OpenAI
APIs for accessing OpenAI's artificial intelligence models including GPT, DALL-E, Whisper, and Embeddings.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles OpenAI the way a machine reads it — 228 machine-readable artifacts across 51 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — OpenAI scores 72.2/100 (exemplar), with a separate agent-readiness read of 59/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile OpenAI
Each block below is one kind of artifact we hold for OpenAI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 51
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
OpenAI Responses API
The Responses API is OpenAI's most advanced interface for generating model responses. It combines the strengths of the Chat Completions and Assistants APIs into a single streaml...
OpenAI Moderations API
The Moderations API can be used to check whether text or images are potentially harmful. It classifies content across several categories including harassment, hate speech, sexua...
OpenAI Batch API
The Batch API enables asynchronous processing of requests with 50% cost discount, higher rate limits, and completion within 24 hours. It supports /v1/responses, /v1/chat/complet...
OpenAI Vector Stores API
Vector stores are collections of processed files that power semantic search for the file_search tool in the Responses and Assistants APIs. When you add a file to a vector store ...
OpenAI Uploads API
The Uploads API creates an intermediate Upload object that you can add Parts to, enabling large file uploads. Currently an Upload can accept at most 8 GB in total and expires af...
OpenAI Realtime API
The Realtime API enables low-latency, bidirectional communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, an...
OpenAI Evals API
The Evals API allows you to programmatically configure and run evaluations to test model outputs against your expectations. Evaluations ensure model responses meet style and con...
OpenAI Videos API
The Videos API enables programmatic creation, extension, and remixing of videos using Sora models. It provides endpoints for creating a new render job from a text prompt, checki...
OpenAI Conversations API
The Conversations API allows you to create and manage stateful conversations for use with the Responses API. A conversation object contains an id, a created_at timestamp, and me...
OpenAI Containers API
The Containers API manages sandboxed containers used by Code Interpreter for running Python, data work, file transforms, and iterative debugging. Containers can be created expli...
OpenAI ChatKit API
ChatKit is the best way to build agentic chat experiences. It provides session and thread management for building internal knowledge base assistants, research companions, suppor...
OpenAI Skills API
The Skills API surfaces OpenAI's Agent Skills — discoverable folders of instructions, scripts, and resources that agents (notably Codex) can use to perform specific tasks. Opera...
OpenAI Agents SDK
The OpenAI Agents SDK is a lightweight framework for building multi-agent workflows in Python and TypeScript. Primitives include agents (LLMs with instructions, tools, guardrail...
OpenAI Codex
OpenAI Codex is a lightweight coding agent that runs in the terminal, with companion IDE extensions, a desktop app, and a web experience at chatgpt.com/codex. Codex authenticate...
OpenAI Assistants API
Build Assistants that can call models and use tools.
OpenAI Audio API
Learn how to turn audio into text or text into audio.
OpenAI Audit Logs API
List user actions and configuration changes within this organization.
OpenAI Batch API
Create large batches of API requests to run asynchronously.
OpenAI Certificates API
The Certificates API from OpenAI — 7 operation(s) for certificates.
OpenAI Chat API
Given a list of messages comprising a conversation, the model will return a response.
OpenAI Chatkit API
The Chatkit API from OpenAI — 5 operation(s) for chatkit.
OpenAI Completions API
Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
OpenAI Containers API
The Containers API from OpenAI — 5 operation(s) for containers.
OpenAI Conversations API
Manage conversations and conversation items.
OpenAI Embeddings API
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
OpenAI Evals API
Manage and run evals in the OpenAI platform.
OpenAI Files API
Files are used to upload documents that can be used with features like Assistants and Fine-tuning.
OpenAI Fine Tuning API
The Fine Tuning API from OpenAI — 11 operation(s) for fine tuning.
OpenAI Group organization role assignments API
The Group organization role assignments API from OpenAI — 2 operation(s) for group organization role assignments.
OpenAI Group users API
The Group users API from OpenAI — 2 operation(s) for group users.
OpenAI Groups API
The Groups API from OpenAI — 2 operation(s) for groups.
OpenAI Images API
Given a prompt and/or an input image, the model will generate a new image.
OpenAI Invites API
The Invites API from OpenAI — 2 operation(s) for invites.
OpenAI Models API
List and describe the various models available in the API.
OpenAI Moderations API
Given text and/or image inputs, classifies if those inputs are potentially harmful.
OpenAI Organization API
The Organization API from OpenAI — 2 operation(s) for organization.
OpenAI Project group role assignments API
The Project group role assignments API from OpenAI — 2 operation(s) for project group role assignments.
OpenAI Project groups API
The Project groups API from OpenAI — 2 operation(s) for project groups.
OpenAI Project user role assignments API
The Project user role assignments API from OpenAI — 2 operation(s) for project user role assignments.
OpenAI Projects API
The Projects API from OpenAI — 11 operation(s) for projects.
OpenAI Realtime API
The Realtime API from OpenAI — 9 operation(s) for realtime.
OpenAI Responses API
The Responses API from OpenAI — 6 operation(s) for responses.
OpenAI Roles API
The Roles API from OpenAI — 4 operation(s) for roles.
OpenAI Skills API
The Skills API from OpenAI — 6 operation(s) for skills.
OpenAI Threads API
The Threads API from OpenAI — 13 operation(s) for threads.
OpenAI Uploads API
Use Uploads to upload large files in multiple parts.
OpenAI Usage API
The Usage API from OpenAI — 9 operation(s) for usage.
OpenAI User organization role assignments API
The User organization role assignments API from OpenAI — 2 operation(s) for user organization role assignments.
OpenAI Users API
The Users API from OpenAI — 2 operation(s) for users.
OpenAI Vector stores API
The Vector stores API from OpenAI — 10 operation(s) for vector stores.
OpenAI Videos API
The Videos API from OpenAI — 8 operation(s) for videos.
Scroll within the panel for all 51 ·
Postman Collections 14
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
OpenAI Assistants
POSTMANOpenAI audio
POSTMANOpenAI Chat
POSTMANOpenAI Completions
POSTMANOpenAI embeddings
POSTMANOpenAI files
POSTMANOpenAI fine tuning
POSTMANOpenAI images
POSTMANOpenAI models
POSTMANOpenAI Audio API
POSTMANOpenAI Chat Completions API
POSTMANOpenAI Embeddings API
POSTMANOpenAI Images API
POSTMANOpenAI threads
POSTMANScroll within the panel for all 14 ·
Open Collections 6
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
OpenAI Audio API
OPEN COLLECTIONOpenAI Chat Completions API
OPEN COLLECTIONOpenAI Embeddings API
OPEN COLLECTIONAPI Collection
OPEN COLLECTIONOpenAI Images API
OPEN COLLECTIONOpenAI API
OPEN COLLECTIONArazzo Workflows 17
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
OpenAI Assistant Run
Create an assistant, open a thread, add a message, run it, poll the run, and read the reply.
ARAZZOOpenAI Batch Job
Upload a batch input file, create a batch, poll until complete, and read the output file id.
ARAZZOOpenAI Cancel Fine-Tuning Job
Inspect a running fine-tuning job and cancel it only if it is still in progress.
ARAZZOOpenAI Download Batch Results
Retrieve a completed batch and download its output file contents.
ARAZZOOpenAI Fine-Tuning Job
Upload a training file, start a fine-tuning job, poll until terminal, and read the result.
ARAZZOOpenAI Moderate then Generate Image
Screen an image prompt, then generate an image only when it is allowed.
ARAZZOOpenAI List Models then Create Chat Completion
Discover an available model, then generate a chat completion with it.
ARAZZOOpenAI Moderate then Chat
Screen user input with the moderation endpoint, then chat only if it is safe.
ARAZZOOpenAI Retrieve and Delete Fine-Tuned Model
Inspect a model and delete it only when it is an owned fine-tuned model.
ARAZZOOpenAI Create Thread and Run
Start a thread and run in one request against an existing assistant, then poll and read the reply.
ARAZZOOpenAI Transcribe then Summarize
Transcribe an audio file, then summarize the transcript with a chat completion.
ARAZZOOpenAI Upload and Verify File
Upload a file, confirm it appears in the file list, and retrieve its metadata.
ARAZZOOpenAI Vector Store File Batch
Create a vector store, attach a batch of files, and poll the batch to completion.
ARAZZOOpenAI Vector Store Ingest File
Create a vector store, upload a file, attach it, and poll until it is indexed.
ARAZZOOpenAI Vector Store Search
Attach a file to a vector store, wait until it is indexed, then run a semantic search.
ARAZZOScroll within the panel for all 17 ·
Agent Skills 24
An agent skill packages the how-to for driving these APIs from an assistant — the prompts, the sequence, the guardrails — so the knowledge to use the API travels with it.
Packaged agent skills for driving this provider's APIs from an AI assistant.
aspnet-core
AGENT SKILLchatgpt-apps
AGENT SKILLcli-creator
AGENT SKILLcloudflare-deploy
AGENT SKILLdefine-goal
AGENT SKILLfigma-code-connect-components
AGENT SKILLfigma-create-design-system-rules
AGENT SKILLfigma-create-new-file
AGENT SKILLfigma-generate-design
AGENT SKILLfigma-generate-library
AGENT SKILLfigma-implement-design
AGENT SKILLfigma-use
AGENT SKILLfigma
AGENT SKILLgh-address-comments
AGENT SKILLgh-fix-ci
AGENT SKILLhatch-pet
AGENT SKILLimagegen
AGENT SKILLjupyter-notebook
AGENT SKILLlinear
AGENT SKILLmigrate-to-codex
AGENT SKILLnetlify-deploy
AGENT SKILLnotion-knowledge-capture
AGENT SKILLnotion-meeting-intelligence
AGENT SKILLnotion-research-documentation
AGENT SKILLScroll within the panel for all 24 ·
GraphQL 1
Where a provider ships GraphQL, the schema is the contract. We profile it alongside the REST surface so the whole interface is legible in one place.
GraphQL schemas published by this provider.
OpenAI GraphQL
OpenAI does not offer a native public GraphQL endpoint. All official API access is provided through the OpenAI REST API at `https://api.openai.com/v1`. This schema is a comprehe...
GRAPHQLPricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Openai Plans Pricing
PLANSRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Openai Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Openai Finops
FINOPSFeatures 16
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
Scroll within the panel for all 16 ·
Event Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
OpenAI Realtime API
The OpenAI Realtime API provides low-latency, bidirectional, event-driven communication with multimodal models that natively support speech-to-speech, text, and audio in a singl...
ASYNCAPISemantic Vocabularies 5
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Openai Audio Context
JSON-LDOpenai Context
JSON-LDOpenai Embeddings Context
JSON-LDOpenai Images Context
JSON-LDSpectral Rules 3
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
JSON Schema 24
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
CreateSpeechRequest
JSON SCHEMACreateTranscriptionRequest
JSON SCHEMACreateTranslationRequest
JSON SCHEMATranscriptionResponse
JSON SCHEMATranslationResponse
JSON SCHEMAOpenAI Chat Completion
JSON SCHEMAChatCompletionChoice
JSON SCHEMAChatCompletionMessage
JSON SCHEMAChatCompletionTool
JSON SCHEMACompletionUsage
JSON SCHEMAContentPart
JSON SCHEMACreateChatCompletionRequest
JSON SCHEMACreateChatCompletionResponse
JSON SCHEMAToolCall
JSON SCHEMAOpenAI Embedding Response
JSON SCHEMACreateEmbeddingRequest
JSON SCHEMACreateEmbeddingResponse
JSON SCHEMAEmbedding
JSON SCHEMAEmbeddingUsage
JSON SCHEMACreateImageEditRequest
JSON SCHEMACreateImageRequest
JSON SCHEMACreateImageVariationRequest
JSON SCHEMAImage
JSON SCHEMAImagesResponse
JSON SCHEMAScroll within the panel for all 24 ·
JSON Structure 22
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Openai Audio Create Speech Request Structure
JSON STRUCTUREOpenai Audio Create Transcription Request Structure
JSON STRUCTUREOpenai Audio Create Translation Request Structure
JSON STRUCTUREOpenai Audio Transcription Response Structure
JSON STRUCTUREOpenai Audio Translation Response Structure
JSON STRUCTUREOpenai Chat Completions Chat Completion Choice Structure
JSON STRUCTUREOpenai Chat Completions Chat Completion Tool Structure
JSON STRUCTUREOpenai Chat Completions Completion Usage Structure
JSON STRUCTUREOpenai Chat Completions Content Part Structure
JSON STRUCTUREOpenai Chat Completions Tool Call Structure
JSON STRUCTUREOpenai Embeddings Create Embedding Request Structure
JSON STRUCTUREOpenai Embeddings Create Embedding Response Structure
JSON STRUCTUREOpenai Embeddings Embedding Structure
JSON STRUCTUREOpenai Embeddings Embedding Usage Structure
JSON STRUCTUREOpenai Images Create Image Edit Request Structure
JSON STRUCTUREOpenai Images Create Image Request Structure
JSON STRUCTUREOpenai Images Create Image Variation Request Structure
JSON STRUCTUREOpenai Images Image Structure
JSON STRUCTUREOpenai Images Images Response Structure
JSON STRUCTUREScroll within the panel for all 22 ·
Examples 22
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Openai Images Image Example
EXAMPLEScroll within the panel for all 22 ·
Security Posture 4
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 8
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
Conversational AI
Build chatbots, virtual assistants, and customer support agents using Chat Completions or Responses API.
Content Generation
Generate marketing copy, articles, product descriptions, and creative writing with controllable tone and style.
Code Generation
Automate code writing, debugging, refactoring, and documentation generation across programming languages.
Document Analysis
Extract, summarize, and answer questions from uploaded documents using Assistants with file search.
Voice Agents
Build real-time voice-based AI agents for customer service, sales, and interactive experiences.
Semantic Search
Implement intelligent search using embeddings and vector stores for knowledge bases and document retrieval.
Content Moderation
Automatically classify and filter harmful content across text and images using the Moderations API.
Data Extraction
Extract structured data from unstructured text using function calling and structured outputs.
Scroll within the panel for all 8 ·
Integrations 6
Pre-built integrations with other platforms tell you where this provider already fits in a stack.
Pre-built integrations with other platforms and tools.
Python SDK
Official Python client library for accessing all OpenAI API endpoints with async support and streaming.
Node.js SDK
Official TypeScript and JavaScript client library for server-side and edge runtime OpenAI API integration.
Microsoft Azure OpenAI
Run OpenAI models on Azure infrastructure with enterprise security, compliance, and regional data residency.
LangChain
Framework integration for building LLM-powered applications with chains, agents, and retrieval-augmented generation.
Vercel AI SDK
Integration with Vercel AI SDK for building streaming AI-powered web applications with React and Next.js.
Zapier
No-code automation integration connecting OpenAI to thousands of apps for automated AI-powered workflows.
Resources
Every other property we hold for OpenAI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 5
Portal, sign-up, and the first successful call
Documentation 25
Reference material describing how the API behaves
Scroll within the panel for all 25 ·
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 21
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 21 ·
Build 19
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 19 ·
Access & Security 7
Authentication, authorization, and security posture
Scroll within the panel for all 7 ·
Learn 1
Tutorials, courses, talks, and written guidance
Operate 8
Status, limits, changes, and where to get help
Scroll within the panel for all 8 ·
Commercial 6
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 3
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/openai · machine-readable index on apis.io