user_idstringrequired
The ID of the user.
Modifies a user's role in the organization.
post
https://api.openai.com/v1/organization/users/{user_id}
Path Parameters
Body
application/json
Body
application/json
The new user role to modify. This must be one of owner or member.
UserRoleUpdateRequest
rolestringrequired
owner or reader
Allowed values:ownerreader
Response
200 application/json
Response
200 application/json
User role updated successfully.
User
Represents an individual user within an organization.
objectstringrequired
The object type, which is always organization.user
Allowed values:organization.user
idstringrequired
The identifier, which can be referenced in API endpoints
namestringrequired
The name of the user
emailstringrequired
The email address of the user
rolestringrequired
owner or reader
Allowed values:ownerreader
added_atintegerrequired
The Unix timestamp (in seconds) of when the user was added.
post/organization/users/{user_id}
Authentication
Path Parameters
Body
{
"role": "owner"
}
200 application/json
Deletes a user from the organization.
delete
https://api.openai.com/v1/organization/users/{user_id}
Path Parameters
user_idstringrequired
The ID of the user.
Response
200 application/json
Response
200 application/json
User deleted successfully.
UserDeleteResponse
objectstringrequired
Allowed values:organization.user.deleted
idstringrequired
deletedbooleanrequired
delete/organization/users/{user_id}
Authentication
Path Parameters
200 application/json
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
https://api.openai.com/v1/realtime/sessions
Body
application/json
Body
application/json
Create an ephemeral API key with the given session configuration.
RealtimeSessionCreateRequest
Realtime session object configuration.
modalities
The set of modalities the model can respond with. To disable audio,
set this to [“text”].
modelstring
The Realtime model used for this session.
Allowed values:gpt-4o-realtime-previewgpt-4o-realtime-preview-2024-10-01gpt-4o-realtime-preview-2024-12-17gpt-4o-mini-realtime-previewgpt-4o-mini-realtime-preview-2024-12-17
instructionsstring
The default system instructions (i.e. system message) prepended to model
calls. This field allows the client to guide the model on desired
responses. The model can be instructed on response content and format,
(e.g. “be extremely succinct”, “act friendly”, “here are examples of good
responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion
into your voice”, “laugh frequently”). The instructions are not guaranteed
to be followed by the model, but they provide guidance to the model on the
desired behavior.
Note that the server sets default instructions which will be used if this
field is not set and are visible in the session.created event at the
start of the session.
voicestring
The voice the model uses to respond. Voice cannot be changed during the
session once the model has responded with audio at least once. Current
voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.
Allowed values:alloyashballadcoralechosageshimmerverse
input_audio_formatstring
The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate,
single channel (mono), and little-endian byte order.
Allowed values:pcm16g711_ulawg711_alaw
output_audio_formatstring
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, output audio is sampled at a rate of 24kHz.
Allowed values:pcm16g711_ulawg711_alaw
input_audio_transcriptionobject
Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through OpenAI Whisper transcription and should be treated as rough guidance rather than the representation understood by the model. The client can optionally set the language and prompt for transcription, these fields will be passed to the Whisper API.
Show Child Parameters
turn_detectionobject
Configuration for turn detection. Can be set to null to turn off. Server
VAD means that the model will detect the start and end of speech based on
audio volume and respond at the end of user speech.
Show Child Parameters
toolsarray[object]
Tools (functions) available to the model.
Show Child Parameters
tool_choicestring
How the model chooses tools. Options are auto, none, required, or
specify a function.
temperaturenumber
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
max_response_output_tokens
One OfMaximum number of output tokens for a single assistant response,
inclusive of tool calls. Provide an integer between 1 and 4096 to
limit output tokens, or inf for the maximum available tokens for a
given model. Defaults to inf.
Variant 1integer
Response
200 application/json
Response
200 application/json
Session created successfully.
RealtimeSessionCreateResponse
A new Realtime session configuration, with an ephermeral key. Default TTL
for keys is one minute.
client_secretobjectrequired
Ephemeral key returned by the API.
Show Child Parameters
modalities
The set of modalities the model can respond with. To disable audio,
set this to [“text”].
instructionsstring
The default system instructions (i.e. system message) prepended to model
calls. This field allows the client to guide the model on desired
responses. The model can be instructed on response content and format,
(e.g. “be extremely succinct”, “act friendly”, “here are examples of good
responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion
into your voice”, “laugh frequently”). The instructions are not guaranteed
to be followed by the model, but they provide guidance to the model on the
desired behavior.
Note that the server sets default instructions which will be used if this
field is not set and are visible in the session.created event at the
start of the session.
voicestring
The voice the model uses to respond. Voice cannot be changed during the
session once the model has responded with audio at least once. Current
voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.
Allowed values:alloyashballadcoralechosageshimmerverse
input_audio_formatstring
The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.
output_audio_formatstring
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
input_audio_transcriptionobject
Configuration for input audio transcription, defaults to off and can be
set to null to turn off once on. Input audio transcription is not native
to the model, since the model consumes audio directly. Transcription runs
asynchronously through Whisper and should be treated as rough guidance
rather than the representation understood by the model.
Show Child Parameters
turn_detectionobject
Configuration for turn detection. Can be set to null to turn off. Server
VAD means that the model will detect the start and end of speech based on
audio volume and respond at the end of user speech.
Show Child Parameters
toolsarray[object]
Tools (functions) available to the model.
Show Child Parameters
tool_choicestring
How the model chooses tools. Options are auto, none, required, or
specify a function.
temperaturenumber
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
max_response_output_tokens
One OfMaximum number of output tokens for a single assistant response,
inclusive of tool calls. Provide an integer between 1 and 4096 to
limit output tokens, or inf for the maximum available tokens for a
given model. Defaults to inf.
Variant 1integer
post/realtime/sessions
Authentication
Body
{}
200 application/json
Returns a list of vector stores.
get
https://api.openai.com/v1/vector_stores
Query Parameters
limitinteger
A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
Default:20
orderstring
Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.
Allowed values:ascdesc
Default:desc
afterstring
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.
beforestring
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.
Response
200 application/json
Response
200 application/json
OK
ListVectorStoresResponse
objectstringrequired
Example:list
dataarray[object]required
A vector store is a collection of processed files can be used by the file_search tool.
Show Child Parameters
first_idstringrequired
Example:vs_abc123
last_idstringrequired
Example:vs_abc456
has_morebooleanrequired
Example:false
get/vector_stores
Authentication
Query Parameters
200 application/json
Create a vector store.
post
https://api.openai.com/v1/vector_stores
Body
application/json
Body
application/json
CreateVectorStoreRequest
* Additional properties are NOT allowed.
file_idsarray[string]
A list of File IDs that the vector store should use. Useful for tools like file_search that can access files.
<= 500 items
namestring
The name of the vector store.
expires_afterobject
The expiration policy for a vector store.
Show Child Parameters
chunking_strategy
One Ofobject
The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.
Auto Chunking Strategyobject
The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.
* Additional properties are NOT allowed.
Show Child Parameters
metadataobject | null
Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.
Response
200 application/json
Response
200 application/json
OK
Vector store
A vector store is a collection of processed files can be used by the file_search tool.
idstringrequired
The identifier, which can be referenced in API endpoints.
objectstringrequired
The object type, which is always vector_store.
Allowed values:vector_store
created_atintegerrequired
The Unix timestamp (in seconds) for when the vector store was created.
namestringrequired
The name of the vector store.
usage_bytesintegerrequired
The total number of bytes used by the files in the vector store.
file_countsobjectrequired
Show Child Parameters
statusstringrequired
The status of the vector store, which can be either expired, in_progress, or completed. A status of completed indicates that the vector store is ready for use.
Allowed values:expiredin_progresscompleted
expires_afterobject
The expiration policy for a vector store.
Show Child Parameters
expires_atinteger | null
The Unix timestamp (in seconds) for when the vector store will expire.
last_active_atinteger | nullrequired
The Unix timestamp (in seconds) for when the vector store was last active.
metadataobject | nullrequired
Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.
post/vector_stores
Authentication
Body
{}
200 application/json