: string title: Tag predict_route: type: string title: Predict Route default: /predict command: items: type: string type: array title: Command streaming_predict_route: title: Streaming Predict Route type: string streaming_command: title: Streaming Command items: type: string type: array request_schema: additionalProperties: true type: object title: Request Schema default: {} response_schema: additionalProperties: true type: object title: Response Schema default: {} env_vars: additionalProperties: true type: object title: Env Vars default: {} readiness_delay: type: integer title: Readiness Delay default: 120 healthcheck_route: type: string title: Healthcheck Route default: /readyz type: object required: - registry - repository - tag - command title: LaunchModelBundleConfiguration LaunchModelEndpointConfiguration: properties: endpoint_type: type: string enum: - async - sync - streaming title: Endpoint Type default: sync cpus: anyOf: - type: string - type: integer title: Cpus default: 3 gpus: type: integer title: Gpus default: 0 gpu_type: title: Gpu Type 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 memory: type: string title: Memory default: 8Gi storage: type: string title: Storage default: 16Gi 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 default: 10 high_priority: title: High Priority default: false type: boolean labels: title: Labels additionalProperties: type: string type: object public_inference: title: Public Inference default: false type: boolean type: object title: LaunchModelEndpointConfiguration securitySchemes: APIKeyHeader: type: apiKey in: header name: x-api-key ````