Microsoft Azure API Management · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Azure API Management Gateway AI API

4 actions 4 updates phrasing extends openapi/microsoft-azure-api-management-ai-api-openapi.yml

Generated by API Evangelist Written by API Evangelist tooling for Microsoft Azure API Management's API. It is a proposal applied on top of the contract, not a document Microsoft Azure API Management publishes.

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 4

$.info

$.paths['/deployments/{deployment-id}/chat/completions'].post

$.paths['/deployments/{deployment-id}/completions'].post

$.paths['/deployments/{deployment-id}/embeddings'].post

OpenAPI Overlay

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Azure API Management Gateway AI API
  version: 1.0.0
extends: openapi/microsoft-azure-api-management-ai-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 3
- target: $.paths['/deployments/{deployment-id}/chat/completions'].post
  update:
    x-apievangelist-phrasing:
      intent: Send a chat completion through the AI gateway
      effect: write
      questions:
      - How do I send chat messages to an Azure OpenAI deployment through API Management's AI gateway?
      - Can I cap max tokens and set temperature on a chat request routed through the gateway?
      - Does the AI gateway apply token rate limiting and semantic caching to chat calls?
      instructions:
      - text: Send {messages} as a chat completion to deployment {deployment}.
        slots:
          messages: requestBody.messages
          deployment: path.deployment-id
      - text: Get a chat reply from deployment {deployment} limited to {max_tokens} tokens at temperature {temperature}.
        slots:
          deployment: path.deployment-id
          max_tokens: requestBody.max_tokens
          temperature: requestBody.temperature
      method: generated
      generated: '2026-09-26'
- target: $.paths['/deployments/{deployment-id}/completions'].post
  update:
    x-apievangelist-phrasing:
      intent: Complete a text prompt through the AI gateway
      effect: write
      questions:
      - Can I send a plain text prompt, not chat messages, to an AI backend via the gateway?
      - What controls do I have over length and randomness on a legacy prompt completion?
      instructions:
      - text: Complete the prompt {prompt} using deployment {deployment}.
        slots:
          prompt: requestBody.prompt
          deployment: path.deployment-id
      - text: Run text completion on deployment {deployment} with at most {max_tokens} tokens and temperature {temperature}.
        slots:
          deployment: path.deployment-id
          max_tokens: requestBody.max_tokens
          temperature: requestBody.temperature
      method: generated
      generated: '2026-09-26'
- target: $.paths['/deployments/{deployment-id}/embeddings'].post
  update:
    x-apievangelist-phrasing:
      intent: Create embeddings through the AI gateway
      effect: write
      questions:
      - How do I generate vector embeddings for text through the API Management gateway?
      - Can I choose which embedding model a gateway deployment uses?
      instructions:
      - text: Create embeddings for {input} on deployment {deployment}.
        slots:
          input: requestBody.input
          deployment: path.deployment-id
      - text: Embed {input} with model {model} through deployment {deployment}.
        slots:
          input: requestBody.input
          model: requestBody.model
          deployment: path.deployment-id
      method: generated
      generated: '2026-09-26'

Work with this as data

Every overlay 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 openapi overlays

4 MCP tools reach this

find_overlaysBrowse and filter every overlay in the catalog.
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 overlay

curl "https://apis.io/api/v1/overlays/microsoft-azure-api-management-ai-api-phrasing-overlay"

All openapi overlays

curl "https://apis.io/api/v1/overlays?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.