openapi: 3.0.0
info:
  title: Create Workergroup API
  description: Creates a new workergroup configuration for serverless endpoints
  version: 1.0.0
servers:
- url: https://console.vast.ai
  description: Production server
paths:
  /api/v0/workergroups/:
    post:
      summary: create workergroup
      description: |
        Creates a new workergroup configuration that manages worker instances for a serverless endpoint.

        CLI Usage: `vastai create workergroup --template_hash <hash> --endpoint_name <name> [options]`
      security:
      - BearerAuth: []
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                endpoint_name:
                  type: string
                  description: Name of the endpoint group
                  example: vLLM-Qwen3-8B
                endpoint_id:
                  type: integer
                  description: ID of existing endpoint group (alternative to endpoint_name)
                  example: 123
                template_hash:
                  type: string
                  description: Hash ID of template to use for worker instances
                  example: abc123def456
                template_id:
                  type: integer
                  description: ID of template (alternative to template_hash)
                  example: 456
                search_params:
                  type: string
                  description: Search query for finding worker instances (alternative
                    to template)
                  default: 'verified=true rentable=true rented=false'
                  example: gpu_name=RTX_3090 rentable=true
                launch_args:
                  type: string
                  description: Additional launch arguments for worker instances
                  example: "--env VAR=value"
                min_load:
                  type: number
                  description: Minimum load threshold for scaling
                  default: 1.0
                  example: 1.0
                target_util:
                  type: number
                  description: Target GPU utilization
                  default: 0.9
                  example: 0.9
                cold_mult:
                  type: number
                  description: Cold start multiplier
                  default: 3.0
                  example: 3.0
                cold_workers:
                  type: integer
                  description: Number of cold workers to maintain
                  default: 3
                  example: 3
                max_workers:
                  type: integer
                  description: Maximum number of worker instances
                  default: 20
                  example: 20
                test_workers:
                  type: integer
                  description: Number of test workers
                  default: 3
                  example: 3
                gpu_ram:
                  type: integer
                  description: Minimum GPU RAM in GB
                  default: 24
                  example: 24
      responses:
        '200':
          description: Successfully created workergroup
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: true
                  id:
                    type: integer
                    description: ID of created autoscaling job
                    example: 789
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: false
                  error:
                    type: string
                    enum:
                    - invalid_args
                  msg:
                    type: string
                    example: Please assign your workergroup to a valid endpoint identifier
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Too Many Requests
          content:
            application/json:
              schema:
                type: object
                properties:
                  detail:
                    type: string
                    example: API requests too frequent endpoint threshold=4.0
      tags:
      - Serverless
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: API key must be provided in the Authorization header
  schemas:
    Error:
      type: object
      properties:
        success:
          type: boolean
          example: false
        error:
          type: string
        msg:
          type: string
x-rate-limit:
  threshold: 4.0
  per: request
  description: Maximum request frequency per IP address
x-cli-commands:
- name: create workergroup
  description: Create a new workergroup
  endpoint: /api/v0/workergroups/
  method: POST
  example: vast-ai create workergroup --template_hash abc123 --endpoint_name "vLLM-Qwen3-8B"
    --test_workers 5