OpenAI
APIs for accessing OpenAI's artificial intelligence models including GPT, DALL-E, Whisper, and Embeddings.
25 APIs
16 Features
AIArtificial IntelligenceLarge Language ModelsT1
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...
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.
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.
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 jus...
Learn how to turn text into numbers, unlocking use cases like search. OpenAI's text embeddings measure the relatedness of text strings.
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 f...
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.Respons...
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 te...
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.
Create threads that assistants can interact with.
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...
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...
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...
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 ...
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...
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...
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...
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 Co...
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...
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...
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...
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...
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...
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 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...
Create an assistant, open a thread, add a message, run it, poll the run, and read the reply.
ARAZZO
Upload a batch input file, create a batch, poll until complete, and read the output file id.
ARAZZO
Inspect a running fine-tuning job and cancel it only if it is still in progress.
ARAZZO
Generate a chat reply, then synthesize it to spoken audio.
ARAZZO
Confirm an embedding model exists, then embed input text.
ARAZZO
Retrieve a completed batch and download its output file contents.
ARAZZO
Upload a training file, start a fine-tuning job, poll until terminal, and read the result.
ARAZZO
Screen an image prompt, then generate an image only when it is allowed.
ARAZZO
Discover an available model, then generate a chat completion with it.
ARAZZO
Screen user input with the moderation endpoint, then chat only if it is safe.
ARAZZO
Inspect a model and delete it only when it is an owned fine-tuned model.
ARAZZO
Start a thread and run in one request against an existing assistant, then poll and read the reply.
ARAZZO
Transcribe an audio file, then summarize the transcript with a chat completion.
ARAZZO
Upload a file, confirm it appears in the file list, and retrieve its metadata.
ARAZZO
Create a vector store, attach a batch of files, and poll the batch to completion.
ARAZZO
Create a vector store, upload a file, attach it, and poll until it is indexed.
ARAZZO
Attach a file to a vector store, wait until it is indexed, then run a semantic search.
ARAZZO
GPT-5.5 flagship model at $5/$30 per MTok input/output
GPT-5.5 Pro for highest reasoning at $30/$180 per MTok
GPT-5.4 mid-tier balanced model at $2.50/$15 per MTok
GPT-5.4 Mini at $0.75/$4.50 per MTok
GPT-5.4 Nano cheapest model at $0.20/$1.25 per MTok
GPT Realtime 1.5 for low-latency voice with separate audio pricing
Cached input at ~10x discount vs uncached
Batch API at 50% discount on input and output
Flex tier for reduced cost / lower priority workloads
Vision, tool use, structured outputs, and function calling
Six usage tiers (Free + Tier 1-5) with automatic spend-based advancement
Five rate limit metrics: RPM, RPD, TPM, TPD, IPM
Per-model rate ceilings; X-RateLimit-* headers on every response
Project-level API keys for cost allocation
Cost Tracking API and per-project hard spend limits
Regional data residency with 10% uplift
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.
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.
opencollection: 1.0.0
info:
name: OpenAI API
version: 2.3.0
request:
auth:
type: bearer
token: '{{bearerToken}}'
items:
- info:
name: Assistants
type: folder
items:
- info:
name: Returns a list of assistants.
type: http
http:
method: GET
url: https://api.openai.com/v1/assistants
params:
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: before
value: ''
type: query
description: 'A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo
in order to fetch the previous page of the list.
'
docs: Returns a list of assistants.
- info:
name: Create an assistant with a model and instructions.
type: http
http:
method: POST
url: https://api.openai.com/v1/assistants
body:
type: json
data: '{}'
docs: Create an assistant with a model and instructions.
- info:
name: Retrieves an assistant.
type: http
http:
method: GET
url: https://api.openai.com/v1/assistants/:assistant_id
params:
- name: assistant_id
value: ''
type: path
description: The ID of the assistant to retrieve.
docs: Retrieves an assistant.
- info:
name: Modifies an assistant.
type: http
http:
method: POST
url: https://api.openai.com/v1/assistants/:assistant_id
params:
- name: assistant_id
value: ''
type: path
description: The ID of the assistant to modify.
body:
type: json
data: '{}'
docs: Modifies an assistant.
- info:
name: Delete an assistant.
type: http
http:
method: DELETE
url: https://api.openai.com/v1/assistants/:assistant_id
params:
- name: assistant_id
value: ''
type: path
description: The ID of the assistant to delete.
docs: Delete an assistant.
- info:
name: Create a thread.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads
body:
type: json
data: '{}'
docs: Create a thread.
- info:
name: Create a thread and run it in one request.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/runs
body:
type: json
data: '{}'
docs: Create a thread and run it in one request.
- info:
name: Retrieves a thread.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to retrieve.
docs: Retrieves a thread.
- info:
name: Modifies a thread.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to modify. Only the `metadata` can be modified.
body:
type: json
data: '{}'
docs: Modifies a thread.
- info:
name: Delete a thread.
type: http
http:
method: DELETE
url: https://api.openai.com/v1/threads/:thread_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to delete.
docs: Delete a thread.
- info:
name: Returns a list of messages for a given thread.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/messages
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) the messages belong to.
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: before
value: ''
type: query
description: 'A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo
in order to fetch the previous page of the list.
'
- name: run_id
value: ''
type: query
description: 'Filter messages by the run ID that generated them.
'
docs: Returns a list of messages for a given thread.
- info:
name: Create a message.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/messages
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) to create a message for.
body:
type: json
data: '{}'
docs: Create a message.
- info:
name: Retrieve a message.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/messages/:message_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) to which this message belongs.
- name: message_id
value: ''
type: path
description: The ID of the message to retrieve.
docs: Retrieve a message.
- info:
name: Modifies a message.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/messages/:message_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to which this message belongs.
- name: message_id
value: ''
type: path
description: The ID of the message to modify.
body:
type: json
data: '{}'
docs: Modifies a message.
- info:
name: Deletes a message.
type: http
http:
method: DELETE
url: https://api.openai.com/v1/threads/:thread_id/messages/:message_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to which this message belongs.
- name: message_id
value: ''
type: path
description: The ID of the message to delete.
docs: Deletes a message.
- info:
name: Returns a list of runs belonging to a thread.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/runs
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread the run belongs to.
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: before
value: ''
type: query
description: 'A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo
in order to fetch the previous page of the list.
'
docs: Returns a list of runs belonging to a thread.
- info:
name: Create a run.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/runs
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to run.
- name: include[]
value: ''
type: query
description: 'A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content`
to fetch the file search result content.
See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for
more information.
'
body:
type: json
data: '{}'
docs: Create a run.
- info:
name: Retrieves a run.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) that was run.
- name: run_id
value: ''
type: path
description: The ID of the run to retrieve.
docs: Retrieves a run.
- info:
name: Modifies a run.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) that was run.
- name: run_id
value: ''
type: path
description: The ID of the run to modify.
body:
type: json
data: '{}'
docs: Modifies a run.
- info:
name: Cancels a run that is `in_progress`.
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id/cancel
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to which this run belongs.
- name: run_id
value: ''
type: path
description: The ID of the run to cancel.
docs: Cancels a run that is `in_progress`.
- info:
name: Returns a list of run steps belonging to a run.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id/steps
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread the run and run steps belong to.
- name: run_id
value: ''
type: path
description: The ID of the run the run steps belong to.
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: before
value: ''
type: query
description: 'A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo
in order to fetch the previous page of the list.
'
- name: include[]
value: ''
type: query
description: 'A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content`
to fetch the file search result content.
See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for
more information.
'
docs: Returns a list of run steps belonging to a run.
- info:
name: Retrieves a run step.
type: http
http:
method: GET
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id/steps/:step_id
params:
- name: thread_id
value: ''
type: path
description: The ID of the thread to which the run and run step belongs.
- name: run_id
value: ''
type: path
description: The ID of the run to which the run step belongs.
- name: step_id
value: ''
type: path
description: The ID of the run step to retrieve.
- name: include[]
value: ''
type: query
description: 'A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content`
to fetch the file search result content.
See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for
more information.
'
docs: Retrieves a run step.
- info:
name: 'When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint
can be used to submit the outputs from the tool calls once they''re all completed. All outputs must be submitted in
a single request.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/threads/:thread_id/runs/:run_id/submit_tool_outputs
params:
- name: thread_id
value: ''
type: path
description: The ID of the [thread](/docs/api-reference/threads) to which this run belongs.
- name: run_id
value: ''
type: path
description: The ID of the run that requires the tool output submission.
body:
type: json
data: '{}'
docs: 'When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint
can be used to submit the outputs from the tool calls once they''re all completed. All outputs must be submitted in
a single request.
'
- info:
name: Audio
type: folder
items:
- info:
name: 'Generates audio from the input text.
Returns the audio file content, or a stream of audio events.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/speech
body:
type: json
data: '{}'
docs: 'Generates audio from the input text.
Returns the audio file content, or a stream of audio events.
'
- info:
name: 'Transcribes audio into the input language.
Returns a transcription object in `json`, `diarized_json`, or `verbose_json`
format, or a stream of transcript events.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/transcriptions
body:
type: multipart-form
data: []
docs: 'Transcribes audio into the input language.
Returns a transcription object in `json`, `diarized_json`, or `verbose_json`
format, or a stream of transcript events.
'
- info:
name: Translates audio into English.
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/translations
body:
type: multipart-form
data: []
docs: Translates audio into English.
- info:
name: Returns a list of voice consent recordings.
type: http
http:
method: GET
url: https://api.openai.com/v1/audio/voice_consents
params:
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
docs: 'List consent recordings available to your organization for creating custom voices.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.
'
- info:
name: Upload a voice consent recording.
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/voice_consents
body:
type: multipart-form
data: []
docs: 'Upload a consent recording that authorizes creation of a custom voice.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices) for requirements and best practices. Custom
voices are limited to eligible customers.
'
- info:
name: Retrieves a voice consent recording.
type: http
http:
method: GET
url: https://api.openai.com/v1/audio/voice_consents/:consent_id
params:
- name: consent_id
value: ''
type: path
description: The ID of the consent recording to retrieve.
docs: 'Retrieve consent recording metadata used for creating custom voices.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.
'
- info:
name: Updates a voice consent recording (metadata only).
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/voice_consents/:consent_id
params:
- name: consent_id
value: ''
type: path
description: The ID of the consent recording to update.
body:
type: json
data: '{}'
docs: 'Update consent recording metadata used for creating custom voices. This endpoint updates metadata only and does
not replace the underlying audio.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.
'
- info:
name: Deletes a voice consent recording.
type: http
http:
method: DELETE
url: https://api.openai.com/v1/audio/voice_consents/:consent_id
params:
- name: consent_id
value: ''
type: path
description: The ID of the consent recording to delete.
docs: 'Delete a consent recording that was uploaded for creating custom voices.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.
'
- info:
name: Creates a custom voice.
type: http
http:
method: POST
url: https://api.openai.com/v1/audio/voices
body:
type: multipart-form
data: []
docs: 'Create a custom voice you can use for audio output (for example, in Text-to-Speech and the Realtime API). This
requires an audio sample and a previously uploaded consent recording.
See the [custom voices guide](/docs/guides/text-to-speech#custom-voices) for requirements and best practices. Custom
voices are limited to eligible customers.
'
- info:
name: Batch
type: folder
items:
- info:
name: List your organization's batches.
type: http
http:
method: GET
url: https://api.openai.com/v1/batches
params:
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
docs: List your organization's batches.
- info:
name: Creates and executes a batch from an uploaded file of requests
type: http
http:
method: POST
url: https://api.openai.com/v1/batches
body:
type: json
data: '{}'
docs: Creates and executes a batch from an uploaded file of requests
- info:
name: Retrieves a batch.
type: http
http:
method: GET
url: https://api.openai.com/v1/batches/:batch_id
params:
- name: batch_id
value: ''
type: path
description: The ID of the batch to retrieve.
docs: Retrieves a batch.
- info:
name: Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to
`cancelled`, where it will have partial results (if any) available in the output file.
type: http
http:
method: POST
url: https://api.openai.com/v1/batches/:batch_id/cancel
params:
- name: batch_id
value: ''
type: path
description: The ID of the batch to cancel.
docs: Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to
`cancelled`, where it will have partial results (if any) available in the output file.
- info:
name: Chat
type: folder
items:
- info:
name: 'List stored Chat Completions. Only Chat Completions that have been stored
with the `store` parameter set to `true` will be returned.
'
type: http
http:
method: GET
url: https://api.openai.com/v1/chat/completions
params:
- name: model
value: ''
type: query
description: The model used to generate the Chat Completions.
- name: metadata
value: ''
type: query
description: 'A list of metadata keys to filter the Chat Completions by. Example:
`metadata[key1]=value1&metadata[key2]=value2`
'
- name: after
value: ''
type: query
description: Identifier for the last chat completion from the previous pagination request.
- name: limit
value: ''
type: query
description: Number of Chat Completions to retrieve.
- name: order
value: ''
type: query
description: Sort order for Chat Completions by timestamp. Use `asc` for ascending order or `desc` for descending
order. Defaults to `asc`.
docs: 'List stored Chat Completions. Only Chat Completions that have been stored
with the `store` parameter set to `true` will be returned.
'
- info:
name: '**Starting a new project?** We recommend trying [Responses](/docs/api-reference/responses)
to take advantage of the latest OpenAI platform features. Compare
[Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses).
---
Creates a model response for the given chat conversation. Learn more in the
[text generation](/docs/guides/text-generation), [vision](/docs/guides/vision),
and [audio](/docs/guides/audio) guides.
Parameter support can differ depending on the model used to generate the
response, particularly for newer reasoning models. Parameters that are only
supported for reasoning models are noted below. For the current state of
unsupported parameters in reasoning models,
[refer to the reasoning guide](/docs/guides/reasoning).
Returns a chat completion object, or a streamed sequence of chat completion
chunk objects if the request is streamed.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/chat/completions
body:
type: json
data: '{}'
docs: '**Starting a new project?** We recommend trying [Responses](/docs/api-reference/responses)
to take advantage of the latest OpenAI platform features. Compare
[Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses).
---
Creates a model response for the given chat conversation. Learn more in the
[text generation](/docs/guides/text-generation), [vision](/docs/guides/vision),
and [audio](/docs/guides/audio) guides.
Parameter support can differ depending on '
- info:
name: 'Get a stored chat completion. Only Chat Completions that have been created
with the `store` parameter set to `true` will be returned.
'
type: http
http:
method: GET
url: https://api.openai.com/v1/chat/completions/:completion_id
params:
- name: completion_id
value: ''
type: path
description: The ID of the chat completion to retrieve.
docs: 'Get a stored chat completion. Only Chat Completions that have been created
with the `store` parameter set to `true` will be returned.
'
- info:
name: 'Modify a stored chat completion. Only Chat Completions that have been
created with the `store` parameter set to `true` can be modified. Currently,
the only supported modification is to update the `metadata` field.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/chat/completions/:completion_id
params:
- name: completion_id
value: ''
type: path
description: The ID of the chat completion to update.
body:
type: json
data: '{}'
docs: 'Modify a stored chat completion. Only Chat Completions that have been
created with the `store` parameter set to `true` can be modified. Currently,
the only supported modification is to update the `metadata` field.
'
- info:
name: 'Delete a stored chat completion. Only Chat Completions that have been
created with the `store` parameter set to `true` can be deleted.
'
type: http
http:
method: DELETE
url: https://api.openai.com/v1/chat/completions/:completion_id
params:
- name: completion_id
value: ''
type: path
description: The ID of the chat completion to delete.
docs: 'Delete a stored chat completion. Only Chat Completions that have been
created with the `store` parameter set to `true` can be deleted.
'
- info:
name: 'Get the messages in a stored chat completion. Only Chat Completions that
have been created with the `store` parameter set to `true` will be
returned.
'
type: http
http:
method: GET
url: https://api.openai.com/v1/chat/completions/:completion_id/messages
params:
- name: completion_id
value: ''
type: path
description: The ID of the chat completion to retrieve messages from.
- name: after
value: ''
type: query
description: Identifier for the last message from the previous pagination request.
- name: limit
value: ''
type: query
description: Number of messages to retrieve.
- name: order
value: ''
type: query
description: Sort order for messages by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults
to `asc`.
docs: 'Get the messages in a stored chat completion. Only Chat Completions that
have been created with the `store` parameter set to `true` will be
returned.
'
- info:
name: Completions
type: folder
items:
- info:
name: 'Creates a completion for the provided prompt and parameters.
Returns a completion object, or a sequence of completion objects if the request is streamed.
'
type: http
http:
method: POST
url: https://api.openai.com/v1/completions
body:
type: json
data: '{}'
docs: 'Creates a completion for the provided prompt and parameters.
Returns a completion object, or a sequence of completion objects if the request is streamed.
'
- info:
name: Default
type: folder
items:
- info:
name: List Containers
type: http
http:
method: GET
url: https://api.openai.com/v1/containers
params:
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
- name: after
value: ''
type: query
description: 'A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance,
if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
'
- name: name
value: ''
type: query
description: Filter results by container name.
docs: Lists containers.
- info:
name: Create Container
type: http
http:
method: POST
url: https://api.openai.com/v1/containers
body:
type: json
data: '{}'
docs: Creates a container.
- info:
name: Retrieve Container
type: http
http:
method: GET
url: https://api.openai.com/v1/containers/:container_id
params:
- name: container_id
value: ''
type: path
docs: Retrieves a container.
- info:
name: Delete Container
type: http
http:
method: DELETE
url: https://api.openai.com/v1/containers/:container_id
params:
- name: container_id
value: ''
type: path
description: The ID of the container to delete.
docs: Delete a container.
- info:
name: List Container files
type: http
http:
method: GET
url: https://api.openai.com/v1/containers/:container_id/files
params:
- name: container_id
value: ''
type: path
- name: limit
value: ''
type: query
description: 'A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default
is 20.
'
- name: order
value: ''
type: query
description: 'Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending
order.
'
# --- truncated at 32 KB (174 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/apis.yml