Envoy

Envoy is a high-performance, open-source edge and service proxy designed for cloud-native applications and microservice architectures. It provides advanced load balancing, observability, and traffic management features, and serves as the data plane for many service mesh implementations including Istio.

5 APIs 0 Features

Cloud NativeLoad BalancingProxyService Mesh

APIs

Envoy Admin API

The Envoy Admin API provides local administrative access to a running Envoy proxy instance, exposing endpoints for inspecting clusters, listeners, configuration, statistics, hea...

Envoy xDS APIs

The xDS (x Discovery Service) APIs provide dynamic configuration for Envoy proxies via a management server, including LDS, RDS, CDS, EDS, SDS, and ADS. xDS APIs are served over ...

Envoy API V3

The Envoy API v3 is the current stable protobuf-based configuration and extension API for Envoy proxy. It defines the configuration types for all Envoy subsystems including list...

Envoy Gateway API

Envoy Gateway manages Envoy Proxy as a standalone or Kubernetes-based application gateway, implementing and extending the Kubernetes Gateway API. It provides Gateway API extensi...

Envoy AI Gateway API

The Envoy AI Gateway manages unified access to Generative AI services built on Envoy Gateway. It provides OpenAI-compatible and Anthropic-compatible API endpoints for routing LL...

Collections

Envoy Admin API

OPEN

Envoy AI Gateway API

OPEN

Pricing Plans

Envoy Plans Pricing

2 plans

PLANS

Rate Limits

Envoy Rate Limits

3 limits

RATE LIMITS

FinOps

Envoy Finops

FINOPS

Semantic Vocabularies

Envoy Context

0 classes · 10 properties

JSON-LD

Resources

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Envoy AI Gateway API
  version: 0.2.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Envoy Create a chat completion
      type: http
    http:
      method: POST
      url: https://{gateway-host}/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: Creates a chat completion response for the provided messages using an AI model routed through the gateway. The request
      format is compatible with the OpenAI Chat Completions API. The gateway selects a backend based on the AIGatewayRoute
      rules, which may include header-based routing, model-based routing, and backend traffic policies for rate limiting and
      token quota management. Supports streaming via server-sent events when stream is set to true.
- info:
    name: Text Completions
    type: folder
  items:
  - info:
      name: Envoy Create a text completion
      type: http
    http:
      method: POST
      url: https://{gateway-host}/v1/completions
      body:
        type: json
        data: '{}'
    docs: Creates a text completion for the provided prompt using an AI model routed through the gateway. The request format
      is compatible with the OpenAI legacy Completions API. This endpoint is primarily provided for backward compatibility;
      the chat completions endpoint is preferred for modern applications.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: Envoy List available models
      type: http
    http:
      method: GET
      url: https://{gateway-host}/v1/models
    docs: Returns a list of AI models available through the gateway as configured in AIGatewayRoute resources. The available
      models correspond to the model names that the gateway has been configured to route to upstream AI backends.
bundled: true