OpenAI

aid: openai
url: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/apis.yml
apis:
  - aid: openai:openai-assistants-api
    name: OpenAI Assistants API
    tags:
      - Assistants
    score: 1329
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/assistants/overview
    properties:
      - url: https://platform.openai.com/docs/assistants/overview
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/assistants
        type: Documentation
      - url: openapi/assistants-openapi-original.yml
        type: OpenAPI
    description: >-
      The Assistants API allows you to build AI assistants within your own applications. An Assistant has instructions
      and can leverage models, tools, and knowledge to respond to user queries. The Assistants API currently supports
      three types of tools - Code Interpreter, Retrieval, and Function calling. In the future, we plan to release more
      OpenAI-built tools, and allow you to provide your own tools on our platform.
  - aid: openai:openai-audio-api
    name: OpenAI Audio API
    tags:
      - Audio
    score: 128
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/guides/text-to-speech
    properties:
      - url: https://platform.openai.com/docs/guides/text-to-speech
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/audio
        type: Documentation
      - url: https://platform.openai.com/docs/guides/speech-to-text
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/audio/
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/voice-agents/
        type: Documentation
      - url: openapi/audio-openapi-original.yml
        type: OpenAPI
      - url: openapi/openai-audio-openapi.yml
        type: OpenAPI
      - url: json-ld/openai-context.jsonld
        type: JSONLD
    description: >-
      The Audio API provides two speech to text endpoints, transcriptions and translations, based on our
      state-of-the-art open source large-v2 Whisper model.
  - aid: openai:openai-chat-api
    name: OpenAI Chat API
    tags:
      - Chat
    score: 149
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/chat
    properties:
      - url: https://platform.openai.com/docs/api-reference/chat
        type: Documentation
      - url: openapi/chat-openapi-original.yml
        type: OpenAPI
      - url: openapi/openai-chat-completions-openapi.yml
        type: OpenAPI
      - url: json-schema/openai-chat-completion-schema.json
        type: JSONSchema
      - url: json-ld/openai-context.jsonld
        type: JSONLD
    description: >-
      Given a list of messages comprising a conversation, the model will return a response., providing an AI chat
      interface you can use to engage with users.
  - aid: openai:openai-chat-completions-api
    name: OpenAI Chat Completions API
    tags:
      - Chat
      - Completions
    score: 281
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/chat
    properties:
      - url: https://platform.openai.com/docs/api-reference/chat
        type: Documentation
      - url: properties/openai-chat-completions-api-openapi.yml
        type: OpenAPI
      - url: openapi/openai-chat-completions-openapi.yml
        type: OpenAPI
      - url: json-schema/openai-chat-completion-schema.json
        type: JSONSchema
      - url: json-ld/openai-context.jsonld
        type: JSONLD
    description: >-
      Chat models take a list of messages as input and return a model-generated message as output. Although the chat
      format is designed to make multi-turn conversations easy, it's just as useful for single-turn tasks without any
      conversation.
  - aid: openai:openai-embeddings-api
    name: OpenAI Embeddings API
    tags:
      - Embedding
      - Embeddings
      - Inputs
      - Representing
      - Text
      - Vectors
    score: 112
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/guides/embeddings
    properties:
      - url: https://platform.openai.com/docs/guides/embeddings
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/embeddings
        type: Documentation
      - url: openapi/embeddings-openapi-original.yml
        type: OpenAPI
      - url: openapi/openai-embeddings-openapi.yml
        type: OpenAPI
      - url: json-schema/openai-embedding-schema.json
        type: JSONSchema
      - url: json-ld/openai-context.jsonld
        type: JSONLD
    description: >-
      Learn how to turn text into numbers, unlocking use cases like search. OpenAI's text embeddings measure the
      relatedness of text strings.
  - aid: openai:openai-files-api
    name: OpenAI Files API
    tags:
      - AI
      - Artificial Intelligence
      - Files
    score: 894
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/files
    properties:
      - url: https://platform.openai.com/docs/api-reference/files
        type: Documentation
      - url: openapi/files-openapi-original.yml
        type: OpenAPI
    description: >-
      Files are used to upload documents that can be used with features like Assistants and Fine-tuning. Upload a file
      that can be used across various endpoints. The size of all the files uploaded by one organization can be up to 100
      GB.
  - aid: openai:openai-fine-tuning-api
    name: OpenAI Fine Tuning API
    tags:
      - Fine Tune
      - Fine Tuning
    score: 492
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/guides/fine-tuning
    properties:
      - url: https://platform.openai.com/docs/guides/fine-tuning
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/fine-tuning
        type: Documentation
      - url: openapi/fine-tuning-openapi-original.yml
        type: OpenAPI
    description: >-
      Manage fine-tuning jobs to tailor a model to your specific training data. Creates a fine-tuning job which begins
      the process of creating a new model from a given dataset.Response includes details of the enqueued job including
      job status and the name of the fine-tuned models once complete.
  - aid: openai:openai-images-api
    name: OpenAI Images API
    tags:
      - Images
    score: 120
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/guides/images
    properties:
      - url: https://platform.openai.com/docs/guides/images
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/images
        type: Documentation
      - url: https://platform.openai.com/docs/guides/image-generation
        type: Documentation
      - url: https://platform.openai.com/docs/guides/images-vision
        type: Documentation
      - url: openapi/images-openapi-original.yml
        type: OpenAPI
      - url: openapi/openai-images-openapi.yml
        type: OpenAPI
      - url: json-ld/openai-context.jsonld
        type: JSONLD
    description: >-
      Learn how to generate or manipulate images with DALL_E in the API. The Images API provides three methods for
      interacting with images - creating images from scratch based on a text prompt, creating edited versions of images
      by having the model replace some areas of a pre-existing image, based on a new text prompt, Creating variations of
      an existing image.
  - aid: openai:openai-models-api
    name: OpenAI Models API
    tags:
      - Large Language Models
      - Models
    score: 201
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/models
    properties:
      - url: https://platform.openai.com/docs/models
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/models
        type: Documentation
      - url: openapi/models-openapi-original.yml
        type: OpenAPI
    description: >-
      List and describe the various models available in the API. You can refer to the Models documentation to understand
      what models are available and the differences between them.
  - aid: openai:openai-threads-api
    name: OpenAI Threads API
    tags:
      - Assistants
      - Threads
    score: 1861
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/assistants/how-it-works/managing-threads-and-messages
    properties:
      - url: https://platform.openai.com/docs/assistants/how-it-works/managing-threads-and-messages
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/threads
        type: Documentation
      - url: openapi/threads-openapi-original.yml
        type: OpenAPI
    description: Create threads that assistants can interact with.
  - aid: openai:openai-responses-api
    name: OpenAI Responses API
    tags:
      - Agents
      - Responses
      - Text Generation
      - Reasoning
      - Tools
    score: 150
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/responses
    properties:
      - url: https://platform.openai.com/docs/api-reference/responses
        type: Documentation
      - url: https://platform.openai.com/docs/guides/text
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/deep-research/
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/conversation-state/
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/migrate-to-responses/
        type: Documentation
    description: >-
      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 streamlined interface, supporting text and image inputs,
      text outputs, and built-in tools like web search, file search, computer use, code interpreter, and image
      generation. The upstream OpenAI OpenAPI spec exposes Responses as a dedicated tag group with
      create/retrieve/list/cancel/delete/stream operations plus input items management. Recommended for all new
      projects.
  - aid: openai:openai-moderations-api
    name: OpenAI Moderations API
    tags:
      - Content Safety
      - Moderation
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/moderations
    properties:
      - url: https://platform.openai.com/docs/api-reference/moderations
        type: Documentation
      - url: https://platform.openai.com/docs/guides/moderation
        type: Documentation
    description: >-
      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, sexual content, self-harm, violence, and illicit
      content. The moderation endpoint is free to use and supports the omni-moderation-latest model for multi-modal
      inputs.
  - aid: openai:openai-batch-api
    name: OpenAI Batch API
    tags:
      - Async
      - Batch
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/batch
    properties:
      - url: https://platform.openai.com/docs/api-reference/batch
        type: Documentation
      - url: https://platform.openai.com/docs/guides/batch
        type: Documentation
    description: >-
      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/completions, /v1/embeddings, /v1/completions, and
      /v1/moderations endpoints. A single batch may include up to 50,000 requests with a batch input file size up to 200
      MB.
  - aid: openai:openai-vector-stores-api
    name: OpenAI Vector Stores API
    tags:
      - Retrieval
      - Search
      - Vector Stores
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/vector-stores
    properties:
      - url: https://platform.openai.com/docs/api-reference/vector-stores
        type: Documentation
      - url: https://platform.openai.com/docs/guides/retrieval
        type: Documentation
    description: >-
      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 it is automatically chunked, embedded, and
      indexed. You can query a vector store using natural language to retrieve relevant chunks with similarity scores.
  - aid: openai:openai-uploads-api
    name: OpenAI Uploads API
    tags:
      - Files
      - Uploads
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/uploads
    properties:
      - url: https://platform.openai.com/docs/api-reference/uploads
        type: Documentation
    description: >-
      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 after an hour. Once you complete the Upload, a
      File object is created that can be used across the platform.
  - aid: openai:openai-realtime-api
    name: OpenAI Realtime API
    tags:
      - Audio
      - Realtime
      - Streaming
      - Voice
      - SIP
      - WebRTC
    score: 150
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/realtime
    properties:
      - url: https://platform.openai.com/docs/api-reference/realtime
        type: Documentation
      - url: https://platform.openai.com/docs/guides/realtime
        type: Documentation
      - url: https://platform.openai.com/docs/guides/realtime-webrtc
        type: Documentation
      - url: https://platform.openai.com/docs/guides/realtime-server-controls
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/realtime-conversations/
        type: Documentation
      - url: https://github.com/openai/openai-realtime-agents
        type: GitHubRepository
      - url: asyncapi/openai-realtime-asyncapi.yml
        type: AsyncAPI
    description: >-
      The Realtime API enables low-latency, bidirectional communication with models that natively support
      speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text).
      It supports WebRTC, WebSocket, and SIP connection methods for real-time voice agents and conversational
      interfaces. The Realtime API is represented as a dedicated tag group in the upstream OpenAI OpenAPI specification
      with operations covering client/server events, translation client secrets, and voice call lifecycle (accept,
      hangup, refer, reject).
  - aid: openai:openai-evals-api
    name: OpenAI Evals API
    tags:
      - Evals
      - Evaluation
      - Testing
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/evals
    properties:
      - url: https://platform.openai.com/docs/api-reference/evals
        type: Documentation
      - url: https://platform.openai.com/docs/guides/evals
        type: Documentation
    description: >-
      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 content criteria you specify, and are essential
      for building reliable LLM applications, especially when upgrading or trying new models.
  - aid: openai:openai-completions-api
    name: OpenAI Completions API
    tags:
      - Completions
      - Legacy
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/completions
    properties:
      - url: https://platform.openai.com/docs/api-reference/completions
        type: Documentation
      - url: openapi/completions-openapi-original.yml
        type: OpenAPI
    description: >-
      The legacy Completions API endpoint provides a freeform text completion interface using a text prompt. Unlike the
      Chat Completions endpoint which uses a list of messages, the Completions API input is a freeform text string
      called a prompt. This endpoint received its last update in July 2023.
  - aid: openai:openai-videos-api
    name: OpenAI Videos API
    tags:
      - Sora
      - Video Generation
      - Videos
    score: 150
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/videos
    properties:
      - url: https://platform.openai.com/docs/api-reference/videos
        type: Documentation
      - url: https://platform.openai.com/docs/guides/video-generation
        type: Documentation
    description: >-
      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, checking video status, downloading finished MP4 files,
      listing videos with pagination, and deleting videos from storage. Supported models include sora-2 and sora-2-pro.
  - aid: openai:openai-conversations-api
    name: OpenAI Conversations API
    tags:
      - Conversations
      - State Management
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/conversations/create
    properties:
      - url: https://platform.openai.com/docs/api-reference/conversations/create
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/conversation-state/
        type: Documentation
    description: >-
      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 metadata. Because conversations are stateful,
      managing context across conversations is handled automatically, and the /responses/compact endpoint can shrink
      context for long-running conversations.
  - aid: openai:openai-containers-api
    name: OpenAI Containers API
    tags:
      - Code Interpreter
      - Containers
      - Sandbox
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/containers
    properties:
      - url: https://platform.openai.com/docs/api-reference/containers
        type: Documentation
      - url: https://platform.openai.com/docs/api-reference/container-files
        type: Documentation
      - url: https://developers.openai.com/api/docs/guides/tools-code-interpreter/
        type: Documentation
    description: >-
      The Containers API manages sandboxed containers used by Code Interpreter for running Python, data work, file
      transforms, and iterative debugging. Containers can be created explicitly or auto-managed, with configurable
      memory limits of 1g, 4g, 16g, or 64g. Container files can be uploaded, listed, retrieved, and downloaded.
      Containers expire after 20 minutes of inactivity.
  - aid: openai:openai-chatkit-api
    name: OpenAI ChatKit API
    tags:
      - Agents
      - Chat
      - ChatKit
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference/chatkit
    properties:
      - url: https://platform.openai.com/docs/api-reference/chatkit
        type: Documentation
      - url: https://platform.openai.com/docs/guides/chatkit
        type: Documentation
      - url: https://github.com/openai/chatkit-js
        type: GitHubRepository
    description: >-
      ChatKit is the best way to build agentic chat experiences. It provides session and thread management for building
      internal knowledge base assistants, research companions, support agents, and more. ChatKit sessions include
      resolved feature configuration for automatic thread titling, file upload, and history settings. Threads have
      statuses including active, locked, and closed.
  - aid: openai:openai-skills-api
    name: OpenAI Skills API
    tags:
      - Agents
      - Codex
      - Skills
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://platform.openai.com/docs/api-reference
    properties:
      - url: https://platform.openai.com/docs/api-reference
        type: Documentation
      - url: https://github.com/openai/skills
        type: GitHubRepository
    description: >-
      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. Operations cover creating, retrieving, updating,
      deleting, and versioning skills as well as retrieving skill content. The companion github.com/openai/skills
      repository hosts a catalog of system, curated, and experimental skills.
  - aid: openai:openai-agents-sdk
    name: OpenAI Agents SDK
    tags:
      - Agents
      - SDK
      - Voice
      - Sandbox
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://github.com/openai/openai-agents-python
    properties:
      - url: https://github.com/openai/openai-agents-python
        type: GitHubRepository
      - url: https://github.com/openai/openai-agents-js
        type: GitHubRepository
    description: >-
      The OpenAI Agents SDK is a lightweight framework for building multi-agent workflows in Python and TypeScript.
      Primitives include agents (LLMs with instructions, tools, guardrails), handoffs between specialists, guardrails
      for safety checks, sessions for conversation history, tracing for run observability, and realtime agents for voice
      workflows. The SDK is provider-agnostic and supports OpenAI Responses and Chat Completions plus other LLM
      providers.
  - aid: openai:openai-codex
    name: OpenAI Codex
    tags:
      - Agents
      - Codex
      - Coding Agent
    score: 100
    baseURL: https://api.openai.com
    humanURL: https://developers.openai.com/codex
    properties:
      - url: https://developers.openai.com/codex
        type: Documentation
      - url: https://github.com/openai/codex
        type: GitHubRepository
    description: >-
      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 authenticates with a ChatGPT
      Plus/Pro/Business/Edu/Enterprise account or an API key, and integrates with the Skills catalog for repeatable task
      workflows.
name: OpenAI
tags:
  - AI
  - Artificial Intelligence
  - Large Language Models
  - T1
kind: contract
score: 308
access: 3rd-Party
common:
  - type: PostmanWorkspace
    url: https://www.postman.com/kinlaneapi/openai/overview
  - type: ArazzoWorkflows
    url: arazzo/
    workflows:
      - url: arazzo/openai-assistant-run-workflow.yml
        name: OpenAI Assistant Run
        summary: Create an assistant, open a thread, add a message, run it, poll the run, and read the reply.
      - url: arazzo/openai-batch-job-workflow.yml
        name: OpenAI Batch Job
        summary: Upload a batch input file, create a batch, poll until complete, and read the output file id.
      - url: arazzo/openai-cancel-fine-tuning-job-workflow.yml
        name: OpenAI Cancel Fine-Tuning Job
        summary: Inspect a running fine-tuning job and cancel it only if it is still in progress.
      - url: arazzo/openai-chat-then-speak-workflow.yml
        name: OpenAI Chat then Speak
        summary: Generate a chat reply, then synthesize it to spoken audio.
      - url: arazzo/openai-create-embedding-workflow.yml
        name: OpenAI Create Embedding
        summary: Confirm an embedding model exists, then embed input text.
      - url: arazzo/openai-download-batch-results-workflow.yml
        name: OpenAI Download Batch Results
        summary: Retrieve a completed batch and download its output file contents.
      - url: arazzo/openai-fine-tuning-job-workflow.yml
        name: OpenAI Fine-Tuning Job
        summary: Upload a training file, start a fine-tuning job, poll until terminal, and read the result.
      - url: arazzo/openai-generate-image-workflow.yml
        name: OpenAI Moderate then Generate Image
        summary: Screen an image prompt, then generate an image only when it is allowed.
      - url: arazzo/openai-list-models-then-chat-workflow.yml
        name: OpenAI List Models then Create Chat Completion
        summary: Discover an available model, then generate a chat completion with it.
      - url: arazzo/openai-moderate-then-chat-workflow.yml
        name: OpenAI Moderate then Chat
        summary: Screen user input with the moderation endpoint, then chat only if it is safe.
      - url: arazzo/openai-retrieve-and-delete-model-workflow.yml
        name: OpenAI Retrieve and Delete Fine-Tuned Model
        summary: Inspect a model and delete it only when it is an owned fine-tuned model.
      - url: arazzo/openai-thread-and-run-workflow.yml
        name: OpenAI Create Thread and Run
        summary: Start a thread and run in one request against an existing assistant, then poll and read the reply.
      - url: arazzo/openai-transcribe-then-summarize-workflow.yml
        name: OpenAI Transcribe then Summarize
        summary: Transcribe an audio file, then summarize the transcript with a chat completion.
      - url: arazzo/openai-upload-and-verify-file-workflow.yml
        name: OpenAI Upload and Verify File
        summary: Upload a file, confirm it appears in the file list, and retrieve its metadata.
      - url: arazzo/openai-vector-store-file-batch-workflow.yml
        name: OpenAI Vector Store File Batch
        summary: Create a vector store, attach a batch of files, and poll the batch to completion.
      - url: arazzo/openai-vector-store-ingest-file-workflow.yml
        name: OpenAI Vector Store Ingest File
        summary: Create a vector store, upload a file, attach it, and poll until it is indexed.
      - url: arazzo/openai-vector-store-search-workflow.yml
        name: OpenAI Vector Store Search
        summary: Attach a file to a vector store, wait until it is indexed, then run a semantic search.
  - type: LinkedIn
    url: https://www.linkedin.com/company/openai
  - url: https://platform.openai.com/docs/overview
    name: Overview - OpenAI API
    type: Portal
    description: 'null'
  - url: https://platform.openai.com/docs/quickstart
    name: Developer quickstart - OpenAI API
    type: GettingStarted
    description: 'null'
  - url: https://platform.openai.com/docs/libraries
    name: Libraries - OpenAI API
    type: SDKs
    description: 'null'
  - url: https://community.openai.com/categories
    name: Categories - OpenAI Developer Community
    type: Forums
    description: 'null'
  - url: https://platform.openai.com/docs/guides/rate-limits
    name: Rate limits - OpenAI API
    type: RateLimits
    description: 'null'
  - url: https://platform.openai.com/docs/deprecations
    name: Deprecations - OpenAI API
    type: Deprecations
    description: 'null'
  - url: https://openai.com/policies/
    name: Terms & policies | OpenAI
    type: TermsOfService
    description: 'null'
  - url: https://openai.com/policies/terms-of-use/
    name: Terms of use | OpenAI
    type: TermsOfService
    description: 'null'
  - url: https://openai.com/policies/privacy-policy/
    name: Privacy policy | OpenAI
    type: PrivacyPolicy
    description: 'null'
  - url: https://platform.openai.com/docs/overview
    name: Overview - OpenAI API
    type: Documentation
    description: 'null'
  - url: https://help.openai.com/en
    name: OpenAI Help Center
    type: Support
    description: 'null'
  - url: https://status.openai.com/
    name: OpenAI Status
    type: StatusPage
    description: 'null'
  - url: https://platform.openai.com/docs/api-reference/authentication
    name: API Reference - OpenAI API
    type: Authentication
    description: 'null'
  - url: https://platform.openai.com/docs/api-reference/webhook_events/response
    name: API Reference - OpenAI API
    type: Webhooks
    description: 'null'
  - url: properties/openai-openapi
    name: OpenAPI
    type: OpenAPI
  - url: json-schema/openai-chat-completion-schema.json
    name: Chat Completion JSON Schema
    type: JSONSchema
    description: 'null'
  - url: json-schema/openai-embedding-schema.json
    name: Embedding JSON Schema
    type: JSONSchema
    description: 'null'
  - url: json-ld/openai-context.jsonld
    name: OpenAI JSON-LD Context
    type: JSONLD
    description: 'null'
  - url: https://github.com/openai
    name: GitHub Organization
    type: GitHubOrganization
  - url: https://openai.com/api/pricing/
    data:
      - id: free
        name: Free
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: 0
            metric: user
            timeFrame: month
            description: User based pricing.
        elements:
          - name: Access to GPT5
          - name: Real-time data from the web with search
          - name: Limited access to file uploads, data analysis, image generation, and voice mode
          - name: Code edits with the ChatGPT desktop app for macOS
          - name: Use custom GPTs
        description: Explore how AI can help with everyday tasks
      - id: plus
        name: Plus
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: $20.00
            metric: user
            timeFrame: month
            description: User based pricing.
        elements:
          - name: Extended access to GPT5, our flagship model
          - name: Extended limits on messaging, file uploads, data analysis, and image generation
          - name: Standard and advanced voice mode with video and screensharing
          - name: Access to ChatGPT agent
          - name: Create and use projects, tasks, and custom GPTs
          - name: Limited access to Sora video generation
          - name: Opportunities to test new features
        description: Level up productivity and creativity with expanded access
      - id: pro
        name: Pro
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: $200.00
            metric: user
            timeFrame: month
            description: User based pricing.
        elements:
          - name: Unlimited access to GPT5
          - name: Access to GPT5 pro, which uses more compute for the best answers to the hardest questions
          - name: Unlimited access to advanced voice, with higher limits for video and screensharing
          - name: Access to OpenAI o3pro, which uses more compute for the best answers to the hardest questions
          - name: Extended access to ChatGPT agent
          - name: Extended access to Sora video generation
          - name: Access to research preview of Codex agent
        description: Get the best of OpenAI with the highest level of access
      - id: team
        name: Team
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: $25.00
            metric: user
            timeFrame: month
            description: User based pricing.
        elements:
          - name: >-
              Unlimited GPT5 messages, with generous access to GPT5 thinking, and access to GPT5 proplus the flexibility
              to add credits as needed
          - name: A secure, dedicated workspace with essential admin controls, SAML SSO, and MFA
          - name: Team data is excluded from training by default, with encryption at rest and in transit. Learn more`
          - name: >-
              Support for compliance with GDPR, CCPA, and other privacy laws. Aligned with CSA STAR` and SOC 2 Type 2
              Trust Services Criteria.
          - name: Connectors to apps for more personalized answersGoogle Drive, SharePoint, GitHub, Notion, and more
          - name: >-
              Business features like data analysis, record mode, canvas, projects, tasks, custom workspace GPTs, and
              deep research
          - name: >-
              Includes access to Codex and ChatGPT agent for reasoning and taking action across your documents, tools,
              and codebases
        description: A secure, collaborative workspace for startups and growing teams
 

# --- truncated at 32 KB (55 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/apis.yml