CentML

CentML Deployments API

The Deployments API from CentML — 6 operation(s) for deployments.

GitHub OpenAPI

Operations 8

GET /deployments Lists all deployments for the account #
POST /deployments/inference Creates a dedicated inference deployment #
PUT /deployments/inference Updates an existing inference deployment #
GET /deployments/inference/{deployment_id} Retrieves an inference deployment by ID #
POST /deployments/compute Creates a compute deployment #
GET /deployments/status/{deployment_id} Gets the status of a deployment #
PUT /deployments/status/{deployment_id} Updates the status of a deployment (e.g. pause or delete) #
GET /deployments/logs/{deployment_id} Returns logs for a deployment #

Documentation

📖
Documentation
https://docs.centml.ai/apps/serverless
📖
APIReference
https://docs.centml.ai/clients/sdk
📖
APIReference
https://centml.ai/models/
📖
Documentation
https://docs.centml.ai/apps/inference

Specifications

⚙
OpenAPI
https://artifacts.apis.io/centml/openapi/centml-deployments-api-openapi.yml
⚙
AsyncAPI
https://artifacts.apis.io/centml/asyncapi/centml-asyncapi.yml

Other Resources

🔗
Postman
https://artifacts.apis.io/centml/collections/centml.postman_collection.json

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/centml:centml-deployments-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

centml-deployments-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: CentML Deployments API
  description: Specification of the CentML API surface.
  termsOfService: https://centml.ai/terms-of-service/
  contact:
    name: CentML Support
    url: https://docs.centml.ai/resources/requesting_support
  version: '1.0'
servers:
- url: https://api.centml.com/openai/v1
  description: OpenAI-compatible serverless inference base URL.
- url: https://api.centml.com
  description: CentML platform (control-plane) base URL for deployments and clusters.
security:
- bearerAuth: []
tags:
- name: Deployments
paths:
  /deployments:
    get:
      operationId: listDeployments
      tags:
      - Deployments
      summary: Lists all deployments for the account
      description: Platform control-plane endpoint. Returns all deployments (inference, compute, and job) for the authenticated account. Served at https://api.centml.com/deployments.
      servers:
      - url: https://api.centml.com
      parameters:
      - name: type
        in: query
        required: false
        description: Optional deployment type filter (e.g. inference, compute, job).
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentList'
  /deployments/inference:
    post:
      operationId: createInferenceDeployment
      tags:
      - Deployments
      summary: Creates a dedicated inference deployment
      description: Platform control-plane endpoint. Creates a dedicated, autoscaling inference deployment that serves a model as an HTTPS endpoint on a selected cluster and hardware instance. Served at https://api.centml.com/deployments/inference.
      servers:
      - url: https://api.centml.com
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateInferenceDeploymentRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
    put:
      operationId: updateInferenceDeployment
      tags:
      - Deployments
      summary: Updates an existing inference deployment
      servers:
      - url: https://api.centml.com
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateInferenceDeploymentRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
  /deployments/inference/{deployment_id}:
    get:
      operationId: getInferenceDeployment
      tags:
      - Deployments
      summary: Retrieves an inference deployment by ID
      servers:
      - url: https://api.centml.com
      parameters:
      - name: deployment_id
        in: path
        required: true
        description: The ID of the deployment to retrieve.
        schema:
          type: integer
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
  /deployments/compute:
    post:
      operationId: createComputeDeployment
      tags:
      - Deployments
      summary: Creates a compute deployment
      description: Platform control-plane endpoint to create a compute deployment. Served at https://api.centml.com/deployments/compute.
      servers:
      - url: https://api.centml.com
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateComputeDeploymentRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Deployment'
  /deployments/status/{deployment_id}:
    get:
      operationId: getDeploymentStatus
      tags:
      - Deployments
      summary: Gets the status of a deployment
      servers:
      - url: https://api.centml.com
      parameters:
      - name: deployment_id
        in: path
        required: true
        schema:
          type: integer
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentStatus'
    put:
      operationId: updateDeploymentStatus
      tags:
      - Deployments
      summary: Updates the status of a deployment (e.g. pause or delete)
      servers:
      - url: https://api.centml.com
      parameters:
      - name: deployment_id
        in: path
        required: true
        schema:
          type: integer
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeploymentStatus'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentStatus'
  /deployments/logs/{deployment_id}:
    get:
      operationId: getDeploymentLogs
      tags:
      - Deployments
      summary: Returns logs for a deployment
      servers:
      - url: https://api.centml.com
      parameters:
      - name: deployment_id
        in: path
        required: true
        schema:
          type: integer
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentLogs'
components:
  schemas:
    CreateComputeDeploymentRequest:
      type: object
      required:
      - name
      - cluster_id
      - hardware_instance_id
      properties:
        name:
          type: string
        cluster_id:
          type: integer
        hardware_instance_id:
          type: integer
    Deployment:
      type: object
      properties:
        id:
          type: integer
          description: The unique deployment ID.
        name:
          type: string
          description: Human-readable deployment name.
        type:
          type: string
          description: Deployment type (inference, compute, or job).
        status:
          type: string
          description: Current deployment status (e.g. running, paused, deleted).
        cluster_id:
          type: integer
          description: The cluster the deployment is placed on.
        endpoint_url:
          type: string
          description: The HTTPS endpoint URL once the deployment is ready.
    DeploymentStatus:
      type: object
      properties:
        id:
          type: integer
        status:
          type: string
          description: The deployment status to read or set (e.g. running, paused, deleted).
    DeploymentList:
      type: object
      properties:
        results:
          type: array
          items:
            $ref: '#/components/schemas/Deployment'
    CreateInferenceDeploymentRequest:
      type: object
      required:
      - name
      - cluster_id
      - hardware_instance_id
      properties:
        name:
          type: string
          description: A name for the inference deployment.
        cluster_id:
          type: integer
          description: ID of the cluster to deploy to (from GET /clusters).
        hardware_instance_id:
          type: integer
          description: ID of the GPU hardware instance (from GET /capacity).
        model:
          type: string
          description: The model or image to serve.
        min_replicas:
          type: integer
          description: Minimum number of replicas for autoscaling.
        max_replicas:
          type: integer
          description: Maximum number of replicas for autoscaling.
    DeploymentLogs:
      type: object
      properties:
        logs:
          type: string
          description: Log output for the deployment.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: CentML API key
      description: 'Set the `Authorization: Bearer <CENTML_API_KEY>` header. Serverless inference uses a serverless token; the platform API uses an account access token. Both are issued from the CentML platform.'