Parasail

Parasail Dedicated Deployments API

Control-plane API for managing Parasail Dedicated and Dedicated Serverless deployments. Provision reserved GPU capacity (H100, A100, H200, etc.) running any Hugging Face or custom model, then list, retrieve, update, pause, resume, and delete deployments. Read-only API keys can list and retrieve but cannot mutate. Endpoint: /api/v1/dedicated/deployments.

Parasail Dedicated Deployments API is one of 3 APIs that Parasail publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 1 machine-runnable capability that can be deployed as REST, MCP, or Agent Skill surfaces via Naftiko and 1 JSON Schema definition.

Tagged areas include AI, Artificial Intelligence, GPU, Deployments, and Dedicated. The published artifact set on APIs.io includes API documentation, an OpenAPI specification, 1 Naftiko capability spec, and 1 JSON Schema.

Documentation GitHub OpenAPI

OpenAPI Specification

openapi: 3.1.0
info:
  title: Parasail Dedicated Deployments API
  description: |
    Control-plane API for managing Parasail Dedicated and Dedicated Serverless deployments.
    Create, list, retrieve, update, pause, resume, and delete reserved GPU deployments
    that run a chosen Hugging Face or custom model on isolated capacity.
  version: '1.0'
  contact:
    name: Parasail
    url: https://docs.parasail.io/parasail-docs/
servers:
  - url: https://api.parasail.io/api/v1
    description: Parasail Dedicated control plane
security:
  - bearerAuth: []
tags:
  - name: Deployments
    description: Manage dedicated GPU deployments for custom and reserved-capacity inference.
paths:
  /dedicated/deployments:
    get:
      tags: [Deployments]
      operationId: listDeployments
      summary: List Deployments
      description: List all dedicated deployments owned by the authenticated organization.
      responses:
        '200':
          description: A list of dedicated deployments.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Deployment'
    post:
      tags: [Deployments]
      operationId: createDeployment
      summary: Create Deployment
      description: Provision a new dedicated deployment of a chosen model on a chosen GPU device configuration.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeploymentCreateRequest'
      responses:
        '201':
          description: The created deployment.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
  /dedicated/deployments/{deployment_id}:
    get:
      tags: [Deployments]
      operationId: getDeployment
      summary: Retrieve Deployment
      description: Retrieve a dedicated deployment by ID.
      parameters:
        - in: path
          name: deployment_id
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The deployment.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
    put:
      tags: [Deployments]
      operationId: updateDeployment
      summary: Update Deployment
      description: Update mutable properties of a dedicated deployment (e.g. replicas, autoscaling).
      parameters:
        - in: path
          name: deployment_id
          required: true
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeploymentUpdateRequest'
      responses:
        '200':
          description: The updated deployment.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
    delete:
      tags: [Deployments]
      operationId: deleteDeployment
      summary: Delete Deployment
      description: Permanently delete a dedicated deployment and release its reserved GPU capacity.
      parameters:
        - in: path
          name: deployment_id
          required: true
          schema:
            type: string
      responses:
        '204':
          description: Deployment deleted.
  /dedicated/deployments/{deployment_id}/pause:
    post:
      tags: [Deployments]
      operationId: pauseDeployment
      summary: Pause Deployment
      description: Pause a dedicated deployment to stop billing while preserving configuration.
      parameters:
        - in: path
          name: deployment_id
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The paused deployment.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
  /dedicated/deployments/{deployment_id}/resume:
    post:
      tags: [Deployments]
      operationId: resumeDeployment
      summary: Resume Deployment
      description: Resume a previously-paused dedicated deployment.
      parameters:
        - in: path
          name: deployment_id
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The resumed deployment.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Send your Parasail API key as a Bearer token. Read-only keys can list and retrieve but cannot mutate.
  schemas:
    DeploymentCreateRequest:
      type: object
      required: [deploymentName, modelName, deviceConfigs, replicas]
      properties:
        deploymentName:
          type: string
          description: Human-readable name for the deployment.
        modelName:
          type: string
          description: Hugging Face model name or Parasail-recognised model ID to serve.
        deviceConfigs:
          type: array
          description: GPU device configurations to provision (count and SKU).
          items:
            type: object
            properties:
              device:
                type: string
                description: GPU SKU identifier (e.g. H100, A100, H200).
              count:
                type: integer
        replicas:
          type: integer
          description: Number of replicas to run.
        autoscaling:
          type: object
          properties:
            min_replicas:
              type: integer
            max_replicas:
              type: integer
    DeploymentUpdateRequest:
      type: object
      properties:
        replicas:
          type: integer
        autoscaling:
          type: object
          properties:
            min_replicas:
              type: integer
            max_replicas:
              type: integer
    Deployment:
      type: object
      properties:
        deployment_id:
          type: string
        deploymentName:
          type: string
        modelName:
          type: string
        status:
          type: string
          enum: [provisioning, running, paused, updating, deleting, failed]
        deviceConfigs:
          type: array
          items:
            type: object
            properties:
              device:
                type: string
              count:
                type: integer
        replicas:
          type: integer
        endpoint_url:
          type: string
          description: The OpenAI-compatible inference URL for this dedicated deployment.
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time

Parasail Dedicated Deployments API

Documentation

Specifications

Schemas & Data

Other Resources

OpenAPI Specification