Cloudflare · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Cloudflare Workers AI AI Inference API

2 actions 2 updates phrasing extends openapi/cloudflare-ai-inference-api-openapi.yml
Generated by API Evangelist Written by API Evangelist tooling for Cloudflare's API. It is a proposal applied on top of the contract, not a document Cloudflare publishes.
View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 2

$.info
$.paths['/accounts/{account_id}/ai/run/{model}'].post

OpenAPI Overlay

Raw ↑
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Cloudflare Workers AI AI Inference API
  version: 1.0.0
extends: openapi/cloudflare-ai-inference-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: 1
- target: $.paths['/accounts/{account_id}/ai/run/{model}'].post
  update:
    x-apievangelist-phrasing:
      intent: Run a Workers AI model
      effect: write
      questions:
      - How do I run a text generation model like Llama on Cloudflare's network?
      - Can I stream the model's output back as server-sent events?
      - What inputs can I send, such as a chat message list, an image or text to translate?
      instructions:
      - text: Run model {model} on account {account_id} with the prompt {prompt}.
        slots:
          model: path.model
          account_id: path.account_id
          prompt: requestBody.prompt
      - text: Send chat {messages} to model {model} in account {account_id}, capped at {max_tokens} tokens.
        slots:
          messages: requestBody.messages
          model: path.model
          account_id: path.account_id
          max_tokens: requestBody.max_tokens
      - text: Translate {text} from {source_lang} to {target_lang} using model {model} on account {account_id}.
        slots:
          text: requestBody.text
          source_lang: requestBody.source_lang
          target_lang: requestBody.target_lang
          model: path.model
          account_id: path.account_id
      method: generated
      generated: '2026-09-26'