OpenAI integration: operations for AI agents
OpenAI connects to Type.com as an integration. This page lists the 376 operations documented for Claude and Codex in Type.com: 172 read, 129 write, 75 destructive.
About OpenAI
Toolkit for OpenAI APIs: manage Assistants, Threads/Messages; upload/list/delete Files; list/retrieve Models (including vision/multimodal); and view fine-tune listings and events.
Categories: Developer Tools & IT
How to connect OpenAI to Type.com
- Access
- Organization connection: one shared account for the workspace.
- MCP
- Selected AI media-generation operations are not available through Type’s MCP server. Other operations remain available through MCP, subject to your connection’s permissions. These MCP restrictions do not apply within Type.
To add the connection, follow the steps in Space connections.
Documented operations
376 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.
376 operations listed.
Assistants
- Read
List assistants (deprecated)
Returns a list of assistants.
GET /assistants - Read
Retrieve assistant (deprecated)
Retrieves an assistant.
GET /assistants/{assistant_id} - Read
Retrieve thread
Retrieves a thread.
GET /threads/{thread_id} - Read
List messages
Returns a list of messages for a given thread.
GET /threads/{thread_id}/messages - Read
Retrieve message
Retrieve a message.
GET /threads/{thread_id}/messages/{message_id} - Read
List runs
Returns a list of runs belonging to a thread.
GET /threads/{thread_id}/runs - Read
Retrieve run
Retrieves a run.
GET /threads/{thread_id}/runs/{run_id} - Read
List run steps
Returns a list of run steps belonging to a run.
GET /threads/{thread_id}/runs/{run_id}/steps - Read
Retrieve run step
Retrieves a run step.
GET /threads/{thread_id}/runs/{run_id}/steps/{step_id} - Write
Create assistant (deprecated)
Create an assistant with a model and instructions.
POST /assistants - Write
Modify assistant (deprecated)
Modifies an assistant.
POST /assistants/{assistant_id} - Write
Create thread
Create a thread.
POST /threads - Write
Create thread and run
Create a thread and run it in one request.
POST /threads/runs - Write
Modify thread
Modifies a thread.
POST /threads/{thread_id} - Write
Create message
Create a message.
POST /threads/{thread_id}/messages - Write
Modify message
Modifies a message.
POST /threads/{thread_id}/messages/{message_id} - Write
Create run
Create a run.
POST /threads/{thread_id}/runs - Write
Modify run
Modifies a run.
POST /threads/{thread_id}/runs/{run_id} - Write
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.
POST /threads/{thread_id}/runs/{run_id}/submit_tool_outputs - Destructive
Delete assistant (deprecated)
Delete an assistant.
DELETE /assistants/{assistant_id} - Destructive
Delete thread
Delete a thread.
DELETE /threads/{thread_id} - Destructive
Delete message
Deletes a message.
DELETE /threads/{thread_id}/messages/{message_id} - Destructive
Cancel a run
Cancels a run that is `in_progress`.
POST /threads/{thread_id}/runs/{run_id}/cancel
Audio
- Read
List voice consents
Returns a list of voice consent recordings.
GET /audio/voice_consents - Read
Retrieve voice consent
Retrieves a voice consent recording.
GET /audio/voice_consents/{consent_id} - Write
Create speech
Generates audio from the input text. Returns the audio file content, or a stream of audio events. The `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, `gpt-4o-mini-tts-2025-03-20`, and `gpt-4o-mini-tts-2025-12-15` models are deprecated and scheduled to shut down on January 6, 2027. These examples use the existing Speech API; for new integrations, migrate to `gpt-realtime-2.1-mini` through the [Realtime API](https://developers.openai.com/api/docs/guides/realtime). See the [deprecation schedule](https://developers.openai.com/api/docs/deprecations) for migration details.
POST /audio/speech - Write
Create transcription
Transcribes audio into the input language. Returns a transcription object in `json`, `diarized_json`, or `verbose_json` format, plain text in `text`, `srt`, or `vtt` format, or a stream of transcript events. Supported formats depend on the model.
POST /audio/transcriptions - Write
Create translation (deprecated)
Translates audio into English. This endpoint supports only `whisper-1`. The endpoint and model are deprecated and scheduled to shut down on February 26, 2027. Migrate to `/v1/realtime/translations`, which requires a separate integration. See the [deprecation schedule](https://developers.openai.com/api/docs/deprecations) for details.
POST /audio/translations - Write
Create voice consent
Upload a voice consent recording.
POST /audio/voice_consents - Write
Update voice consent
Updates a voice consent recording (metadata only).
POST /audio/voice_consents/{consent_id} - Write
Create voice
Creates a voice from a text prompt or from a consent recording and an audio sample. For prompt-based creation, send `type: "prompt"` with a `name` and `prompt` as JSON or multipart form data. For creation from an audio sample, send `type: "audio_sample"` with a `name`, `audio_sample`, and `consent` recording ID as multipart form data. The type defaults to `audio_sample` when omitted. Returns the saved voice's metadata. Voices created from text prompts are supported only in Live, not in Realtime or the speech endpoint. The response does not include preview audio.
POST /audio/voices - Destructive
Delete voice consent
Deletes a voice consent recording.
DELETE /audio/voice_consents/{consent_id} - Destructive
Delete voice
Deletes a voice created from a text prompt or an audio sample. Requires voice write permission and access to the voice's project. Access to voices created from recordings is limited to eligible customers. See the [custom voices guide](https://developers.openai.com/api/docs/guides/custom-voices). Deleting a voice does not delete its consent recording. Deleting an already deleted voice returns a 404 error.
DELETE /audio/voices/{voice_id}
Batch
- Read
List batches
List your organization's batches.
GET /batches - Read
Retrieve batch
Retrieves a batch.
GET /batches/{batch_id} - Write
Create batch
Creates and executes a batch from an uploaded file of requests
POST /batches - Destructive
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.
POST /batches/{batch_id}/cancel
Chat
- Read
List Chat Completions
List stored Chat Completions. Only Chat Completions that have been stored with the `store` parameter set to `true` will be returned.
GET /chat/completions - Read
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/completions/{completion_id} - Read
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.
GET /chat/completions/{completion_id}/messages - Write
Create chat completion
**Starting a new project?** We recommend trying [Responses](https://developers.openai.com/api/reference/resources/responses) to take advantage of the latest OpenAI platform features. Compare [Chat Completions with Responses](https://developers.openai.com/api/docs/guides/migrate-to-responses?api-mode=responses). --- Creates a model response for the given chat conversation. Learn more in the [text generation](https://developers.openai.com/api/docs/guides/text), [vision](https://developers.openai.com/api/docs/guides/images-vision), and [audio](https://developers.openai.com/api/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](https://developers.openai.com/api/docs/guides/reasoning). Returns a chat completion object, or a streamed sequence of chat completion chunk objects if the request is streamed.
POST /chat/completions - Write
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.
POST /chat/completions/{completion_id} - Destructive
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 /chat/completions/{completion_id}
Completions
- Write
Create completion
Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed.
POST /completions
Containers
- Read
List containers
List Containers
GET /containers - Read
Retrieve container
Retrieve Container
GET /containers/{container_id} - Read
List container files
List Container files
GET /containers/{container_id}/files - Read
Retrieve container file
Retrieve Container File
GET /containers/{container_id}/files/{file_id} - Read
Retrieve container file content
Retrieve Container File Content
GET /containers/{container_id}/files/{file_id}/content - Write
Create container
Create Container
POST /containers - Write
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.
POST /containers/{container_id}/files - Destructive
Delete a container
Delete Container
DELETE /containers/{container_id} - Destructive
Delete a container file
Delete Container File
DELETE /containers/{container_id}/files/{file_id}
Conversations
- Read
List items
List all items for a conversation with the given ID.
GET /conversations/{conversation_id}/items - Read
Retrieve an item
Get a single item from a conversation with the given IDs.
GET /conversations/{conversation_id}/items/{item_id} - Read
Retrieve a conversation
Get a conversation
GET /conversations/{conversation_id} - Write
Create items
Create items in a conversation with the given ID.
POST /conversations/{conversation_id}/items - Write
Create a conversation
Create a conversation.
POST /conversations - Write
Update a conversation
Update a conversation
POST /conversations/{conversation_id} - Destructive
Delete an item
Delete an item from a conversation with the given IDs.
DELETE /conversations/{conversation_id}/items/{item_id} - Destructive
Delete a conversation
Delete a conversation. Items in the conversation will not be deleted.
DELETE /conversations/{conversation_id}
Embeddings
- Write
Create embeddings
Creates an embedding vector representing the input text.
POST /embeddings
Evals
- Read
List evals
List evaluations for a project.
GET /evals - Read
Get an eval
Get an evaluation by ID.
GET /evals/{eval_id} - Read
Get eval runs
Get a list of runs for an evaluation.
GET /evals/{eval_id}/runs - Read
Get an eval run
Get an evaluation run by ID.
GET /evals/{eval_id}/runs/{run_id} - Read
Get eval run output items
Get a list of output items for an evaluation run.
GET /evals/{eval_id}/runs/{run_id}/output_items - Read
Get an output item of an eval run
Get an evaluation run output item by ID.
GET /evals/{eval_id}/runs/{run_id}/output_items/{output_item_id} - Write
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](https://developers.openai.com/api/docs/guides/evals).
POST /evals - Write
Update an eval
Update certain properties of an evaluation.
POST /evals/{eval_id} - Write
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.
POST /evals/{eval_id}/runs - Destructive
Delete an eval
Delete an evaluation.
DELETE /evals/{eval_id} - Destructive
Delete eval run
Delete an eval run.
DELETE /evals/{eval_id}/runs/{run_id} - Destructive
Cancel eval run
Cancel an ongoing evaluation run.
POST /evals/{eval_id}/runs/{run_id}/cancel
Files
- Read
List files
Returns a list of files.
GET /files - Read
Retrieve file
Returns information about a specific file.
GET /files/{file_id} - Read
Retrieve file content
Returns a response containing the contents of the specified file.
GET /files/{file_id}/content - Write
Upload file
Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and each project can store up to 2.5 TB of files in total. There is no organization-wide storage limit. Uploads to this endpoint are rate-limited to 1,000 requests per minute per authenticated user. - The Assistants API supports files up to 2 million tokens and of specific file types. See the [Assistants Tools guide](https://developers.openai.com/api/docs/guides/tools) for details. - The Fine-tuning API only supports `.jsonl` files. The input also has certain required formats for fine-tuning [chat](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) or [completions](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) models. - The Batch API only supports `.jsonl` files up to 200 MB in size. The input also has a specific required [format](https://developers.openai.com/api/docs/guides/batch#1-prepare-your-batch-file). - For Retrieval or `file_search` ingestion, upload files here first. If you need to attach multiple uploaded files to the same vector store, use [`/vector_stores/{vector_store_id}/file_batches`](https://developers.openai.com/api/reference/resources/vector_stores/subresources/file_batches/methods/create) instead of attaching them one by one. Vector store attachment has separate limits from file upload, including 2,000 attached files per minute per organization. Please [contact us](https://help.openai.com/) if you need to increase these storage limits.
POST /files - Destructive
Delete file
Delete a file and remove it from all vector stores.
DELETE /files/{file_id}
Fine tuning
- Read
Validate grader
Validate a grader.
POST /fine_tuning/alpha/graders/validate - Read
List checkpoint permissions
**NOTE:** This endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys). Organization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint.
GET /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions - Read
List fine-tuning jobs
List your organization's fine-tuning jobs
GET /fine_tuning/jobs - Read
Retrieve fine-tuning job
Get info about a fine-tuning job. [Learn more about fine-tuning](https://developers.openai.com/api/docs/guides/model-optimization)
GET /fine_tuning/jobs/{fine_tuning_job_id} - Read
List fine-tuning checkpoints
List checkpoints for a fine-tuning job.
GET /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints - Read
List fine-tuning events
Get status updates for a fine-tuning job.
GET /fine_tuning/jobs/{fine_tuning_job_id}/events - Write
Run grader
Run a grader.
POST /fine_tuning/alpha/graders/run - Write
Create checkpoint permissions
**NOTE:** Calling this endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys). This enables organization owners to share fine-tuned models with other projects in their organization.
POST /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions - Write
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](https://developers.openai.com/api/docs/guides/model-optimization)
POST /fine_tuning/jobs - Write
Pause fine-tuning
Pause a fine-tune job.
POST /fine_tuning/jobs/{fine_tuning_job_id}/pause - Write
Resume fine-tuning
Resume a fine-tune job.
POST /fine_tuning/jobs/{fine_tuning_job_id}/resume - Destructive
Delete checkpoint permission
**NOTE:** This endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys). Organization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint.
DELETE /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id} - Destructive
Cancel fine-tuning
Immediately cancel a fine-tune job.
POST /fine_tuning/jobs/{fine_tuning_job_id}/cancel
Images
- Write
Create image edit
Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models.
POST /images/edits - Write
Create image
Creates an image given a prompt using a GPT Image model. [Learn more](https://developers.openai.com/api/docs/guides/images-vision).
POST /images/generations - Write
Create image variation (deprecated)
This endpoint is retired and no longer available. Use the image edits endpoint with a GPT Image model and a prompt to create a variation of an image. The request and response schemas below describe the legacy contract.
POST /images/variations
Live
- Read
Download recording
Get Live session content
GET /live/sessions/{session_id}/content - Write
Create session
Create a Live WebRTC session or place an outbound SIP call. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) for session configuration and [Telephony and SIP](https://developers.openai.com/api/docs/guides/voice-sip?api=live#place-an-outbound-call) for trunk setup and call monitoring. Set transport.type to `webrtc` and supply an SDP offer, or set it to `sip` and supply an E.164 destination and trunk credentials. Outbound SIP calling must be enabled for your organization. Ringing is limited to 3 minutes and connected calls to 2 hours; these limits are not configurable in the request. Returns `201 Created` after session initialization. WebRTC responses include an SDP answer. SIP responses do not wait for the callee to answer. Attach a sideband connection using session.id to monitor SIP call progress. Each SIP request creates a new call. If a request times out or the connection fails, retry with caution: the original request may have succeeded, and a retry can place another call.
POST /live/sessions - Write
Accept call
Accept an incoming SIP call. Supply session with type live, the model, and startup configuration. Before accepting calls, follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to write frontend conversation instructions and a separate backend prompt. SIP media format is negotiated; omit audio.format.
POST /live/sessions/{session_id}/accept - Write
Fork session
Fork a stored Live session onto a new WebRTC connection.
POST /live/sessions/{session_id}/fork - Write
Hang up session
End a SIP call identified by session_id.
POST /live/sessions/{session_id}/hangup - Write
Transfer call
Transfer a SIP call to another destination. Supply a nonblank target_uri for the SIP Refer-To header.
POST /live/sessions/{session_id}/refer - Write
Reject call
Reject an incoming SIP call. Send a required SIP rejection status_code between 300 and 699.
POST /live/sessions/{session_id}/reject
Models
- Read
List models
Lists the currently available models, and provides basic information about each one such as the owner and availability.
GET /models - Read
Retrieve model
Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
GET /models/{model} - Destructive
Delete a fine-tuned model
Delete a fine-tuned model. You must have the Owner role in your organization to delete a model.
DELETE /models/{model}
Moderations
- Write
Create moderation
Classifies if text and/or image inputs are potentially harmful. Learn more in the [moderation guide](https://developers.openai.com/api/docs/guides/moderation).
POST /moderations
Organization
- Read
List all organization and project API keys.
List organization API keys
GET /organization/admin_api_keys - Read
Retrieve admin API key
Retrieve a single organization API key
GET /organization/admin_api_keys/{key_id} - Read
Decisions
Get Decisions API usage details for the organization.
GET /organization/usage/decisions - Read
List external storage configurations
List the organization's customer-managed external storage configurations.
GET /organization/external_storage - Read
Get an external storage configuration
Get one customer-managed external storage configuration.
GET /organization/external_storage/{external_storage_id} - Read
Validate an external storage configuration
Validate one customer-managed external storage configuration.
POST /organization/external_storage/{external_storage_id}/validate - Read
Get organization spend limit
Get the organization's hard spend limit.
GET /organization/spend_limit - Read
Get project spend limit
Get a project's hard spend limit.
GET /organization/projects/{project_id}/spend_limit - Write
Create admin API key
Create an organization admin API key
POST /organization/admin_api_keys - Write
Create an external storage configuration
Register one customer-managed external storage configuration.
POST /organization/external_storage - Write
Create an API key for a service account
Creates an API key for a service account in the project.
POST /organization/projects/{project_id}/service_accounts/{service_account_id}/api_keys - Destructive
Delete admin API key
Delete an organization admin API key
DELETE /organization/admin_api_keys/{key_id} - Destructive
Delete an external storage configuration
Disconnect a customer-managed external storage configuration. Removing the project's last configuration restores organization-default retention if customer-managed retention was active. Repeating a deletion also completes any interrupted retention update. Cloud storage is unchanged.
DELETE /organization/external_storage/{external_storage_id} - Destructive
Update organization spend limit
Create or replace the organization's hard spend limit.
POST /organization/spend_limit - Destructive
Delete organization spend limit
Delete the organization's hard spend limit.
DELETE /organization/spend_limit - Destructive
Delete project spend limit
Delete a project's hard spend limit.
DELETE /organization/projects/{project_id}/spend_limit - Destructive
Update project spend limit
Create or replace a project's hard spend limit.
POST /organization/projects/{project_id}/spend_limit
Audit Logs
- Read
List audit logs
List user actions and configuration changes within this organization.
GET /organization/audit_logs
Certificates
- Read
List organization certificates
List uploaded certificates for this organization.
GET /organization/certificates - Read
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 /organization/certificates/{certificate_id} - Read
List project certificates
List certificates for this project.
GET /organization/projects/{project_id}/certificates - Write
Upload certificate
Upload a certificate to the organization. This does **not** automatically activate the certificate. Organizations can upload up to 50 certificates.
POST /organization/certificates - Write
Activate certificates for organization
Activate certificates at the organization level. You can atomically and idempotently activate up to 10 certificates at a time.
POST /organization/certificates/activate - Write
Deactivate certificates for organization
Deactivate certificates at the organization level. You can atomically and idempotently deactivate up to 10 certificates at a time.
POST /organization/certificates/deactivate - Write
Modify certificate
Modify a certificate. Note that only the name can be modified.
POST /organization/certificates/{certificate_id} - Write
Activate certificates for project
Activate certificates at the project level. You can atomically and idempotently activate up to 10 certificates at a time.
POST /organization/projects/{project_id}/certificates/activate - Write
Deactivate certificates for project
Deactivate certificates at the project level. You can atomically and idempotently deactivate up to 10 certificates at a time.
POST /organization/projects/{project_id}/certificates/deactivate - Destructive
Delete certificate
Delete a certificate from the organization. The certificate must be inactive for the organization and all projects.
DELETE /organization/certificates/{certificate_id}
Usage
- Read
Costs
Get costs details for the organization.
GET /organization/costs - Read
Audio speeches
Get audio speeches usage details for the organization.
GET /organization/usage/audio_speeches - Read
Audio transcriptions
Get audio transcriptions usage details for the organization.
GET /organization/usage/audio_transcriptions - Read
Code interpreter sessions
Get code interpreter sessions usage details for the organization.
GET /organization/usage/code_interpreter_sessions - Read
Completions
Get completions usage details for the organization.
GET /organization/usage/completions - Read
Embeddings
Get embeddings usage details for the organization.
GET /organization/usage/embeddings - Read
File search calls
Get file search calls usage details for the organization.
GET /organization/usage/file_search_calls - Read
Images
Get images usage details for the organization.
GET /organization/usage/images - Read
Moderations
Get moderations usage details for the organization.
GET /organization/usage/moderations - Read
Vector stores
Get vector stores usage details for the organization.
GET /organization/usage/vector_stores - Read
Web search calls
Get web search calls usage details for the organization.
GET /organization/usage/web_search_calls
Data retention
- Read
Retrieve organization data retention
Retrieves organization data retention controls.
GET /organization/data_retention - Read
Retrieve project data retention
Retrieves project data retention controls.
GET /organization/projects/{project_id}/data_retention - Write
Update organization data retention
Updates organization data retention controls.
POST /organization/data_retention - Write
Update project data retention
Updates project data retention controls.
POST /organization/projects/{project_id}/data_retention
Groups
- Read
List groups
Lists all groups in the organization.
GET /organization/groups - Read
Retrieve group
Retrieves a group.
GET /organization/groups/{group_id} - Write
Create group
Creates a new group in the organization.
POST /organization/groups - Write
Update group
Updates a group's information.
POST /organization/groups/{group_id} - Destructive
Delete group
Deletes a group from the organization.
DELETE /organization/groups/{group_id}
Group organization role assignments
- Read
List group organization role assignments
Lists the organization roles assigned to a group within the organization.
GET /organization/groups/{group_id}/roles - Read
Retrieve group organization role
Retrieves an organization role assigned to a group.
GET /organization/groups/{group_id}/roles/{role_id} - Write
Assign organization role to group
Assigns an organization role to a group within the organization.
POST /organization/groups/{group_id}/roles - Destructive
Unassign organization role from group
Unassigns an organization role from a group within the organization.
DELETE /organization/groups/{group_id}/roles/{role_id}
Group users
- Read
List group users
Lists the users assigned to a group.
GET /organization/groups/{group_id}/users - Read
Retrieve group user
Retrieves a user in a group.
GET /organization/groups/{group_id}/users/{user_id} - Write
Add group user
Adds a user to a group.
POST /organization/groups/{group_id}/users - Destructive
Remove group user
Removes a user from a group.
DELETE /organization/groups/{group_id}/users/{user_id}
Invites
- Read
List invites
Returns a list of invites in the organization.
GET /organization/invites - Read
Retrieve invite
Retrieves an invite.
GET /organization/invites/{invite_id} - Write
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.
POST /organization/invites - Destructive
Delete invite
Delete an invite. If the invite has already been accepted, it cannot be deleted.
DELETE /organization/invites/{invite_id}
Projects
- Read
List projects
Returns a list of projects.
GET /organization/projects - Read
Retrieve project
Retrieves a project.
GET /organization/projects/{project_id} - Read
List project API keys
Returns a list of API keys in the project.
GET /organization/projects/{project_id}/api_keys - Read
Retrieve project API key
Retrieves an API key in the project.
GET /organization/projects/{project_id}/api_keys/{api_key_id} - Read
Retrieve project model permissions
Returns model permissions for a project.
GET /organization/projects/{project_id}/model_permissions - Read
List project rate limits
Returns the rate limits per model for a project.
GET /organization/projects/{project_id}/rate_limits - Read
List project service accounts
Returns a list of service accounts in the project.
GET /organization/projects/{project_id}/service_accounts - Read
Retrieve project service account
Retrieves a service account in the project.
GET /organization/projects/{project_id}/service_accounts/{service_account_id} - Read
List project users
Returns a list of users in the project.
GET /organization/projects/{project_id}/users - Read
Retrieve project user
Retrieves a user in the project.
GET /organization/projects/{project_id}/users/{user_id} - Write
Create project
Create a new project in the organization. Projects can be created and archived, but cannot be deleted.
POST /organization/projects - Write
Modify project
Modifies a project in the organization.
POST /organization/projects/{project_id} - Write
Modify project model permissions
Updates model permissions for a project.
POST /organization/projects/{project_id}/model_permissions - Write
Modify project rate limit
Updates a project rate limit.
POST /organization/projects/{project_id}/rate_limits/{rate_limit_id} - Write
Create project service account
Creates a new service account in the project. By default, this also returns an unredacted API key for the service account.
POST /organization/projects/{project_id}/service_accounts - Write
Update project service account
Updates a service account in the project.
POST /organization/projects/{project_id}/service_accounts/{service_account_id} - Write
Create project user
Adds a user to the project. Users must already be members of the organization to be added to a project.
POST /organization/projects/{project_id}/users - Write
Modify project user
Modifies a user's role in the project.
POST /organization/projects/{project_id}/users/{user_id} - Destructive
Delete project API key
Deletes an API key from the project, including keys owned by service accounts. Requires permission to write project API keys. Deleting a service-account key does not delete the service account or its other keys. Returns confirmation of the key deletion.
DELETE /organization/projects/{project_id}/api_keys/{api_key_id} - Destructive
Update project API key
Updates the scopes and/or expiration of an existing API key in the project, including a service-account-owned key. Requires permission to write project API keys. Provide at least one of `scopes` or `expires_in_seconds`. Omitted fields stay unchanged; neither field accepts `null`. Both changes are saved together. `scopes` replaces the key's scope restrictions using the same scope identifiers as the dashboard. An empty array means All permissions, subject to the owner's effective access; it does not mean no access. Use `["api.all.read"]` for read-only access or specific scopes such as `["api.files.read"]` for restricted access. This does not change user or service-account roles or grant admin permissions. Scope changes follow the same authentication-cache propagation as dashboard edits. Provide `expires_in_seconds` to set the expiration relative to this request. The value must satisfy the organization's and project's expiry policies. Expired keys cannot be updated. Retrying resets the expiration relative to the new request. The response contains only the redacted key, not its secret.
POST /organization/projects/{project_id}/api_keys/{api_key_id} - Destructive
Archive project
Archives a project in the organization. Archived projects cannot be used or updated.
POST /organization/projects/{project_id}/archive - Destructive
Delete project model permissions
Deletes model permissions for a project.
DELETE /organization/projects/{project_id}/model_permissions - Destructive
Delete project service account
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).
DELETE /organization/projects/{project_id}/service_accounts/{service_account_id} - Destructive
Delete project user
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).
DELETE /organization/projects/{project_id}/users/{user_id}
Project groups
- Read
List project groups
Lists the groups that have access to a project.
GET /organization/projects/{project_id}/groups - Read
Retrieve project group
Retrieves a project's group.
GET /organization/projects/{project_id}/groups/{group_id} - Write
Add project group
Grants a group access to a project.
POST /organization/projects/{project_id}/groups - Destructive
Remove project group
Revokes a group's access to a project.
DELETE /organization/projects/{project_id}/groups/{group_id}
Hosted tools
- Read
Retrieve project hosted tool permissions
Returns hosted tool permissions for a project.
GET /organization/projects/{project_id}/hosted_tool_permissions - Write
Modify project hosted tool permissions
Updates hosted tool permissions for a project.
POST /organization/projects/{project_id}/hosted_tool_permissions
Spend alerts
- Read
List project spend alerts
Lists project spend alerts.
GET /organization/projects/{project_id}/spend_alerts - Read
Retrieve project spend alert
Retrieves a project spend alert.
GET /organization/projects/{project_id}/spend_alerts/{alert_id} - Read
List organization spend alerts
Lists organization spend alerts.
GET /organization/spend_alerts - Read
Retrieve organization spend alert
Retrieves an organization spend alert.
GET /organization/spend_alerts/{alert_id} - Write
Create project spend alert
Creates a project spend alert.
POST /organization/projects/{project_id}/spend_alerts - Write
Update project spend alert
Updates a project spend alert.
POST /organization/projects/{project_id}/spend_alerts/{alert_id} - Write
Create organization spend alert
Creates an organization spend alert.
POST /organization/spend_alerts - Write
Update organization spend alert
Updates an organization spend alert.
POST /organization/spend_alerts/{alert_id} - Destructive
Delete project spend alert
Deletes a project spend alert.
DELETE /organization/projects/{project_id}/spend_alerts/{alert_id} - Destructive
Delete organization spend alert
Deletes an organization spend alert.
DELETE /organization/spend_alerts/{alert_id}
Roles
- Read
List organization roles
Lists the roles configured for the organization.
GET /organization/roles - Read
Retrieve organization role
Retrieves an organization role.
GET /organization/roles/{role_id} - Read
List project roles
Lists the roles configured for a project.
GET /projects/{project_id}/roles - Read
Retrieve project role
Retrieves a project role.
GET /projects/{project_id}/roles/{role_id} - Write
Create organization role
Creates a custom role for the organization.
POST /organization/roles - Write
Update organization role
Updates an existing organization role.
POST /organization/roles/{role_id} - Write
Create project role
Creates a custom role for a project.
POST /projects/{project_id}/roles - Write
Update project role
Updates an existing project role.
POST /projects/{project_id}/roles/{role_id} - Destructive
Delete organization role
Deletes a custom role from the organization.
DELETE /organization/roles/{role_id} - Destructive
Delete project role
Deletes a custom role from a project.
DELETE /projects/{project_id}/roles/{role_id}
Users
- Read
List users
Lists all of the users in the organization.
GET /organization/users - Read
Retrieve user
Retrieves a user by their identifier.
GET /organization/users/{user_id} - Write
Modify user
Modifies a user's role in the organization.
POST /organization/users/{user_id} - Destructive
Delete user
Deletes a user from the organization.
DELETE /organization/users/{user_id}
User organization role assignments
- Read
List user organization role assignments
Lists the organization roles assigned to a user within the organization.
GET /organization/users/{user_id}/roles - Read
Retrieve user organization role
Retrieves an organization role assigned to a user.
GET /organization/users/{user_id}/roles/{role_id} - Write
Assign organization role to user
Assigns an organization role to a user within the organization.
POST /organization/users/{user_id}/roles - Destructive
Unassign organization role from user
Unassigns an organization role from a user within the organization.
DELETE /organization/users/{user_id}/roles/{role_id}
Project group role assignments
- Read
List project group role assignments
Lists the project roles assigned to a group within a project.
GET /projects/{project_id}/groups/{group_id}/roles - Read
Retrieve project group role
Retrieves a project role assigned to a group.
GET /projects/{project_id}/groups/{group_id}/roles/{role_id} - Write
Assign project role to group
Assigns a project role to a group within a project.
POST /projects/{project_id}/groups/{group_id}/roles - Destructive
Unassign project role from group
Unassigns a project role from a group within a project.
DELETE /projects/{project_id}/groups/{group_id}/roles/{role_id}
Project user role assignments
- Read
List project user role assignments
Lists the project roles assigned to a user within a project.
GET /projects/{project_id}/users/{user_id}/roles - Read
Retrieve project user role
Retrieves a project role assigned to a user.
GET /projects/{project_id}/users/{user_id}/roles/{role_id} - Write
Assign project role to user
Assigns a project role to a user within a project.
POST /projects/{project_id}/users/{user_id}/roles - Destructive
Unassign project role from user
Unassigns a project role from a user within a project.
DELETE /projects/{project_id}/users/{user_id}/roles/{role_id}
Realtime
- Write
Create call
Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.
POST /realtime/calls - Write
Accept call
Accept an incoming SIP call and configure the realtime session that will handle it.
POST /realtime/calls/{call_id}/accept - Write
Hang up call
End an active Realtime API call, whether it was initiated over SIP or WebRTC.
POST /realtime/calls/{call_id}/hangup - Write
Refer call
Transfer an active SIP call to a new destination using the SIP REFER verb.
POST /realtime/calls/{call_id}/refer - Write
Reject call
Decline an incoming SIP call by returning a SIP status code to the caller.
POST /realtime/calls/{call_id}/reject - Write
Create client secret
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](https://developers.openai.com/api/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`.
POST /realtime/client_secrets - Write
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. Returns the created Realtime session object, plus an ephemeral key.
POST /realtime/sessions - Write
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. Returns the created Realtime transcription session object, plus an ephemeral key.
POST /realtime/transcription_sessions - Write
Create translation client secret
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`.
POST /realtime/translations/client_secrets
Responses
- Read
Get a model response
Retrieves a model response with the given ID.
GET /responses/{response_id} - Read
List input items
Returns a list of input items for a given response.
GET /responses/{response_id}/input_items - Read
Get input token counts
Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.
POST /responses/input_tokens - Read
Get a model response
Retrieves a model response with the given ID.
GET /responses/{response_id}?beta=true - Read
List input items
Returns a list of input items for a given response.
GET /responses/{response_id}/input_items?beta=true - Read
Get input token counts
Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.
POST /responses/input_tokens?beta=true - Write
Create a model response
Creates a model response. Provide [text](https://developers.openai.com/api/docs/guides/text) or [image](https://developers.openai.com/api/docs/guides/images-vision) inputs to generate [text](https://developers.openai.com/api/docs/guides/text) or [JSON](https://developers.openai.com/api/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](https://developers.openai.com/api/docs/guides/function-calling) or use built-in [tools](https://developers.openai.com/api/docs/guides/tools) like [web search](https://developers.openai.com/api/docs/guides/tools-web-search) or [file search](https://developers.openai.com/api/docs/guides/tools-file-search) to use your own data as input for the model's response.
POST /responses - Write
Compact conversation
Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](https://developers.openai.com/api/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://developers.openai.com/api/docs/guides/conversation-state#compaction-advanced).
POST /responses/compact - Write
Create a model response
Creates a model response. Provide [text](https://developers.openai.com/api/docs/guides/text) or [image](https://developers.openai.com/api/docs/guides/images-vision) inputs to generate [text](https://developers.openai.com/api/docs/guides/text) or [JSON](https://developers.openai.com/api/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](https://developers.openai.com/api/docs/guides/function-calling) or use built-in [tools](https://developers.openai.com/api/docs/guides/tools) like [web search](https://developers.openai.com/api/docs/guides/tools-web-search) or [file search](https://developers.openai.com/api/docs/guides/tools-file-search) to use your own data as input for the model's response.
POST /responses?beta=true - Write
Compact conversation
Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](https://developers.openai.com/api/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://developers.openai.com/api/docs/guides/conversation-state#compaction-advanced).
POST /responses/compact?beta=true - Destructive
Delete a model response
Deletes a model response with the given ID.
DELETE /responses/{response_id} - Destructive
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](https://developers.openai.com/api/docs/guides/background).
POST /responses/{response_id}/cancel - Destructive
Delete a model response
Deletes a model response with the given ID.
DELETE /responses/{response_id}?beta=true - Destructive
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](https://developers.openai.com/api/docs/guides/background).
POST /responses/{response_id}/cancel?beta=true
Uploads
- Write
Create upload
Creates an intermediate [Upload](https://developers.openai.com/api/reference/resources/uploads) object that you can add [Parts](https://developers.openai.com/api/reference/resources/uploads/subresources/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](https://developers.openai.com/api/reference/resources/files) 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](https://developers.openai.com/api/docs/guides/tools-file-search#supported-files). For guidance on the proper filename extensions for each purpose, please follow the documentation on [creating a File](https://developers.openai.com/api/reference/resources/files/methods/create). Returns the Upload object with status `pending`.
POST /uploads - Write
Complete upload
Completes the [Upload](https://developers.openai.com/api/reference/resources/uploads). Within the returned Upload object, there is a nested [File](https://developers.openai.com/api/reference/resources/files) 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.
POST /uploads/{upload_id}/complete - Write
Add upload part
Adds a [Part](https://developers.openai.com/api/reference/resources/uploads/subresources/parts) to an [Upload](https://developers.openai.com/api/reference/resources/uploads) 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](https://developers.openai.com/api/reference/resources/uploads/methods/complete).
POST /uploads/{upload_id}/parts - Destructive
Cancel upload
Cancels the Upload. No Parts may be added after an Upload is cancelled. Returns the Upload object with status `cancelled`.
POST /uploads/{upload_id}/cancel
Vector stores
- Read
List vector stores
Returns a list of vector stores.
GET /vector_stores - Read
Retrieve vector store
Retrieves a vector store.
GET /vector_stores/{vector_store_id} - Read
Retrieve vector store file batch
Retrieves a vector store file batch.
GET /vector_stores/{vector_store_id}/file_batches/{batch_id} - Read
List vector store files in a batch
Returns a list of vector store files in a batch.
GET /vector_stores/{vector_store_id}/file_batches/{batch_id}/files - Read
List vector store files
Returns a list of vector store files.
GET /vector_stores/{vector_store_id}/files - Read
Retrieve vector store file
Retrieves a vector store file.
GET /vector_stores/{vector_store_id}/files/{file_id} - Read
Retrieve vector store file content
Retrieve the parsed contents of a vector store file.
GET /vector_stores/{vector_store_id}/files/{file_id}/content - Read
Search vector store
Search a vector store for relevant chunks based on a query and file attributes filter.
POST /vector_stores/{vector_store_id}/search - Write
Create vector store
Create a vector store.
POST /vector_stores - Write
Modify vector store
Modifies a vector store.
POST /vector_stores/{vector_store_id} - Write
Create vector store file batch
Create a vector store file batch.
POST /vector_stores/{vector_store_id}/file_batches - Write
Create vector store file
Create a vector store file by attaching a [File](https://developers.openai.com/api/reference/resources/files) to a [vector store](https://developers.openai.com/api/reference/resources/vector_stores).
POST /vector_stores/{vector_store_id}/files - Write
Update vector store file attributes
Update attributes on a vector store file.
POST /vector_stores/{vector_store_id}/files/{file_id} - Destructive
Delete vector store
Delete a vector store.
DELETE /vector_stores/{vector_store_id} - Destructive
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.
POST /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel - Destructive
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](https://developers.openai.com/api/reference/resources/files/methods/delete) endpoint.
DELETE /vector_stores/{vector_store_id}/files/{file_id}
Safety
- Read
Get safety case
Get a safety case by ID.
GET /safety/cases/{id} - Read
Get project safety alert
Get a safety alert belonging to the authenticated API project.
GET /safety/alerts/{id}
Other
- Read
List the external key configs registered on the user's organization
List the external key configs registered on the user's organization
GET /organization/external_keys - Read
Retrieve an external key registration
Retrieve a stored external key registration for the user's organization.
GET /organization/external_keys/{external_key_id} - Read
Validate an external key config for the user's organization
Validate an external key config for the user's organization
POST /organization/external_keys/{external_key_id}/validate - Write
Add an external key config for an organization
Add an external key config for an organization
POST /organization/external_keys - Destructive
Delete an external key config for the user's organization
Delete an external key config for the user's organization
DELETE /organization/external_keys/{external_key_id}
Content provenance checks
- Read
Create content provenance check
Check whether an image or audio file contains known OpenAI provenance signals. [Learn more about content provenance](https://developers.openai.com/api/docs/guides/content-provenance). If `not_detected`, it means the tool did not find supported signals in the uploaded file. The content could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, it comes from a legacy generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company's model, which the tool currently does not detect.
POST /content_provenance_checks
Videos
- Read
List videos (deprecated)
List recently generated videos for the current project.
GET /videos - Read
Retrieve a character (deprecated)
Fetch a character.
GET /videos/characters/{character_id} - Read
Retrieve a video (deprecated)
Fetch the latest metadata for a generated video.
GET /videos/{video_id} - Read
Download video content (deprecated)
Download the generated video bytes or a derived preview asset. Streams the rendered video content for the specified video job.
GET /videos/{video_id}/content - Write
Create a video (deprecated)
Create a new video generation job from a prompt and optional reference assets.
POST /videos - Write
Create a character (deprecated)
Create a character from an uploaded video.
POST /videos/characters - Write
Create a video edit (deprecated)
Create a new video generation job by editing a source video or existing generated video.
POST /videos/edits - Write
Create a video extension (deprecated)
Create an extension of a completed video.
POST /videos/extensions - Write
Create a video remix (deprecated)
Create a remix of a completed video using a refreshed prompt.
POST /videos/{video_id}/remix - Destructive
Delete a video (deprecated)
Permanently delete a completed or failed video and its stored assets.
DELETE /videos/{video_id}
Skills
- Read
List Skills
List all skills for the current project.
GET /skills - Read
Get Skill
Get a skill by its ID.
GET /skills/{skill_id} - Read
Get Skill Content
Download a skill zip bundle by its ID.
GET /skills/{skill_id}/content - Read
List Skill Versions
List skill versions for a skill.
GET /skills/{skill_id}/versions - Read
Get Skill Version
Get a specific skill version.
GET /skills/{skill_id}/versions/{version} - Read
Get Skill Version Content
Download a skill version zip bundle.
GET /skills/{skill_id}/versions/{version}/content - Write
Create Skill
Create a new skill.
POST /skills - Write
Update Skill Default Version
Update the default version pointer for a skill.
POST /skills/{skill_id} - Write
Create Skill Version
Create a new immutable skill version.
POST /skills/{skill_id}/versions - Destructive
Delete Skill
Delete a skill by its ID.
DELETE /skills/{skill_id} - Destructive
Delete Skill Version
Delete a skill version.
DELETE /skills/{skill_id}/versions/{version}
Chatkit
- Read
List ChatKit thread items
List items that belong to a ChatKit thread.
GET /chatkit/threads/{thread_id}/items - Read
Retrieve a ChatKit thread
Retrieve a ChatKit thread by its identifier.
GET /chatkit/threads/{thread_id} - Read
List ChatKit threads
List ChatKit threads with optional pagination and user filters.
GET /chatkit/threads - Write
Create a ChatKit session
Create a ChatKit session.
POST /chatkit/sessions - Destructive
Cancel a ChatKit session
Cancel an active ChatKit session and return its most recent metadata. Cancelling prevents new requests from using the issued client secret.
POST /chatkit/sessions/{session_id}/cancel - Destructive
Delete a ChatKit thread
Delete a ChatKit thread along with its items and stored attachments.
DELETE /chatkit/threads/{thread_id}
Decisions
- Write
Create a decision
Use this endpoint to quickly answer classification or scoring questions about some input. You can ask multiple questions in one request.
POST /decisions
Agents
- Read
List automations
Lists project-owned automations, optionally filtered by target session.
GET /agents/automations - Read
Get an automation
Retrieves a project-owned automation.
GET /agents/automations/{automation_id} - Read
List automation invocations
Lists delivery records for a project-owned automation.
GET /agents/automations/{automation_id}/invocations - Read
Get an automation invocation
Retrieves a delivery record for a project-owned automation.
GET /agents/automations/{automation_id}/invocations/{invocation_id} - Read
List agent environments
Lists OpenAI-hosted environments owned by the authenticated principal. Requires access to the prewarming beta.
GET /agents/environments - Read
Retrieve an agent environment
Retrieves an execution environment's connection status and safe installed metadata. See [environment lifecycle](https://developers.openai.com/api/docs/guides/agents-api/environments/lifecycle).
GET /agents/environments/{environment_id} - Read
List agent environment files
Lists live files on a connected execution environment with optional directory filtering and opaque cursor pagination. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).
GET /agents/environments/{environment_id}/files - Read
List session subagents
Lists subagents in a session, including nested and closed subagents. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents - Read
Retrieve a session subagent
Retrieves a subagent belonging to this session. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents/{subagent_id} - Read
List subagent items
Lists this subagent's own items across all of its turns. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents/{subagent_id}/items - Read
List subagent turns
Lists all turns of this subagent, including turns after a resume. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents/{subagent_id}/turns - Read
Retrieve a subagent turn
Retrieves a turn belonging to this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id} - Read
List subagent turn items
Lists items belonging to one turn of this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).
GET /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}/items - Read
List agents
Lists reusable agents in the current project. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).
GET /agents - Read
Retrieve an agent
Retrieves a reusable agent by ID. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).
GET /agents/{agent_id} - Read
List agent environment templates
Lists reusable environment templates without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).
GET /agents/environments/templates - Read
Retrieve an agent environment template
Retrieves reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).
GET /agents/environments/templates/{environment_template_id} - Read
List agent sessions
Lists managed agent sessions using ID-based pagination and the requested sort order. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).
GET /agents/sessions - Read
Retrieve an agent session
Retrieves the current state of a managed agent session. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).
GET /agents/sessions/{session_id} - Read
List agent session artifacts
Lists immutable artifacts published by completed hosted session turns. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).
GET /agents/sessions/{session_id}/artifacts - Read
Retrieve an agent session artifact
Retrieves immutable metadata for one durable session artifact. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).
GET /agents/sessions/{session_id}/artifacts/{artifact_id} - Read
Retrieve agent session artifact content
Downloads immutable session artifact bytes after the execution environment expires. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).
GET /agents/sessions/{session_id}/artifacts/{artifact_id}/content - Read
Stream agent session events
Streams live events for an agent session. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).
GET /agents/sessions/{session_id}/events - Read
List agent session items
Lists items produced by the session's root agent, including its interactions with subagents. Each subagent has its own item history. See [inspecting agent output](https://developers.openai.com/api/docs/guides/agents-api/observability).
GET /agents/sessions/{session_id}/items - Read
List agent session traces
Lists published root-turn traces as OTLP JSON, ordered by turn creation time and ID. Unpublished traces are skipped. Each page returns data available when read; it does not wait for late traces. Trace reads and the JSON response are limited to 16 MiB per request. If the limit is exceeded, request fewer traces.
GET /agents/sessions/{session_id}/traces - Read
List agent session turns
Lists turns by creation time and turn ID. The after cursor is exclusive in the selected order. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).
GET /agents/sessions/{session_id}/turns - Read
Retrieve an agent session turn
Retrieves a turn's current status, timestamps, usage, and error. Returns 404 if the turn does not belong to the session. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).
GET /agents/sessions/{session_id}/turns/{turn_id} - Read
List agent session turn items
Lists items belonging to one root-agent turn, including its interactions with subagents. See [inspecting agent output](https://developers.openai.com/api/docs/guides/agents-api/observability).
GET /agents/sessions/{session_id}/turns/{turn_id}/items - Write
Create an automation
Saves an active automation without invoking it immediately.
POST /agents/automations - Write
Pause an automation
Pauses future scheduled delivery without stopping an active session.
POST /agents/automations/{automation_id}/pause - Write
Resume an automation
Resumes scheduled delivery; one-time automations without a pending invocation require a future run_at.
POST /agents/automations/{automation_id}/resume - Write
Invoke an automation
Queues a manual delivery without changing the saved schedule.
POST /agents/automations/{automation_id}/invocations - Write
Create an agent environment
Creates an OpenAI-hosted environment before creating a session. Requires access to the prewarming beta.
POST /agents/environments - Write
Create an agent
Creates a reusable agent without storing credentials. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).
POST /agents - Write
Create an agent environment template
Creates reusable environment configuration without returning confidential setup commands or environment values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).
POST /agents/environments/templates - Write
Create an agent session
Creates a managed agent session, optionally submits initial input, and returns the session or streams its events when stream is true. See [running sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions).
POST /agents/sessions - Destructive
Update an automation
Updates supplied fields; target and metadata replace the whole field.
POST /agents/automations/{automation_id} - Destructive
Delete an automation
Deletes the automation and prevents future invocations without deleting its target session.
DELETE /agents/automations/{automation_id} - Destructive
Write an agent environment file
Copies inline bytes or a Files API file into a connected execution environment, replacing an existing regular file at the same path. Upload between turns and wait for success before starting the next turn. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).
POST /agents/environments/{environment_id}/files - Destructive
Update an agent
Updates a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).
POST /agents/{agent_id} - Destructive
Delete an agent
Deletes a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).
DELETE /agents/{agent_id} - Destructive
Update an agent environment template
Updates reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).
POST /agents/environments/templates/{environment_template_id} - Destructive
Delete an agent environment template
Deletes reusable environment configuration and all confidential template inputs. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).
DELETE /agents/environments/templates/{environment_template_id} - Destructive
Update an agent session
Updates session metadata, model, reasoning effort, or service tier. Model settings apply to subsequent turns. Omitted fields are unchanged. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).
POST /agents/sessions/{session_id} - Destructive
Delete an agent session
Removes a managed agent session from the public API and returns a deletion confirmation. If backend execution has ended, deletion can cancel a still-open public turn and abandon unpublished outputs. Running execution must be cancelled first. Physical cleanup may continue asynchronously. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).
DELETE /agents/sessions/{session_id} - Destructive
Delete an agent session artifact
Deletes an immutable session artifact without deleting its live environment file or original Files API object. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).
DELETE /agents/sessions/{session_id}/artifacts/{artifact_id} - Destructive
Create agent session input events
Submits message, cancellation, tool-result, or computer-use approval-response events to a managed agent session. Cancellation can recover a still-open turn whose backend execution has ended by marking it cancelled and abandoning unpublished outputs. Saved results, published files, and existing terminal outcomes are preserved. HTTP 202 confirms acceptance, not durable completion. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).
POST /agents/sessions/{session_id}/events
Vaults
- Read
List vaults
Lists vaults using ID-based pagination. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
GET /vaults - Read
Retrieve a vault
Retrieves a vault by its ID. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
GET /vaults/{vault_id} - Read
List vault credentials
Lists a vault's credentials using ID-based pagination without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
GET /vaults/{vault_id}/credentials - Read
Retrieve a vault credential
Retrieves vault credential metadata without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
GET /vaults/{vault_id}/credentials/{credential_id} - Write
Create a vault
Creates a vault for the current project. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
POST /vaults - Write
Create a vault credential
Creates a vault credential. Secret values are write-only and are never returned. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
POST /vaults/{vault_id}/credentials - Destructive
Update a vault
Updates the name or metadata of an active vault. Omitted fields remain unchanged. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
POST /vaults/{vault_id} - Destructive
Delete a vault
Deletes a vault and all its credentials. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
DELETE /vaults/{vault_id} - Destructive
Update a vault credential
Updates credential metadata or rotates its write-only secret. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
POST /vaults/{vault_id}/credentials/{credential_id} - Destructive
Delete a vault credential
Deletes a vault credential. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).
DELETE /vaults/{vault_id}/credentials/{credential_id}
Webhook endpoints
- Read
List Webhook Endpoints
Returns webhook endpoints for the authenticated project in newest-first order.
GET /webhook_endpoints - Read
Retrieve Webhook Endpoint
Retrieves a webhook endpoint for the authenticated project.
GET /webhook_endpoints/{webhook_endpoint_id} - Write
Create Webhook Endpoint
Creates a webhook endpoint for the authenticated project.
POST /webhook_endpoints - Write
Update Webhook Endpoint
Updates a webhook endpoint for the authenticated project.
POST /webhook_endpoints/{webhook_endpoint_id} - Write
Rotate Webhook Endpoint Signing Secret
Rotates the signing secret for a webhook endpoint in the authenticated project.
POST /webhook_endpoints/{webhook_endpoint_id}/rotate_secret - Write
Test Webhook Endpoint
Sends a sample event to a webhook endpoint for the authenticated project.
POST /webhook_endpoints/{webhook_endpoint_id}/test - Destructive
Delete Webhook Endpoint
Deletes a webhook endpoint for the authenticated project.
DELETE /webhook_endpoints/{webhook_endpoint_id}
Webhook event types
- Read
List Webhook Event Types
Returns webhook event types visible to the authenticated project.
GET /webhook_event_types
No operations match.
See How connections work for access and permissions, or browse all integrations.