> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyceum.technology/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Dedicated Deployment



## OpenAPI

````yaml /api-reference/openapi.json post /api/v2/external/inference/create
openapi: 3.1.0
info:
  title: Lyceum Cloud Execution API
  version: 0.1.0
servers: []
security: []
paths:
  /api/v2/external/inference/create:
    post:
      tags:
        - Dedicated Inference
      summary: Create Dedicated Deployment
      operationId: create_dedicated_deployment_api_v2_external_inference_create_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeployCreationReq'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeployCreationResp'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    DeployCreationReq:
      properties:
        hf_model_id:
          type: string
          title: Hf Model Id
          description: HuggingFace model ID, e.g. 'meta-llama/Llama-3.2-1B'
        hf_token:
          anyOf:
            - type: string
            - type: 'null'
          title: Hf Token
          description: HuggingFace token for gated models
        min_replicas:
          type: integer
          minimum: 1
          title: Min Replicas
          description: Minimum replicas to keep running
          default: 1
        max_replicas:
          type: integer
          minimum: 1
          title: Max Replicas
          description: Maximum replicas allowed
          default: 1
        target_rps:
          type: number
          title: Target Rps
          description: Target requests per second per replica for scale-up
        target_latency_p95_ms:
          type: number
          title: Target Latency P95 Ms
          description: Target p95 latency in milliseconds for scale-up
        stabilisation_window:
          type: integer
          title: Stabilisation Window
          description: Stabilisation window in seconds for scale-down
        gpu_type:
          type: string
          title: Gpu Type
          description: GPU type, e.g. 'h100', 'a100'
        gpu_count:
          type: integer
          minimum: 1
          title: Gpu Count
          description: Number of GPUs per replica
          default: 1
        gpu_vram_gb:
          anyOf:
            - type: integer
              minimum: 1
            - type: 'null'
          title: Gpu Vram Gb
          description: GPU VRAM in GB per GPU
        vllm_args:
          anyOf:
            - type: string
            - type: 'null'
          title: Vllm Args
          description: Extra vLLM engine args, comma-separated without leading --
      type: object
      required:
        - hf_model_id
        - target_rps
        - target_latency_p95_ms
        - stabilisation_window
        - gpu_type
      title: DeployCreationReq
      description: Request body for POST /api/v2/external/inference/create.
    DeployCreationResp:
      properties:
        deployment_id:
          type: string
          format: uuid
          title: Deployment Id
          description: Stable UUID used for all subsequent inference calls
        status:
          type: string
          title: Status
          description: Initial deployment status, e.g. 'pending'
      type: object
      required:
        - deployment_id
        - status
      title: DeployCreationResp
      description: Response body for POST /api/v2/external/inference/create.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    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
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError

````