Assistants
- GETList assistants
- POSTCreate assistant
- GETRetrieve assistant
- POSTModify assistant
- DELDelete assistant
- POSTCreate thread
- POSTCreate thread and run
- GETRetrieve thread.
- POSTModify thread
- DELDelete thread
- GETList messages
- POSTCreate message
- GETRetrieve message
- POSTModify message
- DELDelete message
- GETList runs
- POSTCreate run
- GETRetrieve run
- POSTModify run
- POSTCancel run
- GETList run steps
- GETRetrieve run step
- POSTThe run step object
Chat
Completions
Embeddings
Evals
Files
Fine-tuning
- GETList checkpoint permissions
- POSTCreate checkpoint permissions
- DELDelete checkpoint permission
- GETList your organization's fine-tuning jobs
- POSTCreate a fine-tuning job
- GETRetrieve fine-tuning job
- POSTImmediately cancel a fine-tune job.
- GETList checkpoints for a fine-tuning job.
- GETGet status updates for a fine-tuning job.
Moderations
API Reference
Audit Logs
Certificates
Usage
Projects
- GETReturns a list of projects.
- POSTCreate project
- GETRetrieves a project.
- POSTModify project
- GETList project API keys
- GETRetrieve project API key
- DELDelete project API key
- POSTArchive project
- GETList project rate limits
- POSTUpdate project rate limit
- GETList project service accounts
- POSTCreate project service account
- GETRetrieve project service account
- DELDelete project service account
- GETReturn project users
- POSTCreate project user
- GETRetrieve project user
- POSTModify project user
- DELDelete project user
Responses
Vector stores
- GETReturns a list of vector stores.
- POSTCreate a vector store.
- GETRetrieves a vector store.
- POSTModifies a vector store.
- DELDelete a vector store.
- POSTCreate a vector store file batch.
- GETRetrieves a vector store file batch.
- POSTCancel vector store file batch
- GETReturns a list of vector store files in a batch.
- GETReturns a list of vector store files.
- POSTCreate vector store file
- GETRetrieves a vector store file.
- POSTUpdate attributes on a vector store file.
- DELDelete vector store file
- GETRetrieve vector store
- POSTSearch vector store
Realtime
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.
POST
/
realtime
/
sessions
Copy
Ask AI
curl --request POST \
--url https://api.openai.com/v1/realtime/sessions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"modalities": [
[
"text",
"audio"
]
],
"model": "gpt-4o-realtime-preview",
"instructions": "<string>",
"voice": "ash",
"input_audio_format": "pcm16",
"output_audio_format": "pcm16",
"input_audio_transcription": {
"model": "<string>",
"language": "<string>",
"prompt": "<string>"
},
"turn_detection": {
"type": "server_vad",
"eagerness": "auto",
"threshold": 123,
"prefix_padding_ms": 123,
"silence_duration_ms": 123,
"create_response": true,
"interrupt_response": true
},
"input_audio_noise_reduction": null,
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {}
}
],
"tool_choice": "auto",
"temperature": 0.8,
"max_response_output_tokens": 123
}'
Copy
Ask AI
{
"client_secret": {
"value": "<string>",
"expires_at": 123
},
"modalities": [
"text"
],
"instructions": "<string>",
"voice": "ash",
"input_audio_format": "<string>",
"output_audio_format": "<string>",
"input_audio_transcription": {
"model": "<string>"
},
"turn_detection": {
"type": "<string>",
"threshold": 123,
"prefix_padding_ms": 123,
"silence_duration_ms": 123
},
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {}
}
],
"tool_choice": "<string>",
"temperature": 123,
"max_response_output_tokens": 123
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
application/json
Create an ephemeral API key with the given session configuration.
Realtime session object configuration.
Response
200 - application/json
Session created successfully.
A new Realtime session configuration, with an ephermeral key. Default TTL for keys is one minute.
Was this page helpful?
Copy
Ask AI
curl --request POST \
--url https://api.openai.com/v1/realtime/sessions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"modalities": [
[
"text",
"audio"
]
],
"model": "gpt-4o-realtime-preview",
"instructions": "<string>",
"voice": "ash",
"input_audio_format": "pcm16",
"output_audio_format": "pcm16",
"input_audio_transcription": {
"model": "<string>",
"language": "<string>",
"prompt": "<string>"
},
"turn_detection": {
"type": "server_vad",
"eagerness": "auto",
"threshold": 123,
"prefix_padding_ms": 123,
"silence_duration_ms": 123,
"create_response": true,
"interrupt_response": true
},
"input_audio_noise_reduction": null,
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {}
}
],
"tool_choice": "auto",
"temperature": 0.8,
"max_response_output_tokens": 123
}'
Copy
Ask AI
{
"client_secret": {
"value": "<string>",
"expires_at": 123
},
"modalities": [
"text"
],
"instructions": "<string>",
"voice": "ash",
"input_audio_format": "<string>",
"output_audio_format": "<string>",
"input_audio_transcription": {
"model": "<string>"
},
"turn_detection": {
"type": "<string>",
"threshold": 123,
"prefix_padding_ms": 123,
"silence_duration_ms": 123
},
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {}
}
],
"tool_choice": "<string>",
"temperature": 123,
"max_response_output_tokens": 123
}
Assistant
Responses are generated using AI and may contain mistakes.