OpenAI

Accept an incoming SIP call and configure the realtime session that will handle it.

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

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

Adds a user to a group.

Grants a group access to a project.

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

Delete the specified admin API key.

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

Retrieve a paginated list of organization admin API keys.

Archives a project in the organization. Archived projects cannot be used or updated.

Assigns an organization role to a group within the organization.

Assigns a project role to a group within a project.

Assigns a project role to a user within a project.

Assigns an organization role to a user within the organization.

Cancels a model response with the given ID. Only responses created with the `background` parameter set to `true` can be cancelled. [Learn more](/docs/guides/background).

Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](/docs/guides/conversation-state#compaction-advanced).

Creates a model response. Provide [text](/docs/guides/text) or [image](/docs/guides/images) inputs to generate [text](/docs/guides/text) or [JSON](/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](/docs/guides/function-calling) or use built-in [tools](/docs/guides/tools) like [web search](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search) to use your own data as input for the model's response.

Deletes a model response with the given ID.

Retrieves a model response with the given ID.

Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.

Returns a list of input items for a given response.

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 an active ChatKit session and return its most recent metadata. Cancelling prevents new requests from using the issued client secret.

Cancel an ongoing evaluation run.

Immediately cancel a fine-tune job.

Cancels a model response with the given ID. Only responses created with the `background` parameter set to `true` can be cancelled. [Learn more](/docs/guides/background).

Cancels a run that is `in_progress`.

Cancels the Upload. No Parts may be added after an Upload is cancelled. Returns the Upload object with status `cancelled`.

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](/docs/guides/conversation-state#compaction-advanced).

Completes the [Upload](/docs/api-reference/uploads/object). Within the returned Upload object, there is a nested [File](/docs/api-reference/files/object) object that is ready to use in the rest of the platform. You can specify the order of the Parts by passing in an ordered list of the Part IDs. The number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed. Returns the Upload object with status `completed`, including an additional `file` property containing the created usable File object.

Create an assistant with a model and instructions.

Creates and executes a batch from an uploaded file of requests

**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.

Create a ChatKit session.

Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed.

Creates a container.

Creates a container file.

Create a conversation.

Create items in a conversation with the given ID.

Creates an embedding vector representing the input text.

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 the config for a data source, which dictates the schema of the data used in the evaluation. 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).

Kicks off a new run for a given evaluation, specifying the data source, and what model configuration to use to test. The datasource will be validated against the schema specified in the config of the evaluation.

**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.

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/model-optimization)

Creates a new group in the organization.

Creates an image given a prompt. [Learn more](/docs/guides/images).

You can call this endpoint with either: - `multipart/form-data`: use binary uploads via `image` (and optional `mask`). - `application/json`: use `images` (and optional `mask`) as references with either `image_url` or `file_id`. Note that JSON requests use `images` (array) instead of the multipart `image` field.

Create a message.

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

Creates an organization spend alert.

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

Creates a custom role for a project.

Creates a new service account in the project. By default, this also returns an unredacted API key for the service account.

Creates a project spend alert.

Adds a user to the project. Users must already be members of the organization to be added to a project.

Create a Realtime client secret with an associated session configuration. Client secrets are short-lived tokens that can be passed to a client app, such as a web frontend or mobile client, which grants access to the Realtime API without leaking your main API key. You can configure a custom TTL for each client secret. You can also attach session configuration options to the client secret, which will be applied to any sessions created using that client secret, but these can also be overridden by the client connection. [Learn more about authentication with client secrets over WebRTC](/docs/guides/realtime-webrtc). Returns the created client secret and the effective session object. The client secret is a string that looks like `ek_1234`.

Create an ephemeral API token for use in client-side applications with the Realtime API. Can be configured with the same session parameters as the `session.update` client event. It responds with a session object, plus a `client_secret` key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API. Returns the created Realtime session object, plus an ephemeral key.

Create an ephemeral API token for use in client-side applications with the Realtime API specifically for realtime transcriptions. Can be configured with the same session parameters as the `transcription_session.update` client event. It responds with a session object, plus a `client_secret` key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API. Returns the created Realtime transcription session object, plus an ephemeral key.

Create a Realtime translation client secret with an associated translation session configuration. Client secrets are short-lived tokens that can be passed to a client app, such as a web frontend or mobile client, which grants access to the Realtime Translation API without leaking your main API key. You can configure a custom TTL for each client secret. Returns the created client secret and the effective translation session object. The client secret is a string that looks like `ek_1234`.

Creates a model response. Provide [text](/docs/guides/text) or [image](/docs/guides/images) inputs to generate [text](/docs/guides/text) or [JSON](/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](/docs/guides/function-calling) or use built-in [tools](/docs/guides/tools) like [web search](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search) to use your own data as input for the model's response.

Creates a custom role for the organization.

Create a run.

Create a new skill.

Create a new immutable skill version.

Generates audio from the input text. Returns the audio file content, or a stream of audio events.

Create a thread.

Create a thread and run it in one request.

Creates an intermediate [Upload](/docs/api-reference/uploads/object) object that you can add [Parts](/docs/api-reference/uploads/part-object) to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it. Once you complete the Upload, we will create a [File](/docs/api-reference/files/object) object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object. For certain `purpose` values, the correct `mime_type` must be specified. Please refer to documentation for the [supported MIME types for your use case](/docs/assistants/tools/file-search#supported-files). For guidance on the proper filename extensions for each purpose, please follow the documentation on [creating a File](/docs/api-reference/files/create). Returns the Upload object with status `pending`.

Create a vector store.

This endpoint is subject to a per-vector-store write rate limit of 300 requests per minute, shared with `/vector_stores/{vector_store_id}/file_batches`. For uploading multiple files to the same vector store, use the file batches endpoint to reduce request volume.

The maximum number of files in a single batch request is 2000. Vector store file attach requests are rate limited per vector store (300 requests per minute across both this endpoint and `/vector_stores/{vector_store_id}/files`). For ingesting multiple files into the same vector store, this batch endpoint is recommended.

Create a new video generation job from a prompt and optional reference assets.

Create a new video generation job by editing a source video or existing generated video.

Create an extension of a completed video.

Create a remix of a completed video using a refreshed prompt.

Creates an API key for a service account in the project.

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

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

Delete an assistant.

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

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

Delete a container.

Delete a container file.

Delete a conversation. Items in the conversation will not be deleted.

Delete an item from a conversation with the given IDs.

Delete an evaluation.

Delete an eval run.

Delete a file and remove it from all vector stores.

**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.

Deletes a group from the organization.

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

Deletes a message.

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

Deletes an organization spend alert.

Deletes an API key from the project. Returns confirmation of the key deletion, or an error if the key belonged to a service account.

Deletes model permissions for a project.

Deletes a custom role from a project.

Deletes a service account from the project. Returns confirmation of service account deletion, or an error if the project is archived (archived projects have no service accounts).

Deletes a project spend alert.

Deletes a user from the project. Returns confirmation of project user deletion, or an error if the project is archived (archived projects have no users).

Deletes a model response with the given ID.

Deletes a custom role from the organization.

Delete a skill by its ID.

Delete a skill version.

Delete a thread.

Delete a ChatKit thread along with its items and stored attachments.

Deletes a user from the organization.

Delete a vector store.

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint.

Permanently delete a completed or failed video and its stored assets.

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.

Delete the organization's hard spend limit.

Delete a project's hard spend limit.

Returns a response containing the contents of the specified file.

Retrieves an assistant.

Get a certificate that has been uploaded to the organization. You can get a certificate regardless of whether it is active or not.

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

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 a conversation

Get a single item from a conversation with the given IDs.

Get an evaluation by ID.

Get an evaluation run by ID.

Get an evaluation run output item by ID.

Get a list of output items for an evaluation run.

Get a list of runs for an evaluation.

Retrieve a message.

Retrieves a model response with the given ID.

Retrieves a run.

Retrieves a run step.

Get a skill by its ID.

Download a skill zip bundle by its ID.

Get a specific skill version.

Download a skill version zip bundle.

Retrieves a thread.

Retrieve a ChatKit thread by its identifier.

Retrieves a vector store.

Retrieves a vector store file.

Retrieves a vector store file batch.

Fetch the latest metadata for a generated video.

Fetch a character.

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.

Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.

Get the organization's hard spend limit.

Get a project's hard spend limit.

End an active Realtime API call, whether it was initiated over SIP or WebRTC.

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

Returns a list of assistants.

List user actions and configuration changes within this organization.

List your organization's batches.

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

Lists container files.

Lists containers.

List all items for a conversation with the given ID.

List evaluations for a project.

Returns a list of files.

Returns a list of vector store files in a batch.

**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.

Get status updates for a fine-tuning job.

List checkpoints for a fine-tuning job.

Lists the organization roles assigned to a group within the organization.

Lists the users assigned to a group.

Lists all groups in the organization.

Returns a list of input items for a given response.

Returns a list of invites in the organization.

Returns a list of messages for a given thread.

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

List uploaded certificates for this organization.

Lists organization spend alerts.

List your organization's fine-tuning jobs

Returns a list of API keys in the project.

List certificates for this project.

Lists the project roles assigned to a group within a project.

Lists the groups that have access to a project.

Returns the rate limits per model for a project.

Lists the roles configured for a project.

Returns a list of service accounts in the project.

Lists project spend alerts.

Lists the project roles assigned to a user within a project.

Returns a list of users in the project.

Returns a list of projects.

Lists the roles configured for the organization.

Returns a list of run steps belonging to a run.

Returns a list of runs belonging to a thread.

List skill versions for a skill.

List all skills for the current project.

List items that belong to a ChatKit thread.

List ChatKit threads with optional pagination and user filters.

Lists the organization roles assigned to a user within the organization.

Lists all of the users in the organization.

Returns a list of vector store files.

Returns a list of vector stores.

List recently generated videos for the current project.

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.

Modifies an assistant.

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

Modifies a message.

Modifies a project in the organization.

Modifies a user's role in the project.

Modifies a run.

Modifies a thread.

Modifies a user's role in the organization.

Modifies a vector store.

Pause a fine-tune job.

Transfer an active SIP call to a new destination using the SIP REFER verb.

Decline an incoming SIP call by returning a SIP status code to the caller.

Removes a user from a group.

Revokes a group's access to a project.

Resume a fine-tune job.

Retrieves a batch.

Retrieves a container.

Retrieves a container file.

Retrieves a container file content.

Returns information about a specific file.

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

Retrieves a group.

Retrieves an organization role assigned to a group.

Retrieves a user in a group.

Retrieves an invite.

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

Retrieves organization data retention controls.

Retrieves an organization spend alert.

Retrieves a project.

Retrieves an API key in the project.

Retrieves project data retention controls.

Retrieves a project's group.

Retrieves a project role assigned to a group.

Returns hosted tool permissions for a project.

Returns model permissions for a project.

Retrieves a project role.

Retrieves a service account in the project.

Retrieves a project spend alert.

Retrieves a user in the project.

Retrieves a project role assigned to a user.

Retrieves an organization role.

Retrieves a user by their identifier.

Retrieves an organization role assigned to a user.

Retrieve the parsed contents of a vector store file.

Download the generated video bytes or a derived preview asset. Streams the rendered video content for the specified video job.

Run a grader.

Search a vector store for relevant chunks based on a query and file attributes filter.

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.

Unassigns an organization role from a group within the organization.

Unassigns a project role from a group within a project.

Unassigns a project role from a user within a project.

Unassigns an organization role from a user within the organization.

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 a conversation

Update certain properties of an evaluation.

Updates a group's information.

Updates organization data retention controls.

Updates an organization spend alert.

Updates project data retention controls.

Updates hosted tool permissions for a project.

Updates model permissions for a project.

Updates a project rate limit.

Updates an existing project role.

Updates a service account in the project.

Updates a project spend alert.

Updates an existing organization role.

Update the default version pointer for a skill.

Update attributes on a vector store file.

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.

Create or replace the organization's hard spend limit.

Create or replace a project's hard spend limit.

Upload a certificate to the organization. This does **not** automatically activate the certificate. Organizations can upload up to 50 certificates.

Get audio speeches usage details for the organization.

Get audio transcriptions usage details for the organization.

Get code interpreter sessions usage details for the organization.

Get completions usage details for the organization.

Get costs details for the organization.

Get embeddings usage details for the organization.

Get file search calls usage details for the organization.

Get images usage details for the organization.

Get moderations usage details for the organization.

Get vector stores usage details for the organization.

Get web search calls usage details for the organization.

Validate a grader.