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

# Stop deployment



## OpenAPI

````yaml /api-reference/openapi.json post /v1/deployments/{deployment_id}/stop
openapi: 3.1.0
info:
  title: Veri API
  description: >-
    REST API for the Veri RL post-training platform. All requests require a
    Bearer API key (`vk_` prefix).
  license:
    name: ''
  version: 0.1.0
servers:
  - url: https://api.veri.studio
    description: Production
security: []
tags:
  - name: Training jobs
    description: Create, monitor, and manage training jobs.
  - name: Datasets
    description: Upload and connect training datasets.
  - name: Reward functions
    description: Upload and manage reward functions.
  - name: Deployments
    description: Serve trained models and run inference.
  - name: Evaluations
    description: Score models against datasets and benchmarks.
  - name: Volumes
    description: Persistent file storage mounted into jobs.
  - name: Models
    description: Custom model registry deployments serve from.
  - name: Regions
    description: Discover available launch regions.
  - name: GPU
    description: Live GPU availability by provider and region.
  - name: Code artifacts
    description: Upload custom training script bundles.
  - name: Billing
    description: Credit balance and transaction history.
  - name: API keys
    description: Create and revoke API keys.
  - name: Account
    description: The authenticated caller's identity.
  - name: SSH keys
    description: Manage SSH key pairs for compute access.
  - name: Settings
    description: Account-level integrations (Weights & Biases).
paths:
  /v1/deployments/{deployment_id}/stop:
    post:
      tags:
        - Deployments
      summary: Stop deployment
      operationId: stop
      parameters:
        - name: deployment_id
          in: path
          description: Deployment ID
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The stopped deployment
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentResponse'
        '404':
          description: Not found or not owned by the caller
      security:
        - bearerAuth: []
components:
  schemas:
    DeploymentResponse:
      type: object
      required:
        - object
        - id
        - status
        - name
        - model
        - source
        - created_at
        - updated_at
      properties:
        object:
          type: string
        id:
          type: string
        status:
          $ref: '#/components/schemas/DeploymentStatus'
        name:
          type: string
        model:
          type: string
        source:
          type: string
        source_model_id:
          type:
            - string
            - 'null'
          description: |-
            For a custom_model deployment, the saved model this was created from
            (provenance). Null for other sources.
        endpoint_url:
          type:
            - string
            - 'null'
        gpu:
          oneOf:
            - type: 'null'
            - $ref: '#/components/schemas/GpuInfo'
        provider:
          type:
            - string
            - 'null'
        engine:
          type:
            - string
            - 'null'
        num_replicas:
          type: integer
          format: int32
          description: >-
            VS-341: DESIRED replica count (GPU boxes) behind this deployment.
            The

            observed count is ready_replicas — the K8s spec/status split; the
            CLI

            renders "ready/desired" (e.g. 2/3).
        ready_replicas:
          type: integer
          format: int32
          description: 'Observed: replicas currently serving with a routable endpoint.'
        min_replicas:
          type: integer
          format: int32
          description: Replica-count bounds. min == max => fixed N (autoscaling off).
        max_replicas:
          type: integer
          format: int32
        concurrency_target:
          type:
            - number
            - 'null'
          format: double
          description: >-
            Per-replica concurrency setpoint (stored as
            target_ongoing_requests).
        scale_to_zero_window_seconds:
          type:
            - integer
            - 'null'
          format: int32
          description: 'VS-313: idle window before a min=0 deployment parks (None = 3600s).'
        idle_delete_after_days:
          type:
            - integer
            - 'null'
          format: int32
          description: 'VS-313: parked-deployment GC in days (None = kept forever).'
        cost_per_hour_usd:
          type:
            - number
            - 'null'
          format: double
        total_cost_usd:
          type:
            - number
            - 'null'
          format: double
        total_requests:
          type: integer
          format: int32
        error:
          type:
            - string
            - 'null'
        started_at:
          type:
            - string
            - 'null'
          format: date-time
        stopped_at:
          type:
            - string
            - 'null'
          format: date-time
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
    DeploymentStatus:
      type: string
      enum:
        - queued
        - provisioning
        - serving
        - unhealthy
        - stopped
        - failed
        - scaled_to_zero
        - waking
    GpuInfo:
      type: object
      description: |-
        Pydantic `GPUInfo` (with `type` field). Rust uses `gpu_type` internally
        but serializes as "type" for JSON parity.
      required:
        - type
        - count
      properties:
        type:
          type: string
        count:
          type: integer
          format: int32
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key
      description: API key with the `vk_` prefix. Create one from the dashboard.

````