/
OP
openai
/
OpenAI API
Search skmtc…
⌘K
Docs
Sign in
Sign in
APIs
Generators
Stacks
Projects
Docs
History
Schema
Sources
Checked 2h ago · Updated 17h ago
View markdown
openai
OpenAI API
post
Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.
63028c4d3916
latest
OpenAPI 3.1.0
MIT
raw.githubusercontent.com
2026-08-12
288
1,394
2.7 MB
Assistants
23
Audio
9
Audit Logs
1
Batch
4
Certificates
10
Chat
6
Completions
1
Conversations
8
Data retention
4
Embeddings
1
Evals
12
Files
5
Fine-tuning
13
Group organization role assignments
4
Group users
4
Groups
5
Hosted tools
2
Images
3
Invites
4
Models
3
Moderations
1
Project group role assignments
4
Project groups
4
Project user role assignments
4
Projects
23
Realtime
9
post
Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.
post
Accept an incoming SIP call and configure the realtime session that will handle it.
post
End an active Realtime API call, whether it was initiated over SIP or WebRTC.
post
Transfer an active SIP call to a new destination using the SIP REFER verb.
post
Decline an incoming SIP call by returning a SIP status code to the caller.
post
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](/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
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
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
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`.
Responses
10
Roles
10
Skills
11
Spend alerts
10
Uploads
4
Usage
11
User organization role assignments
4
Users
4
Vector stores
16
Videos
10
get
List Containers
post
Create Container
get
Retrieve Container
delete
Delete Container
get
List Container files
post
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.
get
Retrieve Container File
delete
Delete Container File
get
Retrieve Container File Content
get
List organization API keys
post
Create an organization admin API key
get
Retrieve a single organization API key
delete
Delete an organization admin API key
get
Get the organization's hard spend limit.
post
Create or replace the organization's hard spend limit.
delete
Delete the organization's hard spend limit.
get
Get a project's hard spend limit.
post
Create or replace a project's hard spend limit.
delete
Delete a project's hard spend limit.
post
Creates an API key for a service account in the project.
post
Check whether an image or audio file contains known OpenAI provenance signals. [Learn more about content provenance](/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
Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.
post
Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](/docs/guides/conversation-state#compaction-advanced).
post
Cancel an active ChatKit session and return its most recent metadata. Cancelling prevents new requests from using the issued client secret.
post
Create a ChatKit session.
get
List items that belong to a ChatKit thread.
get
Retrieve a ChatKit thread by its identifier.
delete
Delete a ChatKit thread along with its items and stored attachments.
get
List ChatKit threads with optional pagination and user filters.
post
Compact a conversation. Returns a compacted response object. Learn when and how to compact long-running conversations in the [conversation state guide](/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](/docs/guides/conversation-state#compaction-advanced).
post
Returns input token counts of the request. Returns an object with `object` set to `response.input_tokens` and an `input_tokens` count.
Webhooks
post
batch_cancelled
post
batch_completed
post
batch_expired
post
batch_failed
post
eval_run_canceled
post
eval_run_failed
post
eval_run_succeeded
post
fine_tuning_job_cancelled
post
fine_tuning_job_failed
post
fine_tuning_job_succeeded
post
live_call_incoming
post
realtime_call_incoming
post
response_cancelled
post
response_completed
post
response_failed
post
response_incomplete
Realtime
Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.
post
/realtime/calls
Response
Realtime call created successfully.