:root {
  --rounded-sm: 8px;
  --rounded: 8px;
  --rounded-md: 8px;
  --rounded-lg: 8px;
  --rounded-xl: 8px;
  --rounded-2xl: 8px;
  --rounded-search: 8px;
  --rounded-3xl: 8px;
  --rounded-full: 8px;
  --card-gradient-hover: linear-gradient(90deg,rgba(86,88,105,.5),rgba(86,88,105,.6),rgba(86,88,105,.7));
  --text-default: #acacbe;

  --gray-0: #fff;
  --gray-100: #ececf1;

  --green-600: #10a37f;
  --green-700: #1a7f64;

  --method-pill-bg: linear-gradient( 45deg, rgba(0, 0, 0, .4) 0%, rgba(0, 0, 0, .2) 100% );

  --side-nav-width: 216px;
  --docs-page-max-width: 680px;
}

:root.dark {
  --gray-100: #353740;
  --gray-400: #acacbe;
  --gray-600: #6e6e80;

  --text-secondary: var(--gray-400);
}

* {
  scrollbar-width: thin;
}

#sidebar-content {
  width: var(--side-nav-width);
}

#content-area {
  max-width: var(--docs-page-max-width);
}

#content-container {
  > div {
    column-gap: 1.5rem;
  }
  
  @media (min-width: 1024px) {
    margin-left: var(--side-nav-width);
  }
}

.dark\:text-gray-400:is(.dark *) {
  color: var(--text-secondary) !important;
}

.mdx-content {
  color: #353740 !important;
}

.dark .mdx-content {
  color: var(--text-default) !important;
}

.dark {
  #content-container {
    background-color: #202123 !important;
  }

  div[data-component-part="accordion-caret-right"] > svg {
    background-color: #9ea3a2 !important;
  }
}

#search-bar-entry {
  .dark & {
    border: 1px solid #565869;
  }

  border: 1px solid #d9d9e3;
}

#page-title {
  font-weight: 600;
}

.method-pill {
  background: transparent !important;
  color: var(--text-secondary) !important;
}

.tryit-button {
  background-color: var(--green-600) !important;
}

.mdx-content {
  .link {
    color: var(--green-600) !important;
    border-bottom: none;
  }

  .link:hover {
    color: var(--green-700) !important;
    border-bottom: none;
  }
}

.prose {
  line-height: 1.6em;

  a code {
    text-decoration: none;
    color: var(--green-600) !important;
  }

}

#topbar-cta-button > a {
  background-color: #10a37f;
}

.card {
  background-color: transparent !important;
  border: none !important;
  margin-bottom: 20px;

  > div {
    align-items: start;
    padding: 0;
  }

  [data-component-part="card-title"] {
    font-weight: 500;
  }

  [data-component-part="card-icon"] {
    background-color: transparent;
    border: 1px solid #ececf1;
    
    .dark & {
      background: linear-gradient(90deg,rgba(86,88,105,.5),rgba(86,88,105,.6),rgba(86,88,105,.7));
      border: none
    }
    
    border-radius: var(--rounded);
    width: 48px;
    height: 48px;
    display: flex;
    justify-content: center;
    align-items: center;
    flex-shrink: 0;

    > svg {
      color: white;
    }
  }
}

.navbar-link {
  @media (min-width: 1024px) {
    background-color: #6e6e80 !important;
    &:hover {
      background-color: #565869 !important;
    }

    color: #fff !important;
    > a {
      color: inherit !important;
      &:hover {
        color: inherit !important;
      }
    }
  }
}

.method-nav-pill {
  display: none;
}

.bottom-anchor:hover {
  background-color: #8e8ea020;
  transition: background-color 0.15s ease;
}

.panel {
  max-height: 100%;
  min-height: 18rem;

  .code-block {
    margin: 0;
    display: grid;
    overflow: hidden;
    width: 100%;

    [data-component-part="code-block-root"] {
      overflow: auto;

      > div {
        overflow-y: unset !important;
        overflow-x: unset !important;
      }
    }
  }
}

ul[data-component-part="tabs-list"]:not(.api-section ul[data-component-part="tabs-list"]) {
  margin-bottom: 0.5rem;
  border-radius: var(--rounded-lg);
  border: none;
  padding: 2px;
  gap: 0;
  flex-wrap: wrap;
  width: fit-content;
  min-width: fit-content;
  overflow-x: auto;

  background-color: #ececf1;
  .dark & {
    background-color: black;
  }

  [data-component-part="tab-button"] {
    border: none;
    padding: 3px 12px;
    font-size: 14px;
    font-weight: 600;
    border-radius: var(--rounded-lg);
    margin: 0;
  }

  [data-component-part="tab-button"] {
    color: var(--text-secondary) !important;
  }

  [data-component-part="tab-button"].text-primary {
    background-color: white !important;
    .dark & {
      background-color: #353740 !important;
    }

    color: black !important;
    .dark & {
      color: white !important;
    }
  }
}

#sidebar-content button:nth-child(2) {
  display: none;
}


April, 2025

March, 2025

Apr 14

Mar 20

Mar 19

Mar 11

February, 2025

Mar 03

January, 2025

Feb 27

Jan 31

Changelog

OpenAI

Take your first steps with the OpenAI API.

Quickstart

Developer quickstart

Set up your development environment to use the OpenAI API with an SDK in your preferred language.

Libraries

Learn how to use vision capabilities to understand images.

Images and Vision

Learn how to stream model responses from the OpenAI API using server-sent events.

Streaming

Streaming API responses

Use built-in tools like web search and file search to extend the model's capabilities.

Using built-in Tools

Built-in tools

Learn how to build voice agents that can understand audio and respond back in natural language.

Voice Agents

Learn about automatic voice activity detection in the Realtime API.

Voice Activity Detection

Voice activity detection (VAD)

Identify potentially harmful content in text and images.

Moderation

Improve smaller models with distillation techniques.

Distillation

Model distillation

Implement safety measures like moderation and human oversight.

Safety Best Practices

Build AI Assistants with essential tools and integrations.

Overview

Assistants API overview

Use the Create chat completion endpoint to create a new chat completion.

Create chat completion

List assistants

Create an assistant with a model and instructions.

Create assistant

Retrieve assistant

Modify assistant

Delete assistant

Create thread

Create a thread and run it in one request.

Create thread and run

Retrieve thread.

Modify thread

Delete thread

Returns a list of messages for a given thread.

List messages

Create message

Retrieve message

Modify message

Delete message

Returns a list of runs belonging to a thread.

List runs

Create run

Retrieve run

Modify run

Cancel run

Returns a list of run steps belonging to a run.

List run steps

Retrieve run step

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.


The run step object

Generate speech

Transcribes audio into the input language.

Create transcription

Create translation

List batch

Creates and executes a batch from an uploaded file of requests

Create batch

Retrieve batch

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.

Cancel batch

List stored Chat Completions. Only Chat Completions that have been stored
with the `store` parameter set to `true` will be returned.


List Chat Completions

**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).


Get a stored chat completion. Only Chat Completions that have been created
with the `store` parameter set to `true` will be returned.


Get chat completion

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.


Update chat completion

Delete a stored chat completion. Only Chat Completions that have been
created with the `store` parameter set to `true` can be deleted.


Delete chat completion

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.


Get chat messages

Creates a completion for the provided prompt and parameters.

Create completion

Creates an embedding vector representing the input text.

Create embeddings

List evals

Create the structure of an evaluation that can be used to test a model's performance.
An evaluation is a set of testing criteria and a datasource. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources.
For more information, see the [Evals guide](/docs/guides/evals).


Create eval

Get an eval

Update certain properties of an evaluation.

Update an eval

Delete an eval


Get eval runs

Create a new evaluation run. This is the endpoint that will kick off grading.

Create eval run

Get an eval run

Cancel eval run

Delete an eval run.


Get a list of output items for an evaluation run.

Get eval run output items

Get an output item of an eval run

Returns a list of files.

Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB.

The Assistants API supports files up to 2 million tokens and of specific file types. See the [Assistants Tools guide](/docs/assistants/tools) for details.

The Fine-tuning API only supports `.jsonl` files. The input also has certain required formats for fine-tuning [chat](/docs/api-reference/fine-tuning/chat-input) or [completions](/docs/api-reference/fine-tuning/completions-input) models.

The Batch API only supports `.jsonl` files up to 200 MB in size. The input also has a specific required [format](/docs/api-reference/batch/request-input).

Please [contact us](https://help.openai.com/) if you need to increase these storage limits.


Upload a file

Returns information about a specific file.

Delete a file.

Returns the contents of the specified file.

**NOTE:** This endpoint requires an [admin API key](../admin-api-keys).

Organization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint.


List checkpoint permissions

**NOTE:** Calling this endpoint requires an [admin API key](../admin-api-keys).

This enables organization owners to share fine-tuned models with other projects in their organization.


Create checkpoint permissions

**NOTE:** This endpoint requires an [admin API key](../admin-api-keys).

Organization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint.


Delete checkpoint permission

List your organization's fine-tuning jobs


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.

[Learn more about fine-tuning](/docs/guides/fine-tuning)


Create a fine-tuning job

Get info about a fine-tuning job.
[Learn more about fine-tuning](/docs/guides/fine-tuning)

Retrieve fine-tuning job

Immediately cancel a fine-tune job.


List checkpoints for a fine-tuning job.


Get status updates for a fine-tuning job.


Creates an edited or extended image given an original image and a prompt.

Create image edit

Create image

Create image variation

Lists the currently available models, and provides basic information about each one such as the owner and availability.

List models

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

Retrieve model

Delete a fine-tuned model. You must have the Owner role in your organization to delete a model.

Delete a fine-tuned model

Classifies if text and/or image inputs are potentially harmful. Learn more in the [moderation guide](/docs/guides/moderation).

Create moderation

Retrieve a paginated list of organization admin API keys.

List organization API keys

Create a new admin-level API key for the organization.

Create an organization admin API key

Get details for a specific organization API key by its ID.

Retrieve a single organization API key

Delete an organization admin API key

List user actions and configuration changes within this organization.

List audit logs

List uploaded certificates for this organization.

List organization certificates

Upload a certificate to the organization. This does **not** automatically activate the certificate.

Organizations can upload up to 50 certificates.


Upload certificate

Activate certificates at the organization level. You can atomically and idempotently activate up to 10 certificates at a time.

Activate certificates for organization

Deactivate certificates at the organization level. You can atomically and idempotently deactivate up to 10 certificates at a time.

Deactivate certificates for organization

Get a certificate that has been uploaded to the organization.

You can get a certificate regardless of whether it is active or not.


Get certificate

Modify a certificate. Note that only the name can be modified.

Modify certificate

Delete a certificate from the organization.
The certificate must be inactive for the organization and all projects.

Delete certificate

List project certificates

Activate certificates at the project level.
You can atomically and idempotently activate up to 10 certificates at a time.

Activate project certificates

Deactivate certificates at the project level.
You can atomically and idempotently deactivate up to 10 certificates at a time.

Deactivate project certificates

Costs

Get audio speeches usage details for the organization.

Audio speeches

Get audio transcriptions usage details for the organization.

Audio transcriptions

Get code interpreter sessions usage details for the organization.

Code interpreter sessions

Get completions usage details for the organization.

Completions

Get embeddings usage details for the organization.

Embeddings

Get images usage details for the organization.

Images

Get moderations usage details for the organization.

Moderations

Get vector stores usage details for the organization.

Vector stores

Returns a list of invites in the organization.

List invites

Create an invite for a user to the organization. The invite must be accepted by the user before they have access to the organization.

Create invite

Retrieve invite

Delete an invite. If the invite has already been accepted, it cannot be deleted.

Delete invite

Returns a list of projects.

Create a new project in the organization. Projects can be created and archived, but cannot be deleted.

Get Started

Core Concepts

Built-In-Tools

Agents

Realtime API

Specialized Models

OpenAI Platform

Best Practices

Assistant API

Resources

Changelog

April, 2025

March, 2025

February, 2025

January, 2025

Get Started

Core Concepts

Built-In-Tools

Agents

Realtime API

Specialized Models

OpenAI Platform

Best Practices

Assistant API

Resources

​April, 2025

​March, 2025

​February, 2025

​January, 2025

April, 2025

March, 2025

February, 2025

January, 2025