CentML

opencollection: 1.0.0
info:
  name: CentML API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Creates a model response for the given chat conversation.
      type: http
    http:
      method: POST
      url: https://api.centml.com/openai/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: OpenAI-compatible chat completions on CentML serverless endpoints. Set stream=true for Server-Sent Events.
- info:
    name: Completions
    type: folder
  items:
  - info:
      name: Creates a completion for the provided prompt.
      type: http
    http:
      method: POST
      url: https://api.centml.com/openai/v1/completions
      body:
        type: json
        data: '{}'
    docs: OpenAI-compatible text completions on CentML serverless endpoints.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: Lists the models available on CentML serverless endpoints.
      type: http
    http:
      method: GET
      url: https://api.centml.com/openai/v1/models
    docs: Returns the model IDs available to the account on the serverless API.
  - info:
      name: Retrieves a model instance.
      type: http
    http:
      method: GET
      url: https://api.centml.com/openai/v1/models/:model
      params:
      - name: model
        value: ''
        type: path
        description: The ID of the model to retrieve.
    docs: Returns metadata for a single model by ID.
- info:
    name: Deployments
    type: folder
  items:
  - info:
      name: Lists all deployments for the account.
      type: http
    http:
      method: GET
      url: https://api.centml.com/deployments
    docs: Platform control-plane endpoint. Lists inference, compute, and job deployments.
  - info:
      name: Creates a dedicated inference deployment.
      type: http
    http:
      method: POST
      url: https://api.centml.com/deployments/inference
      body:
        type: json
        data: '{}'
    docs: Creates a dedicated, autoscaling inference deployment on a selected cluster and hardware instance.
  - info:
      name: Retrieves an inference deployment by ID.
      type: http
    http:
      method: GET
      url: https://api.centml.com/deployments/inference/:deployment_id
      params:
      - name: deployment_id
        value: ''
        type: path
        description: The ID of the deployment to retrieve.
    docs: Retrieves a single inference deployment.
  - info:
      name: Creates a compute deployment.
      type: http
    http:
      method: POST
      url: https://api.centml.com/deployments/compute
      body:
        type: json
        data: '{}'
    docs: Creates a compute deployment.
  - info:
      name: Gets the status of a deployment.
      type: http
    http:
      method: GET
      url: https://api.centml.com/deployments/status/:deployment_id
      params:
      - name: deployment_id
        value: ''
        type: path
    docs: Returns the current status of a deployment.
  - info:
      name: Returns logs for a deployment.
      type: http
    http:
      method: GET
      url: https://api.centml.com/deployments/logs/:deployment_id
      params:
      - name: deployment_id
        value: ''
        type: path
    docs: Returns log output for a deployment.
- info:
    name: Clusters
    type: folder
  items:
  - info:
      name: Lists the regional clusters available to the account.
      type: http
    http:
      method: GET
      url: https://api.centml.com/clusters
    docs: Platform control-plane endpoint. Lists managed regional clusters for placing deployments.
  - info:
      name: Lists available GPU capacity and hardware instances.
      type: http
    http:
      method: GET
      url: https://api.centml.com/capacity
    docs: Returns GPU hardware instance types and available capacity.
bundled: true