Kgateway

Kgateway AIBackend API

Configure AI backend providers with support for LLM providers such as OpenAI, Azure OpenAI, and Gemini. Specify provider configuration and priority groups for AI routing.

GitHub OpenAPI

Operations 5

GET /namespaces/{namespace}/aibackends Kgateway List AIBackend resources #
POST /namespaces/{namespace}/aibackends Kgateway Create an AIBackend #
GET /namespaces/{namespace}/aibackends/{name} Kgateway Get an AIBackend #
PUT /namespaces/{namespace}/aibackends/{name} Kgateway Replace an AIBackend #
DELETE /namespaces/{namespace}/aibackends/{name} Kgateway Delete an AIBackend #

Documentation

📖
Documentation
https://kgateway.dev/docs/envoy/latest/reference/api/

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/openapi/kgateway-aibackend-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/traffic-policy.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/backend.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/direct-response.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/gateway-extension.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/gateway-parameters.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/http-listener-policy.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-schema/ai-backend.json

Other Resources

🔗
JSONLD
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/json-ld/kgateway-context.jsonld
🔗
APIsJSON
https://raw.githubusercontent.com/api-evangelist/kgateway/refs/heads/main/apis.yml

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/kgateway-aibackend-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

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

kgateway-aibackend-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: kgateway Kubernetes Gateway AI Backend API
  description: kgateway is the most widely deployed gateway in Kubernetes for microservices and AI agents.
  version: 2.1.0
  contact:
    name: kgateway
    url: https://kgateway.dev
  license:
    name: Apache 2.0
    url: https://github.com/kgateway-dev/kgateway/blob/main/LICENSE
servers:
- url: https://{kubernetes-api-server}/apis/gateway.kgateway.dev/v1alpha1
  description: Kubernetes API Server - kgateway Custom Resources
  variables:
    kubernetes-api-server:
      default: kubernetes.default.svc
      description: The Kubernetes API server hostname
security:
- BearerAuth: []
tags:
- name: AIBackend
  description: Configure AI backend providers with support for LLM providers such as OpenAI, Azure OpenAI, and Gemini. Specify provider configuration and priority groups for AI routing.
paths:
  /namespaces/{namespace}/aibackends:
    get:
      operationId: listAIBackends
      summary: Kgateway List AIBackend resources
      description: List all AIBackend resources in the specified namespace. AIBackends configure AI provider backends such as OpenAI, Azure OpenAI, and Gemini for AI gateway routing.
      tags:
      - AIBackend
      parameters:
      - $ref: '#/components/parameters/Namespace'
      - $ref: '#/components/parameters/LabelSelector'
      - $ref: '#/components/parameters/Limit'
      - $ref: '#/components/parameters/Continue'
      responses:
        '200':
          description: Successfully retrieved list of AIBackend resources.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AIBackendList'
        '401':
          description: Unauthorized
    post:
      operationId: createAIBackend
      summary: Kgateway Create an AIBackend
      description: Create an AIBackend resource to configure an AI provider backend with LLM provider settings and priority groups.
      tags:
      - AIBackend
      parameters:
      - $ref: '#/components/parameters/Namespace'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AIBackend'
      responses:
        '201':
          description: Successfully created AIBackend.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AIBackend'
        '401':
          description: Unauthorized
        '409':
          description: Conflict - resource already exists
  /namespaces/{namespace}/aibackends/{name}:
    get:
      operationId: getAIBackend
      summary: Kgateway Get an AIBackend
      description: Retrieve a specific AIBackend resource by name and namespace.
      tags:
      - AIBackend
      parameters:
      - $ref: '#/components/parameters/Namespace'
      - $ref: '#/components/parameters/Name'
      responses:
        '200':
          description: Successfully retrieved AIBackend.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AIBackend'
        '401':
          description: Unauthorized
        '404':
          description: AIBackend not found
    put:
      operationId: replaceAIBackend
      summary: Kgateway Replace an AIBackend
      description: Replace a specific AIBackend resource.
      tags:
      - AIBackend
      parameters:
      - $ref: '#/components/parameters/Namespace'
      - $ref: '#/components/parameters/Name'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AIBackend'
      responses:
        '200':
          description: Successfully replaced AIBackend.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AIBackend'
        '401':
          description: Unauthorized
        '404':
          description: AIBackend not found
    delete:
      operationId: deleteAIBackend
      summary: Kgateway Delete an AIBackend
      description: Delete a specific AIBackend resource.
      tags:
      - AIBackend
      parameters:
      - $ref: '#/components/parameters/Namespace'
      - $ref: '#/components/parameters/Name'
      responses:
        '200':
          description: Successfully deleted AIBackend.
        '401':
          description: Unauthorized
        '404':
          description: AIBackend not found
components:
  schemas:
    AIBackendList:
      type: object
      description: List of AIBackend resources.
      properties:
        apiVersion:
          type: string
        kind:
          type: string
          enum:
          - AIBackendList
        metadata:
          type: object
          properties:
            continue:
              type: string
            resourceVersion:
              type: string
        items:
          type: array
          items:
            $ref: '#/components/schemas/AIBackend'
    AIBackend:
      type: object
      description: AIBackend configures AI provider backends with support for LLM providers such as OpenAI, Azure OpenAI, and Gemini.
      properties:
        apiVersion:
          type: string
          enum:
          - gateway.kgateway.dev/v1alpha1
        kind:
          type: string
          enum:
          - AIBackend
        metadata:
          $ref: '#/components/schemas/ObjectMeta'
        spec:
          type: object
          description: AIBackendSpec defines the desired state of an AIBackend.
          properties:
            provider:
              type: object
              description: Configuration for the LLM provider.
              properties:
                type:
                  type: string
                  description: The type of LLM provider.
                  enum:
                  - openai
                  - azure
                  - gemini
                  - mistral
                openai:
                  type: object
                  properties:
                    model:
                      type: string
                      description: Model name to use.
                    authToken:
                      type: object
                      properties:
                        secretRef:
                          type: object
                          properties:
                            name:
                              type: string
                            namespace:
                              type: string
                azure:
                  type: object
                  properties:
                    endpoint:
                      type: string
                    deploymentName:
                      type: string
                    apiVersion:
                      type: string
                    authToken:
                      type: object
                      properties:
                        secretRef:
                          type: object
                          properties:
                            name:
                              type: string
                            namespace:
                              type: string
                gemini:
                  type: object
                  properties:
                    model:
                      type: string
                    authToken:
                      type: object
                      properties:
                        secretRef:
                          type: object
                          properties:
                            name:
                              type: string
                            namespace:
                              type: string
            groups:
              type: array
              description: List of groups in priority order where each group defines a set of LLM providers.
              items:
                type: object
                properties:
                  priority:
                    type: integer
                    description: Priority of this group (lower is higher priority).
                  backends:
                    type: array
                    items:
                      type: object
                      properties:
                        backendRef:
                          type: object
                          properties:
                            name:
                              type: string
                            namespace:
                              type: string
                        weight:
                          type: integer
                          description: Weight for load balancing within the group.
        status:
          type: object
          description: Status of the AIBackend.
          properties:
            conditions:
              type: array
              items:
                type: object
                properties:
                  type:
                    type: string
                  status:
                    type: string
                  reason:
                    type: string
                  message:
                    type: string
                  lastTransitionTime:
                    type: string
                    format: date-time
    ObjectMeta:
      type: object
      description: Standard Kubernetes object metadata.
      properties:
        name:
          type: string
          description: Name of the resource.
        namespace:
          type: string
          description: Namespace of the resource.
        labels:
          type: object
          additionalProperties:
            type: string
          description: Map of string keys and values for organizing resources.
        annotations:
          type: object
          additionalProperties:
            type: string
          description: Annotations for storing arbitrary metadata.
        resourceVersion:
          type: string
          description: An opaque value that represents the internal version of this object.
        creationTimestamp:
          type: string
          format: date-time
          description: Timestamp representing the server time when this object was created.
  parameters:
    Namespace:
      name: namespace
      in: path
      required: true
      description: The Kubernetes namespace.
      schema:
        type: string
    Name:
      name: name
      in: path
      required: true
      description: The name of the resource.
      schema:
        type: string
    LabelSelector:
      name: labelSelector
      in: query
      required: false
      description: A selector to restrict the list of returned objects by labels.
      schema:
        type: string
    Continue:
      name: continue
      in: query
      required: false
      description: Continue token for paginated list requests.
      schema:
        type: string
    Limit:
      name: limit
      in: query
      required: false
      description: Maximum number of resources to return.
      schema:
        type: integer
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: Kubernetes API bearer token authentication. Use a service account token or kubeconfig token.
externalDocs:
  description: kgateway API Reference Documentation
  url: https://kgateway.dev/docs/envoy/latest/reference/api/