Parallel · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Parallel Responses API

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

What the actions change

x-apievangelist-phrasing

Targets 2

$.info
$.paths['/v1/responses'].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 Parallel Responses API
  version: 1.0.0
extends: openapi/parallel-responses-api-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 1
- target: $.paths['/v1/responses'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate a cited answer from live web research
      effect: write
      questions:
      - Can I get an answer with URL citations grounded in live web research using the OpenAI Responses format?
      - What does the reasoning effort setting change about how much research is done?
      - Is background mode supported when generating a response?
      - Can a new response build on a previous response as conversation context?
      instructions:
      - text: Generate a cited response to {input} using the {model} model.
        slots:
          input: requestBody.input
          model: requestBody.model
      - text: Answer {input} with the {model} model at {reasoning} reasoning effort.
        slots:
          input: requestBody.input
          model: requestBody.model
          reasoning: requestBody.reasoning
      - text: Follow up on response {previous_response_id} with {input} using {model}.
        slots:
          previous_response_id: requestBody.previous_response_id
          input: requestBody.input
          model: requestBody.model
      method: generated
      generated: '2026-10-01'