OpenAI::Client

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

Activate certificates for organization Activate certificates at the organization level.

You can atomically and idempotently activate up to 10 certificates at a time.

Activate certificates for project Activate certificates at the project level.

You can atomically and idempotently activate up to 10 certificates at a time.

Add group user Adds a user to a group.

Add project group Grants a group access to a project.

Add upload part Adds a Part to an Upload object. A Part represents a chunk of bytes from the file you are trying to upload.

Each Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB.

It is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you complete the Upload.

Create admin API key Create an organization admin API key

Delete admin API key Delete an organization admin API key

Retrieve admin API key Retrieve a single organization API key

List all organization and project API keys. List organization API keys

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

Assign organization role to group Assigns an organization role to a group within the organization.

Assign project role to group Assigns a project role to a group within a project.

Assign project role to user Assigns a project role to a user within a project.

Assign organization role to user Assigns an organization role to a user within the organization.

Cancel 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 chat session Cancel a ChatKit session

Cancel eval run Cancel an ongoing evaluation run.

Cancel fine-tuning Immediately cancel a fine-tune job.

Cancel a response Cancels a model response with the given ID. Only responses created with the background parameter set to true can be cancelled. Learn more.

Cancel a run Cancels a run that is in_progress.

Cancel upload Cancels the Upload. No Parts may be added after an Upload is cancelled.

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

Compact a response Compact conversation

Complete upload Completes the Upload.

Within the returned Upload object, there is a nested File 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.

Create assistant Create an assistant with a model and instructions.

Create batch Creates and executes a batch from an uploaded file of requests

Create chat completion Starting a new project? We recommend trying Responses to take advantage of the latest OpenAI platform features. Compare Chat Completions with Responses.

Creates a model response for the given chat conversation. Learn more in the text generation, vision, and 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.

Streaming version of create_chat_completion

Create ChatKit session Create a ChatKit session

Create completion Creates a completion for the provided prompt and parameters.

Create container Create Container

Create container file Create a Container File

You can send either a multipart/form-data request with the raw file content, or a JSON request with a file ID.

Create a conversation Create a conversation.

Create items Create items in a conversation with the given ID.

Create embeddings Creates an embedding vector representing the input text.

Create eval 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.

Create eval run 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.

Upload file 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 1 TB.

• The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide for details.
• The Fine-tuning API only supports .jsonl files. The input also has certain required formats for fine-tuning chat or completions models.
• The Batch API only supports .jsonl files up to 200 MB in size. The input also has a specific required format.

Please contact us if you need to increase these storage limits.

Create checkpoint permissions NOTE: Calling this endpoint requires an admin API key.

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

Create fine-tuning job 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

Create group Creates a new group in the organization.

Create image Creates an image given a prompt. Learn more.

Create image edit Creates an edited or extended image given one or more source images and a prompt. This endpoint only supports gpt-image-1 and dall-e-2.

Streaming version of create_image_edit

Streaming version of create_image

Create image variation Creates a variation of a given image. This endpoint only supports dall-e-2.

Create message Create a message.

Create moderation Classifies if text and/or image inputs are potentially harmful. Learn more in the moderation guide.

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

Create project role Creates a custom role for a project.

Create project service account Creates a new service account in the project. This also returns an unredacted API key for the service account.

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

Create call Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.

Create client secret Create a Realtime client secret with an associated session configuration.

Create session 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.

Create transcription session 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.

Create a model response Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.

Streaming version of create_response

Create organization role Creates a custom role for the organization.

Create run Create a run.

Create speech Generates audio from the input text.

Streaming version of create_speech

Create thread Create a thread.

Create thread and run Create a thread and run it in one request.

Create transcription Transcribes audio into the input language.

Streaming version of create_transcription

Create translation Translates audio into English.

Create upload Creates an intermediate Upload object that you can add Parts 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 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.

For guidance on the proper filename extensions for each purpose, please follow the documentation on creating a File.

Create vector store Create a vector store.

Create vector store file Create a vector store file by attaching a File to a vector store.

Create vector store file batch Create a vector store file batch.

Create video Create a video

Remix video Create a video remix

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

Delete assistant Delete an assistant.

Delete certificate Delete a certificate from the organization.

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

Delete 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 a container Delete Container

Delete a container file Delete Container File

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

Delete an item Delete an item from a conversation with the given IDs.

Delete an eval Delete an evaluation.

Delete eval run Delete an eval run.

Delete file Delete a file and remove it from all vector stores.

Delete checkpoint permission NOTE: This endpoint requires an admin API key.

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

Delete group Deletes a group from the organization.

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

Delete message Deletes a message.

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

Delete project API key Deletes an API key from the project.

Delete project role Deletes a custom role from a project.

Delete project service account Deletes a service account from the project.

Delete project user Deletes a user from the project.

Delete a model response Deletes a model response with the given ID.

Delete organization role Deletes a custom role from the organization.

Delete thread Delete a thread.

Delete ChatKit thread Delete a ChatKit thread

Delete user Deletes a user from the organization.

Delete vector store Delete a vector store.

Delete vector store file 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 endpoint.

Delete video Delete a video

Retrieve file content Returns the contents of the specified file.

Retrieve assistant Retrieves an assistant.

Get certificate Get a certificate that has been uploaded to the organization.

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

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

Get chat messages 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.

Retrieve a conversation Get a conversation

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

Get an eval Get an evaluation by ID.

Get an eval run Get an evaluation run by ID.

Get an output item of an eval run Get an evaluation run output item by ID.

Get eval run output items Get a list of output items for an evaluation run.

Get eval runs Get a list of runs for an evaluation.

Retrieve message Retrieve a message.

Get a model response Retrieves a model response with the given ID.

Retrieve run Retrieves a run.

Retrieve run step Retrieves a run step.

Retrieve thread Retrieves a thread.

Retrieve ChatKit thread Retrieve a ChatKit thread

Retrieve vector store Retrieves a vector store.

Retrieve vector store file Retrieves a vector store file.

Retrieve vector store file batch Retrieves a vector store file batch.

Retrieve video Retrieve a video

Get input token counts

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

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

List assistants Returns a list of assistants.

List audit logs List user actions and configuration changes within this organization.

List batch List your organization's batches.

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

List container files List Container files

List containers List Containers

List items List all items for a conversation with the given ID.

List evals List evaluations for a project.

List files Returns a list of files.

List vector store files in a batch Returns a list of vector store files in a batch.

List checkpoint permissions NOTE: This endpoint requires an admin API key.

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

List fine-tuning events Get status updates for a fine-tuning job.

List fine-tuning checkpoints List checkpoints for a fine-tuning job.

List group organization role assignments Lists the organization roles assigned to a group within the organization.

List group users Lists the users assigned to a group.

List groups Lists all groups in the organization.

List input items Returns a list of input items for a given response.

List invites Returns a list of invites in the organization.

List messages Returns a list of messages for a given thread.

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

List organization certificates List uploaded certificates for this organization.

List fine-tuning jobs List your organization's fine-tuning jobs

List project API keys Returns a list of API keys in the project.

List project certificates List certificates for this project.

List project group role assignments Lists the project roles assigned to a group within a project.

List project groups Lists the groups that have access to a project.

List project rate limits Returns the rate limits per model for a project.

List project roles Lists the roles configured for a project.

List project service accounts Returns a list of service accounts in the project.

List project user role assignments Lists the project roles assigned to a user within a project.

List project users Returns a list of users in the project.

List projects Returns a list of projects.

List organization roles Lists the roles configured for the organization.

List run steps Returns a list of run steps belonging to a run.

List runs Returns a list of runs belonging to a thread.

List ChatKit thread items

List ChatKit threads

List user organization role assignments Lists the organization roles assigned to a user within the organization.

List users Lists all of the users in the organization.

List vector store files Returns a list of vector store files.

List vector stores Returns a list of vector stores.

List videos

Modify assistant Modifies an assistant.

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

Modify message Modifies a message.

Modify project Modifies a project in the organization.

Modify project user Modifies a user's role in the project.

Modify run Modifies a run.

Modify thread Modifies a thread.

Modify user Modifies a user's role in the organization.

Modify vector store Modifies a vector store.

Pause fine-tuning Pause a fine-tune job.

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

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

Remove group user Removes a user from a group.

Remove project group Revokes a group's access to a project.

Resume fine-tuning Resume a fine-tune job.

Retrieve batch Retrieves a batch.

Retrieve container Retrieve Container

Retrieve container file Retrieve Container File

Retrieve container file content Retrieve Container File Content

Retrieve file Returns information about a specific file.

Retrieve fine-tuning job Get info about a fine-tuning job.

Learn more about fine-tuning

Retrieve invite Retrieves an invite.

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

Retrieve project Retrieves a project.

Retrieve project API key Retrieves an API key in the project.

Retrieve project service account Retrieves a service account in the project.

Retrieve project user Retrieves a user in the project.

Retrieve user Retrieves a user by their identifier.

Retrieve vector store file content Retrieve the parsed contents of a vector store file.

Retrieve video content Download video content

Run grader Run a grader.

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

Submit tool outputs to run 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.

Unassign organization role from group Unassigns an organization role from a group within the organization.

Unassign project role from group Unassigns a project role from a group within a project.

Unassign project role from user Unassigns a project role from a user within a project.

Unassign organization role from user Unassigns an organization role from a user within the organization.

Update 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 a conversation

Update an eval Update certain properties of an evaluation.

Update group Updates a group's information.

Modify project rate limit Updates a project rate limit.

Update project role Updates an existing project role.

Update organization role Updates an existing organization role.

Update vector store file attributes Update attributes on a vector store file.

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

Organizations can upload up to 50 certificates.

Audio speeches Get audio speeches usage details for the organization.

Audio transcriptions Get audio transcriptions usage details for the organization.

Code interpreter sessions Get code interpreter sessions usage details for the organization.

Completions Get completions usage details for the organization.

Costs Get costs details for the organization.

Embeddings Get embeddings usage details for the organization.

Images Get images usage details for the organization.

Moderations Get moderations usage details for the organization.

Vector stores Get vector stores usage details for the organization.

Validate grader Validate a grader.