Triton Inference Server Server Metadata API

openapi: 3.1.0
info:
  title: Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Server Metadata 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: Server Metadata
  description: Server-level metadata and information
paths:
  /v2:
    get:
      operationId: serverMetadata
      summary: Triton Inference Server Get Server Metadata
      description: Retrieve metadata about the Triton server including name, version, and supported extensions.
      tags:
      - Server Metadata
      responses:
        '200':
          description: Server metadata returned successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerMetadataResponse'
        '400':
          description: Error retrieving server metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Error message describing what went wrong
    ServerMetadataResponse:
      type: object
      properties:
        name:
          type: string
          description: Name of the inference server
          examples:
          - triton
        version:
          type: string
          description: Version of the inference server
          examples:
          - 2.42.0
        extensions:
          type: array
          description: List of extensions supported by the server
          items:
            type: string
          examples:
          - - classification
            - sequence
            - model_repository
            - model_configuration
            - schedule_policy
            - server_metadata
            - statistics
            - trace
            - logging
externalDocs:
  description: Triton Inference Server Protocol Documentation
  url: https://github.com/triton-inference-server/server/blob/main/docs/protocol/README.md