KServe KServe Inference Protocol API

The KServe Inference Protocol API from KServe — 1 operation(s) for kserve inference protocol.

OpenAPI Specification

kserve-kserve-inference-protocol-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Health KServe Inference Protocol API
  version: v1+v2
  description: 'Standardized model inference HTTP protocol exposed by KServe model

    servers. Endpoints below cover both the V1 Data Plane (prediction-style)

    and the V2 Data Plane (Open Inference Protocol). Endpoint paths

    transcribed from the public KServe documentation.

    '
  contact:
    name: Kin Lane
    email: kin@apievangelist.com
    url: https://apievangelist.com
  license:
    name: Documentation reference only
    url: https://kserve.github.io/website/docs/concepts/architecture/data-plane/v2-protocol
servers:
- url: http://{host}
  description: KServe inference service ingress (cluster- or gateway-specific)
  variables:
    host:
      default: model.example.com
security: []
tags:
- name: KServe Inference Protocol
paths:
  /v2:
    get:
      summary: Server metadata (V2)
      operationId: v2ServerMetadata
      responses:
        '200':
          description: Server metadata
          content:
            application/json:
              schema:
                type: object
      tags:
      - KServe Inference Protocol
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: 'KServe itself does not mandate an auth scheme; in production the

        InferenceService is typically fronted by an ingress/gateway that

        enforces auth (for example, Istio with OIDC/JWT, Knative serving

        with Kubernetes auth, or an API gateway). Bearer tokens are the

        most common production pattern.

        '