OpenAI

OpenAI Responses API

The Responses API from OpenAI — 6 operation(s) for responses.

Documentation GitHub OpenAPI

Operations 14

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /responses Generate a model response · Create a model response #

Ask an LLM

“How do I send a prompt to a model and get text or JSON back?”

“Can the model call tools like web search or my own functions while answering?”

Tell an agent

Ask {model} to respond to {input}.

Generate a response to {input} that follows up on response {previous_response_id}.

GET /responses/{response_id} Retrieve a model response · Get a model response #

Ask an LLM

“Can I fetch the output of a response I generated earlier by its ID?”

“Is my background response finished yet?”

Tell an agent

Get response {response_id}.

Check whether background response {response_id} has completed and show its output.

DELETE /responses/{response_id} Delete a stored model response · Delete a model response #

Ask an LLM

“How do I delete a stored response so it's no longer kept?”

“Can I remove a model response by its ID?”

Tell an agent destructive · confirm first

Delete response {response_id}.

Remove the stored model response {response_id}.

POST /responses/{response_id}/cancel Cancel a background response · Cancel a response #

Ask an LLM

“Can I stop a background response that is still generating?”

“Which responses are eligible to be cancelled?”

Tell an agent destructive · confirm first

Cancel background response {response_id}.

Stop the still-running response {response_id}.

GET /responses/{response_id}/input_items List the input items of a response · List input items #

Ask an LLM

“What inputs were sent to the model to produce a given response?”

“Can I page through the input items behind a response?”

Tell an agent

List the input items for response {response_id}.

Show the first {limit} inputs that went into response {response_id}.

POST /responses/input_tokens Count input tokens before sending a request · Get input token counts #

Ask an LLM

“How many input tokens will my prompt use before I actually run it?”

“Can I estimate token usage including my tools and instructions?”

Tell an agent

Count the input tokens of {input} for model {model}.

Tell me how many tokens {input} plus instructions {instructions} would use.

POST /responses/compact Compact a long conversation · Compact conversation #

Ask an LLM

“My conversation is getting too long for the context window — how can I shrink it?”

“Can I compact the history that follows a previous response?”

Tell an agent

Compact the conversation after response {previous_response_id} using {model}.

Condense this long input {input} into a compacted response with {model}.

POST /responses?beta=true Create a model response #

GET /responses/{response_id}?beta=true Get a model response #

DELETE /responses/{response_id}?beta=true Delete a model response #

POST /responses/{response_id}/cancel?beta=true Cancel a response #

POST /responses/compact?beta=true Compact conversation #

GET /responses/{response_id}/input_items?beta=true List input items #

POST /responses/input_tokens?beta=true Get input token counts #

Documentation

https://platform.openai.com/docs/assistants/overview

https://platform.openai.com/docs/api-reference/assistants

https://platform.openai.com/docs/guides/text-to-speech

https://platform.openai.com/docs/api-reference/audio

https://platform.openai.com/docs/guides/speech-to-text

https://developers.openai.com/api/docs/guides/audio/

https://developers.openai.com/api/docs/guides/voice-agents/

https://platform.openai.com/docs/api-reference/chat

https://platform.openai.com/docs/guides/embeddings

https://platform.openai.com/docs/api-reference/embeddings

https://platform.openai.com/docs/api-reference/files

https://platform.openai.com/docs/guides/fine-tuning

https://platform.openai.com/docs/api-reference/fine-tuning

https://platform.openai.com/docs/guides/images

https://platform.openai.com/docs/api-reference/images

https://platform.openai.com/docs/guides/image-generation

https://platform.openai.com/docs/guides/images-vision

https://platform.openai.com/docs/models

https://platform.openai.com/docs/api-reference/models

https://platform.openai.com/docs/assistants/how-it-works/managing-threads-and-messages

https://platform.openai.com/docs/api-reference/threads

https://platform.openai.com/docs/api-reference/completions

Specifications

https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/openapi/openai-responses-api-openapi.yml

Schemas & Data

https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-schema/openai-chat-completion-schema.json

https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-schema/openai-embedding-schema.json

Other Resources

https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-ld/openai-context.jsonld

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/openai:openai-responses-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

openapi: 3.2.0
info:
  title: OpenAI Responses API
  description: The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.
  version: 2.3.0
  termsOfService: https://openai.com/policies/terms-of-use
  contact:
    name: OpenAI Support
    url: https://help.openai.com/
  license:
    name: MIT
    identifier: MIT
servers:
- url: https://api.openai.com/v1
security:
- ApiKeyAuth: []
tags:


# --- truncated at 32 KB (848 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/openapi/openai-responses-api-openapi.yml