Triton Inference Server Health API

openapi: 3.1.0
info:
  title: Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Health API
  description: RESTful API for the NVIDIA Triton Inference Server, implementing the KServe V2 inference protocol with Triton-specific extensions. Provides endpoints for model inference, health checks, server and model metadata, model repository management, statistics, tracing, logging, and system shared memory management.
  version: '2.0'
  contact:
    name: NVIDIA Triton Team
    url: https://github.com/triton-inference-server/server
    email: triton@nvidia.com
  license:
    name: BSD 3-Clause
    url: https://github.com/triton-inference-server/server/blob/main/LICENSE
servers:
- url: http://localhost:8000
  description: Triton HTTP endpoint (default)
- url: http://{host}:{port}
  description: Custom Triton HTTP endpoint
  variables:
    host:
      default: localhost
      description: Triton server hostname or IP
    port:
      default: '8000'
      description: Triton HTTP port
tags:
- name: Health
  description: Server and model health and readiness checks
paths:
  /v2/health/live:
    get:
      operationId: serverLive
      summary: Triton Inference Server Server Liveness Check
      description: Check if the Triton server is alive and able to receive requests. This is the KServe V2 standard liveness probe endpoint.
      tags:
      - Health
      responses:
        '200':
          description: Server is live
        '400':
          description: Server is not live
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /v2/health/ready:
    get:
      operationId: serverReady
      summary: Triton Inference Server Server Readiness Check
      description: Check if the Triton server is ready to accept inference requests. The server is ready when all models that are loaded at startup are ready.
      tags:
      - Health
      responses:
        '200':
          description: Server is ready
        '400':
          description: Server is not ready
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /v2/models/{model_name}/versions/{model_version}/ready:
    get:
      operationId: modelVersionReady
      summary: Triton Inference Server Model Version Readiness Check
      description: Check if a specific version of a model is ready to accept inference requests.
      tags:
      - Health
      parameters:
      - $ref: '#/components/parameters/modelName'
      - $ref: '#/components/parameters/modelVersion'
      responses:
        '200':
          description: Model version is ready
        '400':
          description: Model version is not ready
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /v2/models/{model_name}/ready:
    get:
      operationId: modelReady
      summary: Triton Inference Server Model Readiness Check
      description: Check if a model is ready to accept inference requests. Checks the default/latest version of the model.
      tags:
      - Health
      parameters:
      - $ref: '#/components/parameters/modelName'
      responses:
        '200':
          description: Model is ready
        '400':
          description: Model is not ready
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  parameters:
    modelName:
      name: model_name
      in: path
      required: true
      description: Name of the model
      schema:
        type: string
    modelVersion:
      name: model_version
      in: path
      required: true
      description: Version of the model
      schema:
        type: string
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Error message describing what went wrong
externalDocs:
  description: Triton Inference Server Protocol Documentation
  url: https://github.com/triton-inference-server/server/blob/main/docs/protocol/README.md