OpenAI API

Version: 2.3.0

The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.

Schemes:

Summary

Tag: Assistants

Build Assistants that can call models and use tools.

Operation Description
GET /assistants

Returns a list of assistants.
POST /assistants

Create an assistant with a model and instructions.
GET /assistants/{assistant_id}

Retrieves an assistant.
POST /assistants/{assistant_id}

Modifies an assistant.
DELETE /assistants/{assistant_id}

Delete an assistant.
POST /threads

Create a thread.
POST /threads/runs

Create a thread and run it in one request.
GET /threads/{thread_id}

Retrieves a thread.
POST /threads/{thread_id}

Modifies a thread.
DELETE /threads/{thread_id}

Delete a thread.
GET /threads/{thread_id}/messages

Returns a list of messages for a given thread.
POST /threads/{thread_id}/messages

Create a message.
GET /threads/{thread_id}/messages/{message_id}

Retrieve a message.
POST /threads/{thread_id}/messages/{message_id}

Modifies a message.
DELETE /threads/{thread_id}/messages/{message_id}

Deletes a message.
GET /threads/{thread_id}/runs

Returns a list of runs belonging to a thread.
POST /threads/{thread_id}/runs

Create a run.
GET /threads/{thread_id}/runs/{run_id}

Retrieves a run.
POST /threads/{thread_id}/runs/{run_id}

Modifies a run.
POST /threads/{thread_id}/runs/{run_id}/cancel

Cancels a run that is in_progress.
GET /threads/{thread_id}/runs/{run_id}/steps

Returns a list of run steps belonging to a run.
GET /threads/{thread_id}/runs/{run_id}/steps/{step_id}

Retrieves a run step.
POST /threads/{thread_id}/runs/{run_id}/submit_tool_outputs

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.

Tag: Audio

Turn audio into text or text into audio.

Operation Description
POST /audio/speech

Generates audio from the input text.
POST /audio/transcriptions

Transcribes audio into the input language.
POST /audio/translations

Translates audio into English.

Tag: Models

List and describe the various models available in the API.

Operation Description
GET /models

Lists the currently available models, and provides basic information about each one such as the owner and availability.
GET /models/{model}

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
DELETE /models/{model}

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

Tag: Moderations

Given text and/or image inputs, classifies if those inputs are potentially harmful.

Operation Description
POST /moderations

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

Tag: Audit Logs

List user actions and configuration changes within this organization.

Operation Description
GET /organization/audit_logs

List user actions and configuration changes within this organization.

Tag: default

Operation Description
GET /organization/admin_api_keys

List organization API keys
POST /organization/admin_api_keys

Create an organization admin API key
GET /organization/admin_api_keys/{key_id}

Retrieve a single organization API key
DELETE /organization/admin_api_keys/{key_id}

Delete an organization admin API key

Tag: Usage

Operation Description
GET /organization/costs

Get costs details for the organization.
GET /organization/usage/audio_speeches

Get audio speeches usage details for the organization.
GET /organization/usage/audio_transcriptions

Get audio transcriptions usage details for the organization.
GET /organization/usage/code_interpreter_sessions

Get code interpreter sessions usage details for the organization.
GET /organization/usage/completions

Get completions usage details for the organization.
GET /organization/usage/embeddings

Get embeddings usage details for the organization.
GET /organization/usage/images

Get images usage details for the organization.
GET /organization/usage/moderations

Get moderations usage details for the organization.
GET /organization/usage/vector_stores

Get vector stores usage details for the organization.

Tag: Invites

Operation Description
GET /organization/invites

Returns a list of invites in the organization.
POST /organization/invites

Create an invite for a user to the organization. The invite must be accepted by the user before they have access to the organization.
GET /organization/invites/{invite_id}

Retrieves an invite.
DELETE /organization/invites/{invite_id}

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

Tag: Projects

Operation Description
GET /organization/projects

Returns a list of projects.
POST /organization/projects

Create a new project in the organization. Projects can be created and archived, but cannot be deleted.
GET /organization/projects/{project_id}

Retrieves a project.
POST /organization/projects/{project_id}

Modifies a project in the organization.
GET /organization/projects/{project_id}/api_keys

Returns a list of API keys in the project.
GET /organization/projects/{project_id}/api_keys/{key_id}

Retrieves an API key in the project.
DELETE /organization/projects/{project_id}/api_keys/{key_id}

Deletes an API key from the project.
POST /organization/projects/{project_id}/archive

Archives a project in the organization. Archived projects cannot be used or updated.
GET /organization/projects/{project_id}/rate_limits

Returns the rate limits per model for a project.
POST /organization/projects/{project_id}/rate_limits/{rate_limit_id}

Updates a project rate limit.
GET /organization/projects/{project_id}/service_accounts

Returns a list of service accounts in the project.
POST /organization/projects/{project_id}/service_accounts

Creates a new service account in the project. This also returns an unredacted API key for the service account.
GET /organization/projects/{project_id}/service_accounts/{service_account_id}

Retrieves a service account in the project.
DELETE /organization/projects/{project_id}/service_accounts/{service_account_id}

Deletes a service account from the project.
GET /organization/projects/{project_id}/users

Returns a list of users in the project.
POST /organization/projects/{project_id}/users

Adds a user to the project. Users must already be members of the organization to be added to a project.
GET /organization/projects/{project_id}/users/{user_id}

Retrieves a user in the project.
POST /organization/projects/{project_id}/users/{user_id}

Modifies a user's role in the project.
DELETE /organization/projects/{project_id}/users/{user_id}

Deletes a user from the project.

Tag: Users

Operation Description
GET /organization/users

Lists all of the users in the organization.
GET /organization/users/{user_id}

Retrieves a user by their identifier.
POST /organization/users/{user_id}

Modifies a user's role in the organization.
DELETE /organization/users/{user_id}

Deletes a user from the organization.

Tag: Realtime

Operation Description
POST /realtime/sessions

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.

Tag: Vector stores

Operation Description
GET /vector_stores

Returns a list of vector stores.
POST /vector_stores

Create a vector store.
GET /vector_stores/{vector_store_id}

Retrieves a vector store.
POST /vector_stores/{vector_store_id}

Modifies a vector store.
DELETE /vector_stores/{vector_store_id}

Delete a vector store.
POST /vector_stores/{vector_store_id}/file_batches

Create a vector store file batch.
GET /vector_stores/{vector_store_id}/file_batches/{batch_id}

Retrieves a vector store file batch.
POST /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.
GET /vector_stores/{vector_store_id}/file_batches/{batch_id}/files

Returns a list of vector store files in a batch.
GET /vector_stores/{vector_store_id}/files

Returns a list of vector store files.
POST /vector_stores/{vector_store_id}/files

Create a vector store file by attaching a File to a vector store.
GET /vector_stores/{vector_store_id}/files/{file_id}

Retrieves a vector store file.
DELETE /vector_stores/{vector_store_id}/files/{file_id}

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.

Tag: Chat

Given a list of messages comprising a conversation, the model will return a response.

Operation Description
POST /chat/completions

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.

Tag: Completions

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

Operation Description
POST /completions

Creates a completion for the provided prompt and parameters.

Tag: Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Operation Description
POST /embeddings

Creates an embedding vector representing the input text.

Tag: Fine-tuning

Manage fine-tuning jobs to tailor a model to your specific training data.

Operation Description
POST /fine_tuning/jobs

Creates a fine-tuning job which begins the process of creating a new model from a given dataset.

Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.

Learn more about fine-tuning
GET /fine_tuning/jobs

List your organization's fine-tuning jobs
GET /fine_tuning/jobs/{fine_tuning_job_id}

Get info about a fine-tuning job.

Learn more about fine-tuning
POST /fine_tuning/jobs/{fine_tuning_job_id}/cancel

Immediately cancel a fine-tune job.
GET /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

List checkpoints for a fine-tuning job.
GET /fine_tuning/jobs/{fine_tuning_job_id}/events

Get status updates for a fine-tuning job.

Tag: Batch

Create large batches of API requests to run asynchronously.

Operation Description
POST /batches

Creates and executes a batch from an uploaded file of requests
GET /batches

List your organization's batches.
GET /batches/{batch_id}

Retrieves a batch.
POST /batches/{batch_id}/cancel

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.

Tag: Files

Files are used to upload documents that can be used with features like Assistants and Fine-tuning.

Operation Description
GET /files

Returns a list of files.
POST /files

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

The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide 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.
DELETE /files/{file_id}

Delete a file.
GET /files/{file_id}

Returns information about a specific file.
GET /files/{file_id}/content

Returns the contents of the specified file.

Tag: Uploads

Use Uploads to upload large files in multiple parts.

Operation Description
POST /uploads

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 purposes, 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.
POST /uploads/{upload_id}/cancel

Cancels the Upload. No Parts may be added after an Upload is cancelled.
POST /uploads/{upload_id}/complete

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.
POST /uploads/{upload_id}/parts

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.

Tag: Images

Given a prompt and/or an input image, the model will generate a new image.

Operation Description
POST /images/edits

Creates an edited or extended image given an original image and a prompt.
POST /images/generations

Creates an image given a prompt.
POST /images/variations

Creates a variation of a given image.

Paths

Returns a list of assistants.

GET /assistants

Tags: Assistants
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
200 OK

OK

Create an assistant with a model and instructions.

POST /assistants

Tags: Assistants
200 OK

OK

Delete an assistant.

DELETE /assistants/{assistant_id}

Tags: Assistants
assistant_id

The ID of the assistant to delete.

 path object
200 OK

OK

Retrieves an assistant.

GET /assistants/{assistant_id}

Tags: Assistants
assistant_id

The ID of the assistant to retrieve.

 path object
200 OK

OK

Modifies an assistant.

POST /assistants/{assistant_id}

Tags: Assistants
assistant_id

The ID of the assistant to modify.

 path object
200 OK

OK

Generates audio from the input text.

POST /audio/speech

Tags: Audio
200 OK

OK
Transfer-Encoding

chunked

 object
Transcribes audio into the input language.

POST /audio/transcriptions

Tags: Audio
200 OK

OK

Translates audio into English.

POST /audio/translations

Tags: Audio
200 OK

OK

List your organization's batches.

GET /batches

Tags: Batch
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
200 OK

Batch listed successfully.

Creates and executes a batch from an uploaded file of requests

POST /batches

Tags: Batch
200 OK

Batch created successfully.

Retrieves a batch.

GET /batches/{batch_id}

Tags: Batch
batch_id

The ID of the batch to retrieve.

 path object
200 OK

Batch retrieved successfully.

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

Tags: Batch
batch_id

The ID of the batch to cancel.

 path object
200 OK

Batch is cancelling. Returns the cancelling batch's details.

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.

POST /chat/completions

Tags: Chat
200 OK

OK

Creates a completion for the provided prompt and parameters.

POST /completions

Tags: Completions
200 OK

OK

Creates an embedding vector representing the input text.

POST /embeddings

Tags: Embeddings
200 OK

OK

Returns a list of files.

GET /files

Tags: Files
purpose

Only return files with the given purpose.

 query object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

OK

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

The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide 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.

POST /files

Tags: Files
200 OK

OK

Delete a file.

DELETE /files/{file_id}

Tags: Files
file_id

The ID of the file to use for this request.

 path object
200 OK

OK

Returns information about a specific file.

GET /files/{file_id}

Tags: Files
file_id

The ID of the file to use for this request.

 path object
200 OK

OK

Returns the contents of the specified file.

GET /files/{file_id}/content

Tags: Files
file_id

The ID of the file to use for this request.

 path object
200 OK

OK

List your organization's fine-tuning jobs

GET /fine_tuning/jobs

Tags: Fine-tuning
after

Identifier for the last job from the previous pagination request.

 query object
limit

Number of fine-tuning jobs to retrieve.

 query object
200 OK

OK

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

POST /fine_tuning/jobs

Tags: Fine-tuning
200 OK

OK

Get info about a fine-tuning job.

Learn more about fine-tuning

GET /fine_tuning/jobs/{fine_tuning_job_id}

Tags: Fine-tuning
fine_tuning_job_id

The ID of the fine-tuning job.

 path object
200 OK

OK

Immediately cancel a fine-tune job.

POST /fine_tuning/jobs/{fine_tuning_job_id}/cancel

Tags: Fine-tuning
fine_tuning_job_id

The ID of the fine-tuning job to cancel.

 path object
200 OK

OK

List checkpoints for a fine-tuning job.

GET /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

Tags: Fine-tuning
fine_tuning_job_id

The ID of the fine-tuning job to get checkpoints for.

 path object
after

Identifier for the last checkpoint ID from the previous pagination request.

 query object
limit

Number of checkpoints to retrieve.

 query object
200 OK

OK

Get status updates for a fine-tuning job.

GET /fine_tuning/jobs/{fine_tuning_job_id}/events

Tags: Fine-tuning
fine_tuning_job_id

The ID of the fine-tuning job to get events for.

 path object
after

Identifier for the last event from the previous pagination request.

 query object
limit

Number of events to retrieve.

 query object
200 OK

OK

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

POST /images/edits

Tags: Images
200 OK

OK

Creates an image given a prompt.

POST /images/generations

Tags: Images
200 OK

OK

Creates a variation of a given image.

POST /images/variations

Tags: Images
200 OK

OK

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

GET /models

Tags: Models
200 OK

OK

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

DELETE /models/{model}

Tags: Models
model

The model to delete

 path object
200 OK

OK

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

GET /models/{model}

Tags: Models
model

The ID of the model to use for this request

 path object
200 OK

OK

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

POST /moderations

Tags: Moderations
200 OK

OK

List organization API keys

GET /organization/admin_api_keys

Retrieve a paginated list of organization admin API keys.
after query object
order query object
limit query object
200 OK

A list of organization API keys.
bearer_identity_edge key.secret , api.management.read
basic_identity_edge
Create an organization admin API key

POST /organization/admin_api_keys

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

200 OK

The newly created admin API key.
bearer_identity_edge key.secret , api.management.write
basic_identity_edge
Delete an organization admin API key

DELETE /organization/admin_api_keys/{key_id}

Delete the specified admin API key.
key_id path object
200 OK

Confirmation that the API key was deleted.
bearer_identity_edge key.secret , api.management.write
basic_identity_edge
Retrieve a single organization API key

GET /organization/admin_api_keys/{key_id}

Get details for a specific organization API key by its ID.
key_id path object
200 OK

Details of the requested API key.
bearer_identity_edge key.secret , api.management.read
basic_identity_edge
List user actions and configuration changes within this organization.

GET /organization/audit_logs

Tags: Audit Logs
effective_at

Return only events whose effective_at (Unix seconds) is in this range.

 query object
project_ids[]

Return only events for these projects.

 query object
event_types[]

Return only events with a type in one of these values. For example, project.created. For all options, see the documentation for the audit log object.

 query object
actor_ids[]

Return only events performed by these actors. Can be a user ID, a service account ID, or an api key tracking ID.

 query object
actor_emails[]

Return only events performed by users with these emails.

 query object
resource_ids[]

Return only events performed on these targets. For example, a project ID updated.

 query object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
200 OK

Audit logs listed successfully.

Get costs details for the organization.

GET /organization/costs

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently only 1d is supported, default to 1d.

 query object
project_ids

Return only costs for these projects.

 query object
group_by

Group the costs by the specified fields. Support fields include project_id, line_item and any combination of them.

 query object
limit

A limit on the number of buckets to be returned. Limit can range between 1 and 180, and the default is 7.

 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Costs data retrieved successfully.

Returns a list of invites in the organization.

GET /organization/invites

Tags: Invites
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

Invites listed successfully.

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

Tags: Invites
200 OK

User invited successfully.

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

DELETE /organization/invites/{invite_id}

Tags: Invites
invite_id

The ID of the invite to delete.

 path object
200 OK

Invite deleted successfully.

Retrieves an invite.

GET /organization/invites/{invite_id}

Tags: Invites
invite_id

The ID of the invite to retrieve.

 path object
200 OK

Invite retrieved successfully.

Returns a list of projects.

GET /organization/projects

Tags: Projects
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
include_archived

If true returns all projects including those that have been archived. Archived projects are not included by default.

 query object
200 OK

Projects listed successfully.

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

POST /organization/projects

Tags: Projects
200 OK

Project created successfully.

Retrieves a project.

GET /organization/projects/{project_id}

Tags: Projects
project_id

The ID of the project.

 path object
200 OK

Project retrieved successfully.

Modifies a project in the organization.

POST /organization/projects/{project_id}

Tags: Projects
project_id

The ID of the project.

 path object
200 OK

Project updated successfully.

400 Bad Request

Error response when updating the default project.

Returns a list of API keys in the project.

GET /organization/projects/{project_id}/api_keys

Tags: Projects
project_id

The ID of the project.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

Project API keys listed successfully.

Deletes an API key from the project.

DELETE /organization/projects/{project_id}/api_keys/{key_id}

Tags: Projects
project_id

The ID of the project.

 path object
key_id

The ID of the API key.

 path object
200 OK

Project API key deleted successfully.

400 Bad Request

Error response for various conditions.

Retrieves an API key in the project.

GET /organization/projects/{project_id}/api_keys/{key_id}

Tags: Projects
project_id

The ID of the project.

 path object
key_id

The ID of the API key.

 path object
200 OK

Project API key retrieved successfully.

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

POST /organization/projects/{project_id}/archive

Tags: Projects
project_id

The ID of the project.

 path object
200 OK

Project archived successfully.

Returns the rate limits per model for a project.

GET /organization/projects/{project_id}/rate_limits

Tags: Projects
project_id

The ID of the project.

 path object
limit

A limit on the number of objects to be returned. The default is 100.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, beginning with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
200 OK

Project rate limits listed successfully.

Updates a project rate limit.

POST /organization/projects/{project_id}/rate_limits/{rate_limit_id}

Tags: Projects
project_id

The ID of the project.

 path object
rate_limit_id

The ID of the rate limit.

 path object
200 OK

Project rate limit updated successfully.

400 Bad Request

Error response for various conditions.

Returns a list of service accounts in the project.

GET /organization/projects/{project_id}/service_accounts

Tags: Projects
project_id

The ID of the project.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

Project service accounts listed successfully.

400 Bad Request

Error response when project is archived.

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

POST /organization/projects/{project_id}/service_accounts

Tags: Projects
project_id

The ID of the project.

 path object
200 OK

Project service account created successfully.

400 Bad Request

Error response when project is archived.

Deletes a service account from the project.

DELETE /organization/projects/{project_id}/service_accounts/{service_account_id}

Tags: Projects
project_id

The ID of the project.

 path object
service_account_id

The ID of the service account.

 path object
200 OK

Project service account deleted successfully.

Retrieves a service account in the project.

GET /organization/projects/{project_id}/service_accounts/{service_account_id}

Tags: Projects
project_id

The ID of the project.

 path object
service_account_id

The ID of the service account.

 path object
200 OK

Project service account retrieved successfully.

Returns a list of users in the project.

GET /organization/projects/{project_id}/users

Tags: Projects
project_id

The ID of the project.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

Project users listed successfully.

400 Bad Request

Error response when project is archived.

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

Tags: Projects
project_id

The ID of the project.

 path object
200 OK

User added to project successfully.

400 Bad Request

Error response for various conditions.

Deletes a user from the project.

DELETE /organization/projects/{project_id}/users/{user_id}

Tags: Projects
project_id

The ID of the project.

 path object
user_id

The ID of the user.

 path object
200 OK

Project user deleted successfully.

400 Bad Request

Error response for various conditions.

Retrieves a user in the project.

GET /organization/projects/{project_id}/users/{user_id}

Tags: Projects
project_id

The ID of the project.

 path object
user_id

The ID of the user.

 path object
200 OK

Project user retrieved successfully.

Modifies a user's role in the project.

POST /organization/projects/{project_id}/users/{user_id}

Tags: Projects
project_id

The ID of the project.

 path object
user_id

The ID of the user.

 path object
200 OK

Project user's role updated successfully.

400 Bad Request

Error response for various conditions.

Get audio speeches usage details for the organization.

GET /organization/usage/audio_speeches

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get audio transcriptions usage details for the organization.

GET /organization/usage/audio_transcriptions

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get code interpreter sessions usage details for the organization.

GET /organization/usage/code_interpreter_sessions

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get completions usage details for the organization.

GET /organization/usage/completions

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
batch

If true, return batch jobs only. If false, return non-batch jobs only. By default, return both.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, batch or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get embeddings usage details for the organization.

GET /organization/usage/embeddings

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get images usage details for the organization.

GET /organization/usage/images

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
sources

Return only usages for these sources. Possible values are image.generation, image.edit, image.variation or any combination of them.

 query object
sizes

Return only usages for these image sizes. Possible values are 256x256, 512x512, 1024x1024, 1792x1792, 1024x1792 or any combination of them.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, size, source or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get moderations usage details for the organization.

GET /organization/usage/moderations

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
user_ids

Return only usage for these users.

 query object
api_key_ids

Return only usage for these API keys.

 query object
models

Return only usage for these models.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Get vector stores usage details for the organization.

GET /organization/usage/vector_stores

Tags: Usage
start_time

Start time (Unix seconds) of the query time range, inclusive.

 query object
end_time

End time (Unix seconds) of the query time range, exclusive.

 query object
bucket_width

Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

 query object
project_ids

Return only usage for these projects.

 query object
group_by

Group the usage data by the specified fields. Support fields include project_id.

 query object
limit

Specifies the number of buckets to return.

  • bucket_width=1d: default: 7, max: 31
  • bucket_width=1h: default: 24, max: 168
  • bucket_width=1m: default: 60, max: 1440
 query object
page

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

 query object
200 OK

Usage data retrieved successfully.

Lists all of the users in the organization.

GET /organization/users

Tags: Users
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
200 OK

Users listed successfully.

Deletes a user from the organization.

DELETE /organization/users/{user_id}

Tags: Users
user_id

The ID of the user.

 path object
200 OK

User deleted successfully.

Retrieves a user by their identifier.

GET /organization/users/{user_id}

Tags: Users
user_id

The ID of the user.

 path object
200 OK

User retrieved successfully.

Modifies a user's role in the organization.

POST /organization/users/{user_id}

Tags: Users
user_id

The ID of the user.

 path object
200 OK

User role updated successfully.

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.

POST /realtime/sessions

Tags: Realtime
200 OK

Session created successfully.

Create a thread.

POST /threads

Tags: Assistants
200 OK

OK

Create a thread and run it in one request.

POST /threads/runs

Tags: Assistants
200 OK

OK

Delete a thread.

DELETE /threads/{thread_id}

Tags: Assistants
thread_id

The ID of the thread to delete.

 path object
200 OK

OK

Retrieves a thread.

GET /threads/{thread_id}

Tags: Assistants
thread_id

The ID of the thread to retrieve.

 path object
200 OK

OK

Modifies a thread.

POST /threads/{thread_id}

Tags: Assistants
thread_id

The ID of the thread to modify. Only the metadata can be modified.

 path object
200 OK

OK

Returns a list of messages for a given thread.

GET /threads/{thread_id}/messages

Tags: Assistants
thread_id

The ID of the thread the messages belong to.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
run_id

Filter messages by the run ID that generated them.

 query object
200 OK

OK

Create a message.

POST /threads/{thread_id}/messages

Tags: Assistants
thread_id

The ID of the thread to create a message for.

 path object
200 OK

OK

Deletes a message.

DELETE /threads/{thread_id}/messages/{message_id}

Tags: Assistants
thread_id

The ID of the thread to which this message belongs.

 path object
message_id

The ID of the message to delete.

 path object
200 OK

OK

Retrieve a message.

GET /threads/{thread_id}/messages/{message_id}

Tags: Assistants
thread_id

The ID of the thread to which this message belongs.

 path object
message_id

The ID of the message to retrieve.

 path object
200 OK

OK

Modifies a message.

POST /threads/{thread_id}/messages/{message_id}

Tags: Assistants
thread_id

The ID of the thread to which this message belongs.

 path object
message_id

The ID of the message to modify.

 path object
200 OK

OK

Returns a list of runs belonging to a thread.

GET /threads/{thread_id}/runs

Tags: Assistants
thread_id

The ID of the thread the run belongs to.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
200 OK

OK

Create a run.

POST /threads/{thread_id}/runs

Tags: Assistants
thread_id

The ID of the thread to run.

 path object
include[]

A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

See the file search tool documentation for more information.

 query object
200 OK

OK

Retrieves a run.

GET /threads/{thread_id}/runs/{run_id}

Tags: Assistants
thread_id

The ID of the thread that was run.

 path object
run_id

The ID of the run to retrieve.

 path object
200 OK

OK

Modifies a run.

POST /threads/{thread_id}/runs/{run_id}

Tags: Assistants
thread_id

The ID of the thread that was run.

 path object
run_id

The ID of the run to modify.

 path object
200 OK

OK

Cancels a run that is in_progress.

POST /threads/{thread_id}/runs/{run_id}/cancel

Tags: Assistants
thread_id

The ID of the thread to which this run belongs.

 path object
run_id

The ID of the run to cancel.

 path object
200 OK

OK

Returns a list of run steps belonging to a run.

GET /threads/{thread_id}/runs/{run_id}/steps

Tags: Assistants
thread_id

The ID of the thread the run and run steps belong to.

 path object
run_id

The ID of the run the run steps belong to.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
include[]

A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

See the file search tool documentation for more information.

 query object
200 OK

OK

Retrieves a run step.

GET /threads/{thread_id}/runs/{run_id}/steps/{step_id}

Tags: Assistants
thread_id

The ID of the thread to which the run and run step belongs.

 path object
run_id

The ID of the run to which the run step belongs.

 path object
step_id

The ID of the run step to retrieve.

 path object
include[]

A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

See the file search tool documentation for more information.

 query object
200 OK

OK

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

Tags: Assistants
thread_id

The ID of the thread to which this run belongs.

 path object
run_id

The ID of the run that requires the tool output submission.

 path object
200 OK

OK

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 purposes, 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.

POST /uploads

Tags: Uploads
200 OK

OK

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

POST /uploads/{upload_id}/cancel

Tags: Uploads
upload_id

The ID of the Upload.

 path object
200 OK

OK

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.

POST /uploads/{upload_id}/complete

Tags: Uploads
upload_id

The ID of the Upload.

 path object
200 OK

OK

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.

POST /uploads/{upload_id}/parts

Tags: Uploads
upload_id

The ID of the Upload.

 path object
200 OK

OK

Returns a list of vector stores.

GET /vector_stores

Tags: Vector stores
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
200 OK

OK

Create a vector store.

POST /vector_stores

Tags: Vector stores
200 OK

OK

Delete a vector store.

DELETE /vector_stores/{vector_store_id}

Tags: Vector stores
vector_store_id

The ID of the vector store to delete.

 path object
200 OK

OK

Retrieves a vector store.

GET /vector_stores/{vector_store_id}

Tags: Vector stores
vector_store_id

The ID of the vector store to retrieve.

 path object
200 OK

OK

Modifies a vector store.

POST /vector_stores/{vector_store_id}

Tags: Vector stores
vector_store_id

The ID of the vector store to modify.

 path object
200 OK

OK

Create a vector store file batch.

POST /vector_stores/{vector_store_id}/file_batches

Tags: Vector stores
vector_store_id

The ID of the vector store for which to create a File Batch.

 path object
200 OK

OK

Retrieves a vector store file batch.

GET /vector_stores/{vector_store_id}/file_batches/{batch_id}

Tags: Vector stores
vector_store_id

The ID of the vector store that the file batch belongs to.

 path object
batch_id

The ID of the file batch being retrieved.

 path object
200 OK

OK

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

Tags: Vector stores
vector_store_id

The ID of the vector store that the file batch belongs to.

 path object
batch_id

The ID of the file batch to cancel.

 path object
200 OK

OK

Returns a list of vector store files in a batch.

GET /vector_stores/{vector_store_id}/file_batches/{batch_id}/files

Tags: Vector stores
vector_store_id

The ID of the vector store that the files belong to.

 path object
batch_id

The ID of the file batch that the files belong to.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
filter

Filter by file status. One of in_progress, completed, failed, cancelled.

 query object
200 OK

OK

Returns a list of vector store files.

GET /vector_stores/{vector_store_id}/files

Tags: Vector stores
vector_store_id

The ID of the vector store that the files belong to.

 path object
limit

A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

 query object
order

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

 query object
after

A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

 query object
before

A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

 query object
filter

Filter by file status. One of in_progress, completed, failed, cancelled.

 query object
200 OK

OK

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

POST /vector_stores/{vector_store_id}/files

Tags: Vector stores
vector_store_id

The ID of the vector store for which to create a File.

 path object
200 OK

OK

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 /vector_stores/{vector_store_id}/files/{file_id}

Tags: Vector stores
vector_store_id

The ID of the vector store that the file belongs to.

 path object
file_id

The ID of the file to delete.

 path object
200 OK

OK

Retrieves a vector store file.

GET /vector_stores/{vector_store_id}/files/{file_id}

Tags: Vector stores
vector_store_id

The ID of the vector store that the file belongs to.

 path object
file_id

The ID of the file being retrieved.

 path object
200 OK

OK