openapi: 3.0.0
info:
  title: OpenAI Assistants Realtime API
  description: The Assistants API allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries. The Assistants API currently supports three types of tools - Code Interpreter, Retrieval, and Function calling. In the future, we plan to release more OpenAI-built tools, and allow you to provide your own tools on our platform.
  version: 2.0.0
  termsOfService: https://openai.com/policies/terms-of-use
  contact:
    name: OpenAI Support
    url: https://help.openai.com/
  license:
    name: MIT
    url: https://github.com/openai/openai-openapi/blob/master/LICENSE
servers:
- url: https://api.openai.com/v1
security:
- ApiKeyAuth: []
tags:
- name: Realtime
paths:
  /realtime/calls:
    post:
      summary: 'Create a new Realtime API call over WebRTC and receive the SDP answer needed

        to complete the peer connection.'
      operationId: create-realtime-call
      tags:
      - Realtime
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/RealtimeCallCreateRequest'
            encoding:
              sdp:
                contentType: application/sdp
              session:
                contentType: application/json
          application/sdp:
            schema:
              type: string
              description: 'WebRTC SDP offer. Use this variant when you have previously created an

                ephemeral **session token** and are authenticating the request with it.

                Realtime session parameters will be retrieved from the session token.'
      responses:
        '201':
          description: Realtime call created successfully.
          headers:
            Location:
              description: Relative URL containing the call ID for subsequent control requests.
              schema:
                type: string
          content:
            application/sdp:
              schema:
                type: string
                description: SDP answer produced by OpenAI for the peer connection.
      x-oaiMeta:
        name: Create call
        group: realtime
        returns: 'Returns `201 Created` with the SDP answer in the response body. The

          `Location` response header includes the call ID for follow-up requests,

          e.g., establishing a monitoring WebSocket or hanging up the call.'
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/calls \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"sdp=<offer.sdp;type=application/sdp\" \\\n  -F 'session={\"type\":\"realtime\",\"model\":\"gpt-realtime\"};type=application/json'"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\ncall = client.realtime.calls.create(\n    sdp=\"sdp\",\n)\nprint(call)\ncontent = call.read()\nprint(content)"
          response: 'v=0

            o=- 4227147428 1719357865 IN IP4 127.0.0.1

            s=-

            c=IN IP4 0.0.0.0

            t=0 0

            a=group:BUNDLE 0 1

            a=msid-semantic:WMS *

            a=fingerprint:sha-256 CA:92:52:51:B4:91:3B:34:DD:9C:0B:FB:76:19:7E:3B:F1:21:0F:32:2C:38:01:72:5D:3F:78:C7:5F:8B:C7:36

            m=audio 9 UDP/TLS/RTP/SAVPF 111 0 8

            a=mid:0

            a=ice-ufrag:kZ2qkHXX/u11

            a=ice-pwd:uoD16Di5OGx3VbqgA3ymjEQV2kwiOjw6

            a=setup:active

            a=rtcp-mux

            a=rtpmap:111 opus/48000/2

            a=candidate:993865896 1 udp 2130706431 4.155.146.196 3478 typ host ufrag kZ2qkHXX/u11

            a=candidate:1432411780 1 tcp 1671430143 4.155.146.196 443 typ host tcptype passive ufrag kZ2qkHXX/u11

            m=application 9 UDP/DTLS/SCTP webrtc-datachannel

            a=mid:1

            a=sctp-port:5000'
  /realtime/calls/{call_id}/accept:
    post:
      summary: 'Accept an incoming SIP call and configure the realtime session that will

        handle it.'
      operationId: accept-realtime-call
      tags:
      - Realtime
      parameters:
      - in: path
        name: call_id
        required: true
        schema:
          type: string
        description: 'The identifier for the call provided in the

          [`realtime.call.incoming`](/docs/api-reference/webhook-events/realtime/call/incoming)

          webhook.'
      requestBody:
        required: true
        description: Session configuration to apply before the caller is bridged to the model.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeSessionCreateRequestGA'
      responses:
        '200':
          description: Call accepted successfully.
      x-oaiMeta:
        name: Accept call
        group: realtime-calls
        returns: 'Returns `200 OK` once OpenAI starts ringing the SIP leg with the supplied

          session configuration.'
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/accept \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n        \"type\": \"realtime\",\n        \"model\": \"gpt-realtime\",\n        \"instructions\": \"You are Alex, a friendly concierge for Example Corp.\",\n      }'"
            node.js: "import OpenAI from 'openai';\n\nconst client = new OpenAI({\n  apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted\n});\n\nawait client.realtime.calls.accept('call_id', { type: 'realtime' });"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\nclient.realtime.calls.accept(\n    call_id=\"call_id\",\n    type=\"realtime\",\n)"
            go: "package main\n\nimport (\n\t\"context\"\n\n\t\"github.com/openai/openai-go\"\n\t\"github.com/openai/openai-go/option\"\n\t\"github.com/openai/openai-go/realtime\"\n)\n\nfunc main() {\n\tclient := openai.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\terr := client.Realtime.Calls.Accept(\n\t\tcontext.TODO(),\n\t\t\"call_id\",\n\t\trealtime.CallAcceptParams{\n\t\t\tRealtimeSessionCreateRequest: realtime.RealtimeSessionCreateRequestParam{},\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n}\n"
            java: "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.realtime.RealtimeSessionCreateRequest;\nimport com.openai.models.realtime.calls.CallAcceptParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        CallAcceptParams params = CallAcceptParams.builder()\n            .callId(\"call_id\")\n            .realtimeSessionCreateRequest(RealtimeSessionCreateRequest.builder().build())\n            .build();\n        client.realtime().calls().accept(params);\n    }\n}"
            ruby: 'require "openai"


              openai = OpenAI::Client.new(api_key: "My API Key")


              result = openai.realtime.calls.accept("call_id", type: :realtime)


              puts(result)'
          response: ''
  /realtime/calls/{call_id}/hangup:
    post:
      summary: 'End an active Realtime API call, whether it was initiated over SIP or

        WebRTC.'
      operationId: hangup-realtime-call
      tags:
      - Realtime
      parameters:
      - in: path
        name: call_id
        required: true
        schema:
          type: string
        description: 'The identifier for the call. For SIP calls, use the value provided in the

          [`realtime.call.incoming`](/docs/api-reference/webhook-events/realtime/call/incoming)

          webhook. For WebRTC sessions, reuse the call ID returned in the `Location`

          header when creating the call with

          [`POST /v1/realtime/calls`](/docs/api-reference/realtime/create-call).'
      responses:
        '200':
          description: Call hangup initiated successfully.
      x-oaiMeta:
        name: Hang up call
        group: realtime-calls
        returns: Returns `200 OK` when OpenAI begins terminating the realtime call.
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/hangup \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\""
            node.js: "import OpenAI from 'openai';\n\nconst client = new OpenAI({\n  apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted\n});\n\nawait client.realtime.calls.hangup('call_id');"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\nclient.realtime.calls.hangup(\n    \"call_id\",\n)"
            go: "package main\n\nimport (\n\t\"context\"\n\n\t\"github.com/openai/openai-go\"\n\t\"github.com/openai/openai-go/option\"\n)\n\nfunc main() {\n\tclient := openai.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\terr := client.Realtime.Calls.Hangup(context.TODO(), \"call_id\")\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n}\n"
            java: "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.realtime.calls.CallHangupParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        client.realtime().calls().hangup(\"call_id\");\n    }\n}"
            ruby: 'require "openai"


              openai = OpenAI::Client.new(api_key: "My API Key")


              result = openai.realtime.calls.hangup("call_id")


              puts(result)'
          response: ''
  /realtime/calls/{call_id}/refer:
    post:
      summary: Transfer an active SIP call to a new destination using the SIP REFER verb.
      operationId: refer-realtime-call
      tags:
      - Realtime
      parameters:
      - in: path
        name: call_id
        required: true
        schema:
          type: string
        description: 'The identifier for the call provided in the

          [`realtime.call.incoming`](/docs/api-reference/webhook-events/realtime/call/incoming)

          webhook.'
      requestBody:
        required: true
        description: Destination URI for the REFER request.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeCallReferRequest'
      responses:
        '200':
          description: Call referred successfully.
      x-oaiMeta:
        name: Refer call
        group: realtime-calls
        returns: Returns `200 OK` once the REFER is handed off to your SIP provider.
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/refer \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"target_uri\": \"tel:+14155550123\"}'"
            node.js: "import OpenAI from 'openai';\n\nconst client = new OpenAI({\n  apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted\n});\n\nawait client.realtime.calls.refer('call_id', { target_uri: 'tel:+14155550123' });"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\nclient.realtime.calls.refer(\n    call_id=\"call_id\",\n    target_uri=\"tel:+14155550123\",\n)"
            go: "package main\n\nimport (\n\t\"context\"\n\n\t\"github.com/openai/openai-go\"\n\t\"github.com/openai/openai-go/option\"\n\t\"github.com/openai/openai-go/realtime\"\n)\n\nfunc main() {\n\tclient := openai.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\terr := client.Realtime.Calls.Refer(\n\t\tcontext.TODO(),\n\t\t\"call_id\",\n\t\trealtime.CallReferParams{\n\t\t\tTargetUri: \"tel:+14155550123\",\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n}\n"
            java: "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.realtime.calls.CallReferParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        CallReferParams params = CallReferParams.builder()\n            .callId(\"call_id\")\n            .targetUri(\"tel:+14155550123\")\n            .build();\n        client.realtime().calls().refer(params);\n    }\n}"
            ruby: 'require "openai"


              openai = OpenAI::Client.new(api_key: "My API Key")


              result = openai.realtime.calls.refer("call_id", target_uri: "tel:+14155550123")


              puts(result)'
          response: ''
  /realtime/calls/{call_id}/reject:
    post:
      summary: Decline an incoming SIP call by returning a SIP status code to the caller.
      operationId: reject-realtime-call
      tags:
      - Realtime
      parameters:
      - in: path
        name: call_id
        required: true
        schema:
          type: string
        description: 'The identifier for the call provided in the

          [`realtime.call.incoming`](/docs/api-reference/webhook-events/realtime/call/incoming)

          webhook.'
      requestBody:
        required: false
        description: 'Provide an optional SIP status code. When omitted the API responds with

          `603 Decline`.'
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeCallRejectRequest'
      responses:
        '200':
          description: Call rejected successfully.
      x-oaiMeta:
        name: Reject call
        group: realtime-calls
        returns: Returns `200 OK` after OpenAI sends the SIP status code to the caller.
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/reject \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"status_code\": 486}'"
            node.js: "import OpenAI from 'openai';\n\nconst client = new OpenAI({\n  apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted\n});\n\nawait client.realtime.calls.reject('call_id');"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\nclient.realtime.calls.reject(\n    call_id=\"call_id\",\n)"
            go: "package main\n\nimport (\n\t\"context\"\n\n\t\"github.com/openai/openai-go\"\n\t\"github.com/openai/openai-go/option\"\n\t\"github.com/openai/openai-go/realtime\"\n)\n\nfunc main() {\n\tclient := openai.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\terr := client.Realtime.Calls.Reject(\n\t\tcontext.TODO(),\n\t\t\"call_id\",\n\t\trealtime.CallRejectParams{},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n}\n"
            java: "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.realtime.calls.CallRejectParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        client.realtime().calls().reject(\"call_id\");\n    }\n}"
            ruby: 'require "openai"


              openai = OpenAI::Client.new(api_key: "My API Key")


              result = openai.realtime.calls.reject("call_id")


              puts(result)'
          response: ''
  /realtime/client_secrets:
    post:
      summary: '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`.

        '
      operationId: create-realtime-client-secret
      tags:
      - Realtime
      requestBody:
        description: Create a client secret with the given session configuration.
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeCreateClientSecretRequest'
      responses:
        '200':
          description: Client secret created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RealtimeCreateClientSecretResponse'
      x-oaiMeta:
        name: Create client secret
        group: realtime
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/client_secrets \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"expires_after\": {\n      \"anchor\": \"created_at\",\n      \"seconds\": 600\n    },\n    \"session\": {\n      \"type\": \"realtime\",\n      \"model\": \"gpt-realtime\",\n      \"instructions\": \"You are a friendly assistant.\"\n    }\n  }'\n"
            node.js: "import OpenAI from 'openai';\n\nconst client = new OpenAI({\n  apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted\n});\n\nconst clientSecret = await client.realtime.clientSecrets.create();\n\nconsole.log(clientSecret.expires_at);"
            python: "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=os.environ.get(\"OPENAI_API_KEY\"),  # This is the default and can be omitted\n)\nclient_secret = client.realtime.client_secrets.create()\nprint(client_secret.expires_at)"
            go: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/openai/openai-go\"\n\t\"github.com/openai/openai-go/option\"\n\t\"github.com/openai/openai-go/realtime\"\n)\n\nfunc main() {\n\tclient := openai.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tclientSecret, err := client.Realtime.ClientSecrets.New(context.TODO(), realtime.ClientSecretNewParams{})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", clientSecret.ExpiresAt)\n}\n"
            java: "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.realtime.clientsecrets.ClientSecretCreateParams;\nimport com.openai.models.realtime.clientsecrets.ClientSecretCreateResponse;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ClientSecretCreateResponse clientSecret = client.realtime().clientSecrets().create();\n    }\n}"
            ruby: 'require "openai"


              openai = OpenAI::Client.new(api_key: "My API Key")


              client_secret = openai.realtime.client_secrets.create


              puts(client_secret)'
          response: "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"model\": \"gpt-realtime\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"You are a friendly assistant.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"truncation\": \"auto\",\n    \"prompt\": null,\n    \"expires_at\": 0,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n      }\n    },\n    \"include\": null\n  }\n}\n"
  /realtime/sessions:
    post:
      summary: '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.

        '
      operationId: create-realtime-session
      tags:
      - Realtime
      requestBody:
        description: Create an ephemeral API key with the given session configuration.
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeSessionCreateRequest'
      responses:
        '200':
          description: Session created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RealtimeSessionCreateResponse'
      x-oaiMeta:
        name: Create session
        group: realtime
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/sessions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"gpt-realtime\",\n    \"modalities\": [\"audio\", \"text\"],\n    \"instructions\": \"You are a friendly assistant.\"\n  }'\n"
          response: "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"model\": \"gpt-realtime-2025-08-25\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"voice\": \"alloy\",\n  \"input_audio_format\": \"pcm16\",\n  \"output_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n      \"model\": \"whisper-1\"\n  },\n  \"turn_detection\": null,\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"temperature\": 0.7,\n  \"max_response_output_tokens\": 200,\n  \"speed\": 1.1,\n  \"tracing\": \"auto\",\n  \"client_secret\": {\n    \"value\": \"ek_abc123\", \n    \"expires_at\": 1234567890\n  }\n}\n"
  /realtime/transcription_sessions:
    post:
      summary: "Create an ephemeral API token for use in client-side applications with the\nRealtime API specifically for realtime transcriptions. \nCan be configured with the same session parameters as the `transcription_session.update` client event.\n\nIt responds with a session object, plus a `client_secret` key which contains\na usable ephemeral API token that can be used to authenticate browser clients\nfor the Realtime API.\n\nReturns the created Realtime transcription session object, plus an ephemeral key.\n"
      operationId: create-realtime-transcription-session
      tags:
      - Realtime
      requestBody:
        description: Create an ephemeral API key with the given session configuration.
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeTranscriptionSessionCreateRequest'
      responses:
        '200':
          description: Session created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RealtimeTranscriptionSessionCreateResponse'
      x-oaiMeta:
        name: Create transcription session
        group: realtime
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/transcription_sessions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{}'\n"
          response: "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"object\": \"realtime.transcription_session\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"turn_detection\": {\n    \"type\": \"server_vad\",\n    \"threshold\": 0.5,\n    \"prefix_padding_ms\": 300,\n    \"silence_duration_ms\": 200\n  },\n  \"input_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n    \"model\": \"gpt-4o-transcribe\",\n    \"language\": null,\n    \"prompt\": \"\"\n  },\n  \"client_secret\": null\n}\n"
  /realtime/translations/client_secrets:
    post:
      summary: '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`.

        '
      operationId: create-realtime-translation-client-secret
      tags:
      - Realtime
      requestBody:
        description: Create a client secret with the given translation session configuration.
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RealtimeTranslationClientSecretCreateRequest'
      responses:
        '200':
          description: Translation client secret created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RealtimeTranslationClientSecretCreateResponse'
      x-oaiMeta:
        name: Create translation client secret
        group: realtime
        examples:
          request:
            curl: "curl -X POST https://api.openai.com/v1/realtime/translations/client_secrets \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"expires_after\": {\n      \"anchor\": \"created_at\",\n      \"seconds\": 600\n    },\n    \"session\": {\n      \"model\": \"gpt-realtime-translate\",\n      \"audio\": {\n        \"input\": {\n          \"transcription\": {\n            \"model\": \"gpt-realtime-whisper\"\n          },\n          \"noise_reduction\": null\n        },\n        \"output\": {\n          \"language\": \"es\"\n        }\n      }\n    }\n  }'\n"
          response: "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"type\": \"translation\",\n    \"expires_at\": 1756310470,\n    \"model\": \"gpt-realtime-translate\",\n    \"audio\": {\n      \"input\": {\n        \"transcription\": {\n          \"model\": \"gpt-realtime-whisper\"\n        },\n        \"noise_reduction\": null\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
components:
  schemas:
    VoiceIdsShared:
      example: ash
      anyOf:
      - type: string
      - type: string
        enum:
        - alloy
        - ash
        - ballad
        - coral
        - echo
        - sage
        - shimmer
        - verse
        - marin
        - cedar
    AudioTranscription:
      type: object
      properties:
        model:
          description: 'The model to use for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels.

            '
          anyOf:
          - type: string
          - type: string
            enum:
            - whisper-1
            - gpt-4o-mini-transcribe
            - gpt-4o-mini-transcribe-2025-12-15
            - gpt-4o-transcribe
            - gpt-4o-transcribe-diarize
            - gpt-realtime-whisper
        language:
          type: string
          description: 'The language of the input audio. Supplying the input language in

            [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format

            will improve accuracy and latency.

            '
        prompt:
          type: string
          description: 'An optional text to guide the model''s style or continue a previous audio

            segment.

            For `whisper-1`, the [prompt is a list of keywords](/docs/guides/speech-to-text#prompting).

            For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology".

            Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions.

            '
        delay:
          type: string
          description: 'Controls how long the model waits before emitting transcription text.

            Higher values can improve transcription accuracy at the cost of latency.

            Only supported with `gpt-realtime-whisper` in GA Realtime sessions.

            '
          enum:
          - minimal
          - low
          - medium
          - high
          - xhigh
    RealtimeTranscriptionSessionCreateResponseGA:
      type: object
      title: Realtime transcription session configuration object
      description: 'A Realtime transcription session configuration object.

        '
      properties:
        type:
          type: string
          description: 'The type of session. Always `transcription` for transcription sessions.

            '
          enum:
          - transcription
          x-stainless-const: true
        id:
          type: string
          description: 'Unique identifier for the session that looks like `sess_1234567890abcdef`.

            '
        object:
          type: string
          description: The object type. Always `realtime.transcription_session`.
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the session, in seconds since epoch.
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'Additional fields to include in server outputs.

            - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.

            '
        audio:
          type: object
          description: 'Configuration for input audio for the session.

            '
          properties:
            input:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                transcription:
                  description: 'Configuration of the transcription model.

                    '
                  $ref: '#/components/schemas/AudioTranscriptionResponse'
                noise_reduction:
                  type: object
                  description: 'Configuration for input audio noise reduction.

                    '
                  properties:
                    type:
                      $ref: '#/components/schemas/NoiseReductionType'
                turn_detection:
                  description: 'Configuration for turn detection. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported.

                    '
                  anyOf:
                  - type: object
                    description: '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. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported.

                      '
                    properties:
                      type:
                        type: string
                        description: 'Type of turn detection, only `server_vad` is currently supported.

                          '
                      threshold:
                        type: number
                        description: 'Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                          higher threshold will require louder audio to activate the model, and

                          thus might perform better in noisy environments.

                          '
                      prefix_padding_ms:
                        type: integer
                        description: 'Amount of audio to include before the VAD detected speech (in

                          milliseconds). Defaults to 300ms.

                          '
                      silence_duration_ms:
                        type: integer
                        description: 'Duration of silence to detect speech stop (in milliseconds). Defaults

                          to 500ms. With shorter values the model will respond more quickly,

                          but may jump in on short pauses from the user.

                          '
                  - type: 'null'
      required:
      - type
      - id
      - object
      x-oaiMeta:
        name: The transcription session object
        group: realtime
        example: "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"type\": \"transcription\",\n  \"object\": \"realtime.transcription_session\",\n  \"expires_at\": 1742188264,\n  \"include\": [\"item.input_audio_transcription.logprobs\"],\n  \"audio\": {\n    \"input\": {\n      \"format\": \"pcm16\",\n      \"transcription\": {\n        \"model\": \"gpt-4o-transcribe\",\n        \"language\": null,\n        \"prompt\": \"\"\n      },\n      \"noise_reduction\": null,\n      \"turn_detection\": {\n        \"type\": \"server_vad\",\n        \"threshold\": 0.5,\n        \"prefix_padding_ms\": 300,\n        \"silence_duration_ms\": 200\n      }\n    }\n  }\n}\n"
    ResponsePromptVariables:
      anyOf:
      - type: object
        title: Prompt Variables
        description: 'Optional map of values to substitute in for variables in your

          prompt. The substitution values can either be strings, or other

          Response input types like images or files.

          '
        x-oaiExpandable: true
        x-oaiTypeLabel: map
        additionalProperties:
          x-oaiExpandable: true
          x-oaiTypeLabel: map
          oneOf:
          - type: string
          - $ref: '#/components/schemas/InputTextContent'
          - $ref: '#/components/schemas/InputImageContent'
          - $ref: '#/components/schemas/InputFileContent'
      - type: 'null'
    AudioTranscriptionResponse:
      type: object
      properties:
        model:
          description: 'The model used for transcription. Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`.

            '
          anyOf:
          - type: string
          - type: string
            enum:
            - whisper-1
            - gpt-4o-mini-transcribe
            - gpt-4o-mini-transcribe-2025-12-15
            - gpt-4o-transcribe
            - gpt-4o-transcribe-diarize
            - gpt-realtime-whisper
        language:
          type: string
          description: 'The language of the input audio.

            '
        prompt:
          type: string
          description: 'The prompt configured for input audio transcription, when present.

            '
    InputTextContent:
      properties:
        type:
          type: string
          enum:
          - input_text
          description: The type of the input item. Always `input_text`.
          default: input_text
          x-stainless-const: true
        text:
          type: string
          description: The text input to the model.
      type: object
      required:
      - type
      - text
      title: Input text
      description: A text input to the model.
    RealtimeAudioFormats:
      anyOf:
      - type: object
        title: PCM audio format
        description: The PCM audio format. Only a 24kHz sample rate is supported.
        properties:
          type:
            type: string
            description: The audio format. Always `audio/pcm`.
            enum:
            - audio/pcm
          rate:
            type: integer
            description: The sample rate of the audio. Always `24000`.
            enum:
            - 24000
      - type: object
        title: PCMU audio format
        description: The G.711 μ-law format.
        properties:
          type:
            type: string
            description: The audio format. Always `audio/pcmu`.
            enum:
            - audio/pcmu
      - type: object
        title: PCMA audio format
        description: The G.711 A-law format.
        properties:
          type:
            type: string
            description: The audio format. Always `audio/pcma`.
            enum:
            - audio/pcma
    RealtimeFunctionTool:
      type: object
      title: Function tool
      properties:
        type:
          type: string
          enum:
          - function
          description: The type of the tool, i.e. `function`.
          x-stainless-const: true
        name:
          type: string
          description: The name of the function.
        description:
          type: string
          description: 'The description of the function, including guidance on when and how

            to call it, and guidance about what to tell the user when calling

            (if anything).

            '
        parameters:
          type: object
          description: Parameters of the function in JSON Schema.
    RealtimeCallCreateRequest:
      title: Realtime call creation request
      type: object
      description: 'Parameters required to initiate a realtime call and receive the SDP answer

        needed to complete a WebRTC peer connection. Provide an SDP offer generated

        by your client and optionally configure the session that will answer the call.'
      required:
      - sdp
      properties:
        sdp:
          type: string
          description: WebRTC Session Description Protocol (SDP) offer generated by the caller.
        session:
          title: Session configuration
          allOf:
          - $ref: '#/components/schemas/RealtimeSessionCreateRequestGA'
          description: 'Optional session configuration to apply before the realtime session is

            created. Use the same parameters you would send in a [`create client secret`](/docs/api-reference/realtime-sessions/create-realtime-client-secret)

            request.'
      additionalProperties: false
    RealtimeTranslationSessionCreateRequest:
      type: object
      title: Realtime translation session configuration
      description: 'Realtime translation session configuration. Translation sessions stream source

        audio in and translated audio plus transcript deltas out continuously.

        '
      properties:
        model:
          type: string
          description: 'The Realtime translation model used for this session.

            '
        audio:
          type: object
          description: 'Configuration for translation input and output audio.

            '
          properties:
            input:
              type: object
              properties:
                transcription:
                  anyOf:
                  - type: object
                    description: 'Optional source-language transcription. When configured, the server emits

                      `session.input_transcript.delta` events. Translation itself still runs from

                      the input audio stream.

                      '
                    properties:
                      model:
                        type: string
                        description: The transcription model to use for source transcript deltas.
                    required:
                    - model
                  - type: 'null'
                noise_reduction:
                  anyOf:
                  - type: object
                    description: 'Optional input noise reduction. Set to `null` to disable it.

                      '
                    properties:
                      type:
                        $ref: '#/components/schemas/NoiseReductionType'
                    required:
                    - type
                  - type: 'null'
            output:
              type: object
              properties:
                language:
                  type: string
                  description: 'Target language for translated output audio and transcript deltas.

                    '
      required:
      - model
    NoiseReductionType:
      type: string
      enum:
      - near_field
      - far_field
      description: 'Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones.

        '
    RealtimeCreateClientSecretRequest:
      type: object
      title: Realtime client secret creation request
      description: 'Create a session and client secret for the Realtime API. The request can specify

        either a realtime or a transcription session configuration.

        [Learn more about the Realtime API](/docs/guides/realtime).

        '
      properties:
        expires_after:
          type: object
          title: Client secret expiration
          description: 'Configuration for the client secret expiration. Expiration refers to the time after which

            a client secret will no longer be valid for creating sessions. The session itself may

            continue after that time once started. A secret can be used to create multiple sessions

            until it expires.

            '
          properties:
            anchor:
              type: string
              enum:
              - created_at
              description: 'The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported.

                '
              default: created_at
              x-stainless-const: true
            seconds:
              type: integer
              format: int64
              description: 'The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified.

                '
              minimum: 10
              maximum: 7200
              default: 600
        session:
          title: Session configuration
          description: 'Session configuration to use for the client secret. Choose either a realtime

            session or a transcription session.

            '
          oneOf:
          - $ref: '#/components/schemas/RealtimeSessionCreateRequestGA'
          - $ref: '#/components/schemas/RealtimeTranscriptionSessionCreateRequestGA'
    RealtimeTruncation:
      title: Realtime Truncation Controls
      description: 'When the number of tokens in a conversation exceeds the model''s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model''s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.


        Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.


        Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.


        Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model''s input token limit.

        '
      oneOf:
      - type: string
        description: The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit.
        enum:
        - auto
        - disabled
      - type: object
        title: Retention ratio truncation
        description: Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.
        properties:
          type:
            type: string
            enum:
            - retention_ratio
            description: Use retention ratio truncation.
            x-stainless-const: true
          retention_ratio:
            type: number
            description: 'Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.

              '
            minimum: 0
            maximum: 1
          token_limits:
            type: object
            description: Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used.
            properties:
              post_instructions:
                type: integer
                description: Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens.
                minimum: 0
        required:
        - type
        - retention_ratio
    RealtimeSessionCreateRequest:
      type: object
      description: 'A new Realtime session configuration, with an ephemeral key. Default TTL

        for keys is one minute.

        '
      properties:
        client_secret:
          type: object
          description: Ephemeral key returned by the API.
          properties:
            value:
              type: string
              description: 'Ephemeral key usable in client environments to authenticate connections

                to the Realtime API. Use this in client-side environments rather than

                a standard API token, which should only be used server-side.

                '
            expires_at:
              type: integer
              format: unixtime
              description: 'Timestamp for when the token expires. Currently, all tokens expire

                after one minute.

                '
          required:
          - value
          - expires_at
        modalities:
          description: 'The set of modalities the model can respond with. To disable audio,

            set this to ["text"].

            '
          items:
            type: string
            enum:
            - text
            - audio
        instructions:
          type: string
          description: '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.

            '
        voice:
          $ref: '#/components/schemas/VoiceIdsOrCustomVoice'
          description: 'The voice the model uses to respond. Supported built-in voices are

            `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,

            `marin`, and `cedar`. You may also provide a custom voice object with an

            `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed during

            the session once the model has responded with audio at least once.

            '
        input_audio_format:
          type: string
          description: 'The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.

            '
        output_audio_format:
          type: string
          description: 'The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.

            '
        input_audio_transcription:
          type: object
          description: '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 and should be treated as rough guidance

            rather than the representation understood by the model.

            '
          properties:
            model:
              type: string
              description: 'The model to use for transcription.

                '
        speed:
          type: number
          default: 1
          maximum: 1.5
          minimum: 0.25
          description: 'The speed of the model''s spoken response. 1.0 is the default speed. 0.25 is

            the minimum speed. 1.5 is the maximum speed. This value can only be changed

            in between model turns, not while a response is in progress.

            '
        tracing:
          title: Tracing Configuration
          description: 'Configuration options for tracing. Set to null to disable tracing. Once

            tracing is enabled for a session, the configuration cannot be modified.


            `auto` will create a trace for the session with default values for the

            workflow name, group id, and metadata.

            '
          oneOf:
          - type: string
            default: auto
            description: 'Default tracing mode for the session.

              '
            enum:
            - auto
            x-stainless-const: true
          - type: object
            title: Tracing Configuration
            description: 'Granular configuration for tracing.

              '
            properties:
              workflow_name:
                type: string
                description: 'The name of the workflow to attach to this trace. This is used to

                  name the trace in the traces dashboard.

                  '
              group_id:
                type: string
                description: 'The group id to attach to this trace to enable filtering and

                  grouping in the traces dashboard.

                  '
              metadata:
                type: object
                description: 'The arbitrary metadata to attach to this trace to enable

                  filtering in the traces dashboard.

                  '
        turn_detection:
          type: object
          description: '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.

            '
          properties:
            type:
              type: string
              description: 'Type of turn detection, only `server_vad` is currently supported.

                '
            threshold:
              type: number
              description: 'Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                higher threshold will require louder audio to activate the model, and

                thus might perform better in noisy environments.

                '
            prefix_padding_ms:
              type: integer
              description: 'Amount of audio to include before the VAD detected speech (in

                milliseconds). Defaults to 300ms.

                '
            silence_duration_ms:
              type: integer
              description: 'Duration of silence to detect speech stop (in milliseconds). Defaults

                to 500ms. With shorter values the model will respond more quickly,

                but may jump in on short pauses from the user.

                '
        tools:
          type: array
          description: Tools (functions) available to the model.
          items:
            type: object
            properties:
              type:
                type: string
                enum:
                - function
                description: The type of the tool, i.e. `function`.
                x-stainless-const: true
              name:
                type: string
                description: The name of the function.
              description:
                type: string
                description: 'The description of the function, including guidance on when and how

                  to call it, and guidance about what to tell the user when calling

                  (if anything).

                  '
              parameters:
                type: object
                description: Parameters of the function in JSON Schema.
        tool_choice:
          type: string
          description: 'How the model chooses tools. Options are `auto`, `none`, `required`, or

            specify a function.

            '
        temperature:
          type: number
          description: 'Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.

            '
        max_response_output_tokens:
          oneOf:
          - type: integer
          - type: string
            enum:
            - inf
            x-stainless-const: true
          description: 'Maximum 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`.

            '
        truncation:
          $ref: '#/components/schemas/RealtimeTruncation'
        prompt:
          $ref: '#/components/schemas/Prompt'
      required:
      - client_secret
      x-oaiMeta:
        name: The session object
        group: realtime
        example: "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"model\": \"gpt-realtime-2025-08-25\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"voice\": \"alloy\",\n  \"input_audio_format\": \"pcm16\",\n  \"output_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n      \"model\": \"whisper-1\"\n  },\n  \"turn_detection\": null,\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"temperature\": 0.7,\n  \"speed\": 1.1,\n  \"tracing\": \"auto\",\n  \"max_response_output_tokens\": 200,\n  \"truncation\": \"auto\",\n  \"prompt\": null,\n  \"client_secret\": {\n    \"value\": \"ek_abc123\",\n    \"expires_at\": 1234567890\n  }\n}\n"
    RealtimeSessionCreateResponseGA:
      type: object
      title: Realtime session configuration object
      description: 'A Realtime session configuration object.

        '
      properties:
        type:
          type: string
          description: 'The type of session to create. Always `realtime` for the Realtime API.

            '
          enum:
          - realtime
          x-stainless-const: true
        id:
          type: string
          description: 'Unique identifier for the session that looks like `sess_1234567890abcdef`.

            '
        object:
          type: string
          description: The object type. Always `realtime.session`.
          enum:
          - realtime.session
          x-stainless-const: true
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the session, in seconds since epoch.
        output_modalities:
          type: array
          description: 'The set of modalities the model can respond with. It defaults to `["audio"]`, indicating

            that the model will respond with audio plus a transcript. `["text"]` can be used to make

            the model respond with text only. It is not possible to request both `text` and `audio` at the same time.

            '
          default:
          - audio
          items:
            type: string
            enum:
            - text
            - audio
        model:
          anyOf:
          - type: string
          - type: string
            enum:
            - gpt-realtime
            - gpt-realtime-1.5
            - gpt-realtime-2
            - gpt-realtime-2025-08-28
            - gpt-4o-realtime-preview
            - gpt-4o-realtime-preview-2024-10-01
            - gpt-4o-realtime-preview-2024-12-17
            - gpt-4o-realtime-preview-2025-06-03
            - gpt-4o-mini-realtime-preview
            - gpt-4o-mini-realtime-preview-2024-12-17
            - gpt-realtime-mini
            - gpt-realtime-mini-2025-10-06
            - gpt-realtime-mini-2025-12-15
            - gpt-audio-1.5
            - gpt-audio-mini
            - gpt-audio-mini-2025-10-06
            - gpt-audio-mini-2025-12-15
          description: 'The Realtime model used for this session.

            '
        instructions:
          type: string
          description: '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.

            '
        audio:
          type: object
          description: 'Configuration for input and output audio.

            '
          properties:
            input:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                  description: The format of the input audio.
                transcription:
                  description: '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 [the /audio/transcriptions endpoint](/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

                    '
                  $ref: '#/components/schemas/AudioTranscriptionResponse'
                noise_reduction:
                  type: object
                  default: null
                  description: 'Configuration for input audio noise reduction. This can be set to `null` to turn off.

                    Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.

                    Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

                    '
                  properties:
                    type:
                      $ref: '#/components/schemas/NoiseReductionType'
                turn_detection:
                  $ref: '#/components/schemas/RealtimeTurnDetection'
            output:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                  description: The format of the output audio.
                voice:
                  $ref: '#/components/schemas/VoiceIdsShared'
                  default: alloy
                  description: '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`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for

                    best quality.

                    '
                speed:
                  type: number
                  default: 1
                  maximum: 1.5
                  minimum: 0.25
                  description: 'The speed of the model''s spoken response as a multiple of the original speed.

                    1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.


                    This parameter is a post-processing adjustment to the audio after it is generated, it''s

                    also possible to prompt the model to speak faster or slower.

                    '
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'Additional fields to include in server outputs.


            `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.

            '
        tracing:
          anyOf:
          - title: Tracing Configuration
            default: null
            description: 'Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once

              tracing is enabled for a session, the configuration cannot be modified.


              `auto` will create a trace for the session with default values for the

              workflow name, group id, and metadata.

              '
            oneOf:
            - type: string
              title: auto
              default: auto
              description: 'Enables tracing and sets default values for tracing configuration options. Always `auto`.

                '
              enum:
              - auto
              x-stainless-const: true
            - type: object
              title: Tracing Configuration
              description: 'Granular configuration for tracing.

                '
              properties:
                workflow_name:
                  type: string
                  description: 'The name of the workflow to attach to this trace. This is used to

                    name the trace in the Traces Dashboard.

                    '
                group_id:
                  type: string
                  description: 'The group id to attach to this trace to enable filtering and

                    grouping in the Traces Dashboard.

                    '
                metadata:
                  type: object
                  description: 'The arbitrary metadata to attach to this trace to enable

                    filtering in the Traces Dashboard.

                    '
          - type: 'null'
        tools:
          type: array
          description: Tools available to the model.
          items:
            oneOf:
            - $ref: '#/components/schemas/RealtimeFunctionTool'
            - $ref: '#/components/schemas/MCPTool'
        tool_choice:
          description: 'How the model chooses tools. Provide one of the string modes or force a specific

            function/MCP tool.

            '
          oneOf:
          - $ref: '#/components/schemas/ToolChoiceOptions'
          - $ref: '#/components/schemas/ToolChoiceFunction'
          - $ref: '#/components/schemas/ToolChoiceMCP'
          default: auto
        reasoning:
          $ref: '#/components/schemas/RealtimeReasoning'
        max_output_tokens:
          oneOf:
          - type: integer
          - type: string
            enum:
            - inf
            x-stainless-const: true
          description: 'Maximum 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`.

            '
        truncation:
          $ref: '#/components/schemas/RealtimeTruncation'
        prompt:
          $ref: '#/components/schemas/Prompt'
      required:
      - type
      - id
      - object
      x-oaiMeta:
        name: The session object
        group: realtime
    RealtimeReasoningEffort:
      type: string
      description: 'Constrains effort on reasoning for reasoning-capable Realtime models such as

        `gpt-realtime-2`.

        '
      enum:
      - minimal
      - low
      - medium
      - high
      - xhigh
      default: low
    FileInputDetail:
      type: string
      enum:
      - low
      - high
    MCPToolFilter:
      type: object
      title: MCP tool filter
      description: 'A filter object to specify which tools are allowed.

        '
      properties:
        tool_names:
          type: array
          title: MCP allowed tools
          items:
            type: string
          description: List of allowed tool names.
        read_only:
          type: boolean
          description: 'Indicates whether or not a tool modifies data or is read-only. If an

            MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),

            it will match this filter.

            '
      required: []
      additionalProperties: false
    ToolChoiceFunction:
      type: object
      title: Function tool
      description: 'Use this option to force the model to call a specific function.

        '
      properties:
        type:
          type: string
          enum:
          - function
          description: For function calling, the type is always `function`.
          x-stainless-const: true
        name:
          type: string
          description: The name of the function to call.
      required:
      - type
      - name
    RealtimeTranscriptionSessionCreateRequest:
      type: object
      title: Realtime transcription session configuration
      description: Realtime transcription session object configuration.
      properties:
        turn_detection:
          type: object
          description: '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.

            '
          properties:
            type:
              type: string
              description: 'Type of turn detection. Only `server_vad` is currently supported for transcription sessions.

                '
              enum:
              - server_vad
            threshold:
              type: number
              description: 'Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                higher threshold will require louder audio to activate the model, and

                thus might perform better in noisy environments.

                '
            prefix_padding_ms:
              type: integer
              description: 'Amount of audio to include before the VAD detected speech (in

                milliseconds). Defaults to 300ms.

                '
            silence_duration_ms:
              type: integer
              description: 'Duration of silence to detect speech stop (in milliseconds). Defaults

                to 500ms. With shorter values the model will respond more quickly,

                but may jump in on short pauses from the user.

                '
        input_audio_noise_reduction:
          type: object
          default: null
          description: 'Configuration for input audio noise reduction. This can be set to `null` to turn off.

            Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.

            Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

            '
          properties:
            type:
              $ref: '#/components/schemas/NoiseReductionType'
        input_audio_format:
          type: string
          default: pcm16
          enum:
          - pcm16
          - g711_ulaw
          - g711_alaw
          description: '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.

            '
        input_audio_transcription:
          description: 'Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

            '
          $ref: '#/components/schemas/AudioTranscription'
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'The set of items to include in the transcription. Current available items are:

            `item.input_audio_transcription.logprobs`

            '
    RealtimeCallRejectRequest:
      title: Realtime call reject request
      type: object
      description: Parameters used to decline an incoming SIP call handled by the Realtime API.
      properties:
        status_code:
          type: integer
          description: 'SIP response code to send back to the caller. Defaults to `603` (Decline)

            when omitted.'
          example: 486
      additionalProperties: false
    RealtimeTranscriptionSessionCreateResponse:
      type: object
      description: 'A new Realtime transcription session configuration.


        When a session is created on the server via REST API, the session object

        also contains an ephemeral key. Default TTL for keys is 10 minutes. This

        property is not present when a session is updated via the WebSocket API.

        '
      properties:
        client_secret:
          type: object
          description: 'Ephemeral key returned by the API. Only present when the session is

            created on the server via REST API.

            '
          properties:
            value:
              type: string
              description: 'Ephemeral key usable in client environments to authenticate connections

                to the Realtime API. Use this in client-side environments rather than

                a standard API token, which should only be used server-side.

                '
            expires_at:
              type: integer
              format: unixtime
              description: 'Timestamp for when the token expires. Currently, all tokens expire

                after one minute.

                '
          required:
          - value
          - expires_at
        modalities:
          description: 'The set of modalities the model can respond with. To disable audio,

            set this to ["text"].

            '
          items:
            type: string
            enum:
            - text
            - audio
        input_audio_format:
          type: string
          description: 'The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.

            '
        input_audio_transcription:
          description: 'Configuration of the transcription model.

            '
          $ref: '#/components/schemas/AudioTranscriptionResponse'
        turn_detection:
          type: object
          description: '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.

            '
          properties:
            type:
              type: string
              description: 'Type of turn detection, only `server_vad` is currently supported.

                '
            threshold:
              type: number
              description: 'Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                higher threshold will require louder audio to activate the model, and

                thus might perform better in noisy environments.

                '
            prefix_padding_ms:
              type: integer
              description: 'Amount of audio to include before the VAD detected speech (in

                milliseconds). Defaults to 300ms.

                '
            silence_duration_ms:
              type: integer
              description: 'Duration of silence to detect speech stop (in milliseconds). Defaults

                to 500ms. With shorter values the model will respond more quickly,

                but may jump in on short pauses from the user.

                '
      required:
      - client_secret
      x-oaiMeta:
        name: The transcription session object
        group: realtime
        example: "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"object\": \"realtime.transcription_session\",\n  \"expires_at\": 1742188264,\n  \"modalities\": [\"audio\", \"text\"],\n  \"turn_detection\": {\n    \"type\": \"server_vad\",\n    \"threshold\": 0.5,\n    \"prefix_padding_ms\": 300,\n    \"silence_duration_ms\": 200\n  },\n  \"input_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n    \"model\": \"gpt-4o-transcribe\",\n    \"language\": null,\n    \"prompt\": \"\"\n  },\n  \"client_secret\": null\n}\n"
    RealtimeTranslationClientSecretCreateRequest:
      type: object
      title: Realtime translation client secret creation request
      description: 'Create a translation session and client secret for the Realtime API.

        '
      properties:
        expires_after:
          type: object
          title: Client secret expiration
          description: 'Configuration for the client secret expiration. Expiration refers to the time after which

            a client secret will no longer be valid for creating sessions. The session itself may

            continue after that time once started. A secret can be used to create multiple sessions

            until it expires.

            '
          properties:
            anchor:
              type: string
              enum:
              - created_at
              description: 'The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported.

                '
              default: created_at
              x-stainless-const: true
            seconds:
              type: integer
              format: int64
              description: 'The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified.

                '
              minimum: 10
              maximum: 7200
              default: 600
        session:
          $ref: '#/components/schemas/RealtimeTranslationSessionCreateRequest'
      required:
      - session
    RealtimeCallReferRequest:
      title: Realtime call refer request
      type: object
      description: 'Parameters required to transfer a SIP call to a new destination using the

        Realtime API.'
      required:
      - target_uri
      properties:
        target_uri:
          type: string
          description: 'URI that should appear in the SIP Refer-To header. Supports values like

            `tel:+14155550123` or `sip:agent@example.com`.'
          example: tel:+14155550123
      additionalProperties: false
    ToolChoiceOptions:
      type: string
      title: Tool choice mode
      description: 'Controls which (if any) tool is called by the model.


        `none` means the model will not call any tool and instead generates a message.


        `auto` means the model can pick between generating a message or calling one or

        more tools.


        `required` means the model must call one or more tools.

        '
      enum:
      - none
      - auto
      - required
    ToolChoiceMCP:
      type: object
      title: MCP tool
      description: 'Use this option to force the model to call a specific tool on a remote MCP server.

        '
      properties:
        type:
          type: string
          enum:
          - mcp
          description: For MCP tools, the type is always `mcp`.
          x-stainless-const: true
        server_label:
          type: string
          description: 'The label of the MCP server to use.

            '
        name:
          anyOf:
          - type: string
            description: 'The name of the tool to call on the server.

              '
          - type: 'null'
      required:
      - type
      - server_label
    RealtimeTranslationSession:
      type: object
      title: Realtime translation session
      description: 'A Realtime translation session. Translation sessions continuously translate input

        audio into the configured output language.

        '
      properties:
        id:
          type: string
          description: 'Unique identifier for the session that looks like `sess_1234567890abcdef`.

            '
        type:
          type: string
          enum:
          - translation
          description: 'The session type. Always `translation` for Realtime translation sessions.

            '
          x-stainless-const: true
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the session, in seconds since epoch.
        model:
          type: string
          description: 'The Realtime translation model used for this session. This field is set at

            session creation and cannot be changed with `session.update`.

            '
        audio:
          type: object
          description: 'Configuration for translation input and output audio.

            '
          properties:
            input:
              type: object
              properties:
                transcription:
                  anyOf:
                  - type: object
                    description: 'Optional source-language transcription. When configured, the server emits

                      `session.input_transcript.delta` events. Translation itself still runs from

                      the input audio stream.

                      '
                    properties:
                      model:
                        type: string
                        description: The transcription model used for source transcript deltas.
                    required:
                    - model
                  - type: 'null'
                noise_reduction:
                  anyOf:
                  - type: object
                    description: 'Optional input noise reduction.

                      '
                    properties:
                      type:
                        $ref: '#/components/schemas/NoiseReductionType'
                    required:
                    - type
                  - type: 'null'
            output:
              type: object
              properties:
                language:
                  type: string
                  description: 'Target language for translated output audio and transcript deltas.

                    '
      required:
      - id
      - type
      - expires_at
      - model
      - audio
      x-oaiMeta:
        name: The translation session object
        group: realtime
        example: "{\n  \"id\": \"sess_C9G5QPteg4UIbotdKLoYQ\",\n  \"type\": \"translation\",\n  \"expires_at\": 1756324625,\n  \"model\": \"gpt-realtime-translate\",\n  \"audio\": {\n    \"input\": {\n      \"transcription\": {\n        \"model\": \"gpt-realtime-whisper\"\n      },\n      \"noise_reduction\": null\n    },\n    \"output\": {\n      \"language\": \"es\"\n    }\n  }\n}\n"
    ImageDetail:
      type: string
      enum:
      - low
      - high
      - auto
      - original
    RealtimeTurnDetection:
      anyOf:
      - title: Realtime Turn Detection
        description: 'Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response.


          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.


          Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.


          For `gpt-realtime-whisper` transcription sessions, turn detection must be

          set to `null`; VAD is not supported.

          '
        oneOf:
        - type: object
          title: Server VAD
          description: Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence.
          required:
          - type
          properties:
            type:
              type: string
              default: server_vad
              const: server_vad
              description: 'Type of turn detection, `server_vad` to turn on simple Server VAD.

                '
            threshold:
              type: number
              description: 'Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                higher threshold will require louder audio to activate the model, and

                thus might perform better in noisy environments.

                '
            prefix_padding_ms:
              type: integer
              description: 'Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in

                milliseconds). Defaults to 300ms.

                '
            silence_duration_ms:
              type: integer
              description: 'Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults

                to 500ms. With shorter values the model will respond more quickly,

                but may jump in on short pauses from the user.

                '
            create_response:
              type: boolean
              default: true
              description: 'Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding.


                If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted.

                '
            interrupt_response:
              type: boolean
              default: true
              description: 'Whether or not to automatically interrupt (cancel) any ongoing response with output to the default

                conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete.


                If both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted.

                '
            idle_timeout_ms:
              anyOf:
              - type: integer
                minimum: 5000
                maximum: 30000
                description: 'Optional timeout after which a model response will be triggered automatically. This is

                  useful for situations in which a long pause from the user is unexpected, such as a phone

                  call. The model will effectively prompt the user to continue the conversation based

                  on the current context.


                  The timeout value will be applied after the last model response''s audio has finished playing,

                  i.e. it''s set to the `response.done` time plus audio playback duration.


                  An `input_audio_buffer.timeout_triggered` event (plus events

                  associated with the Response) will be emitted when the timeout is reached.

                  Idle timeout is currently only supported for `server_vad` mode.

                  '
              - type: 'null'
        - type: object
          title: Semantic VAD
          description: Server-side semantic turn detection which uses a model to determine when the user has finished speaking.
          required:
          - type
          properties:
            type:
              type: string
              const: semantic_vad
              description: 'Type of turn detection, `semantic_vad` to turn on Semantic VAD.

                '
            eagerness:
              type: string
              default: auto
              enum:
              - low
              - medium
              - high
              - auto
              description: 'Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively.

                '
            create_response:
              type: boolean
              default: true
              description: 'Whether or not to automatically generate a response when a VAD stop event occurs.

                '
            interrupt_response:
              type: boolean
              default: true
              description: 'Whether or not to automatically interrupt any ongoing response with output to the default

                conversation (i.e. `conversation` of `auto`) when a VAD start event occurs.

                '
        discriminator:
          propertyName: type
      - type: 'null'
    RealtimeSessionCreateResponse:
      type: object
      title: Realtime session configuration object
      description: 'A Realtime session configuration object.

        '
      properties:
        id:
          type: string
          description: 'Unique identifier for the session that looks like `sess_1234567890abcdef`.

            '
        object:
          type: string
          description: The object type. Always `realtime.session`.
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the session, in seconds since epoch.
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'Additional fields to include in server outputs.

            - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.

            '
        model:
          type: string
          description: The Realtime model used for this session.
        output_modalities:
          description: 'The set of modalities the model can respond with. To disable audio,

            set this to ["text"].

            '
          items:
            type: string
            enum:
            - text
            - audio
        instructions:
          type: string
          description: '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.

            '
        audio:
          type: object
          description: 'Configuration for input and output audio for the session.

            '
          properties:
            input:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                transcription:
                  description: 'Configuration for input audio transcription.

                    '
                  $ref: '#/components/schemas/AudioTranscriptionResponse'
                noise_reduction:
                  type: object
                  description: 'Configuration for input audio noise reduction.

                    '
                  properties:
                    type:
                      $ref: '#/components/schemas/NoiseReductionType'
                turn_detection:
                  type: object
                  description: 'Configuration for turn detection.

                    '
                  properties:
                    type:
                      type: string
                      description: 'Type of turn detection, only `server_vad` is currently supported.

                        '
                    threshold:
                      type: number
                    prefix_padding_ms:
                      type: integer
                    silence_duration_ms:
                      type: integer
            output:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                voice:
                  $ref: '#/components/schemas/VoiceIdsShared'
                speed:
                  type: number
        tracing:
          title: Tracing Configuration
          description: 'Configuration options for tracing. Set to null to disable tracing. Once

            tracing is enabled for a session, the configuration cannot be modified.


            `auto` will create a trace for the session with default values for the

            workflow name, group id, and metadata.

            '
          oneOf:
          - type: string
            default: auto
            description: 'Default tracing mode for the session.

              '
            enum:
            - auto
            x-stainless-const: true
          - type: object
            title: Tracing Configuration
            description: 'Granular configuration for tracing.

              '
            properties:
              workflow_name:
                type: string
                description: 'The name of the workflow to attach to this trace. This is used to

                  name the trace in the traces dashboard.

                  '
              group_id:
                type: string
                description: 'The group id to attach to this trace to enable filtering and

                  grouping in the traces dashboard.

                  '
              metadata:
                type: object
                description: 'The arbitrary metadata to attach to this trace to enable

                  filtering in the traces dashboard.

                  '
        turn_detection:
          type: object
          description: '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.

            '
          properties:
            type:
              type: string
              description: 'Type of turn detection, only `server_vad` is currently supported.

                '
            threshold:
              type: number
              description: 'Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

                higher threshold will require louder audio to activate the model, and

                thus might perform better in noisy environments.

                '
            prefix_padding_ms:
              type: integer
              description: 'Amount of audio to include before the VAD detected speech (in

                milliseconds). Defaults to 300ms.

                '
            silence_duration_ms:
              type: integer
              description: 'Duration of silence to detect speech stop (in milliseconds). Defaults

                to 500ms. With shorter values the model will respond more quickly,

                but may jump in on short pauses from the user.

                '
        tools:
          type: array
          description: Tools (functions) available to the model.
          items:
            $ref: '#/components/schemas/RealtimeFunctionTool'
        tool_choice:
          type: string
          description: 'How the model chooses tools. Options are `auto`, `none`, `required`, or

            specify a function.

            '
        max_output_tokens:
          oneOf:
          - type: integer
          - type: string
            enum:
            - inf
            x-stainless-const: true
          description: 'Maximum 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`.

            '
      x-oaiMeta:
        name: The session object
        group: realtime
        example: "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"expires_at\": 1742188264,\n  \"model\": \"gpt-realtime\",\n  \"output_modalities\": [\"audio\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"max_output_tokens\": \"inf\",\n  \"tracing\": \"auto\",\n  \"truncation\": \"auto\",\n  \"prompt\": null,\n  \"audio\": {\n    \"input\": {\n      \"format\": {\n        \"type\": \"audio/pcm\",\n        \"rate\": 24000\n      },\n      \"transcription\": { \"model\": \"whisper-1\" },\n      \"noise_reduction\": null,\n      \"turn_detection\": null\n    },\n    \"output\": {\n      \"format\": {\n        \"type\": \"audio/pcm\",\n        \"rate\": 24000\n      },\n      \"voice\": \"alloy\",\n      \"speed\": 1.0\n    }\n  }\n}\n"
    VoiceIdsOrCustomVoice:
      title: Voice
      description: 'A built-in voice name or a custom voice reference.

        '
      anyOf:
      - $ref: '#/components/schemas/VoiceIdsShared'
      - type: object
        description: Custom voice reference.
        additionalProperties: false
        required:
        - id
        properties:
          id:
            type: string
            description: The custom voice ID, e.g. `voice_1234`.
            example: voice_1234
    MCPTool:
      type: object
      title: MCP tool
      description: 'Give the model access to additional tools via remote Model Context Protocol

        (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

        '
      properties:
        type:
          type: string
          enum:
          - mcp
          description: The type of the MCP tool. Always `mcp`.
          x-stainless-const: true
        server_label:
          type: string
          description: 'A label for this MCP server, used to identify it in tool calls.

            '
        server_url:
          type: string
          format: uri
          description: 'The URL for the MCP server. One of `server_url` or `connector_id` must be

            provided.

            '
        connector_id:
          type: string
          enum:
          - connector_dropbox
          - connector_gmail
          - connector_googlecalendar
          - connector_googledrive
          - connector_microsoftteams
          - connector_outlookcalendar
          - connector_outlookemail
          - connector_sharepoint
          description: 'Identifier for service connectors, like those available in ChatGPT. One of

            `server_url` or `connector_id` must be provided. Learn more about service

            connectors [here](/docs/guides/tools-remote-mcp#connectors).


            Currently supported `connector_id` values are:


            - Dropbox: `connector_dropbox`

            - Gmail: `connector_gmail`

            - Google Calendar: `connector_googlecalendar`

            - Google Drive: `connector_googledrive`

            - Microsoft Teams: `connector_microsoftteams`

            - Outlook Calendar: `connector_outlookcalendar`

            - Outlook Email: `connector_outlookemail`

            - SharePoint: `connector_sharepoint`

            '
        authorization:
          type: string
          description: 'An OAuth access token that can be used with a remote MCP server, either

            with a custom MCP server URL or a service connector. Your application

            must handle the OAuth authorization flow and provide the token here.

            '
        server_description:
          type: string
          description: 'Optional description of the MCP server, used to provide more context.

            '
        headers:
          anyOf:
          - type: object
            additionalProperties:
              type: string
            description: 'Optional HTTP headers to send to the MCP server. Use for authentication

              or other purposes.

              '
          - type: 'null'
        allowed_tools:
          anyOf:
          - description: 'List of allowed tool names or a filter object.

              '
            oneOf:
            - type: array
              title: MCP allowed tools
              description: A string array of allowed tool names
              items:
                type: string
            - $ref: '#/components/schemas/MCPToolFilter'
          - type: 'null'
        require_approval:
          anyOf:
          - description: Specify which of the MCP server's tools require approval.
            oneOf:
            - type: object
              title: MCP tool approval filter
              description: 'Specify which of the MCP server''s tools require approval. Can be

                `always`, `never`, or a filter object associated with tools

                that require approval.

                '
              properties:
                always:
                  $ref: '#/components/schemas/MCPToolFilter'
                never:
                  $ref: '#/components/schemas/MCPToolFilter'
              additionalProperties: false
            - type: string
              title: MCP tool approval setting
              description: 'Specify a single approval policy for all tools. One of `always` or

                `never`. When set to `always`, all tools will require approval. When

                set to `never`, all tools will not require approval.

                '
              enum:
              - always
              - never
            default: always
          - type: 'null'
        defer_loading:
          type: boolean
          description: 'Whether this MCP tool is deferred and discovered via tool search.

            '
      required:
      - type
      - server_label
    InputImageContent:
      properties:
        type:
          type: string
          enum:
          - input_image
          description: The type of the input item. Always `input_image`.
          default: input_image
          x-stainless-const: true
        image_url:
          anyOf:
          - type: string
            format: uri
            description: The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
          - type: 'null'
        file_id:
          anyOf:
          - type: string
            description: The ID of the file to be sent to the model.
          - type: 'null'
        detail:
          $ref: '#/components/schemas/ImageDetail'
          description: The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`.
      type: object
      required:
      - type
      - detail
      title: Input image
      description: An image input to the model. Learn about [image inputs](/docs/guides/vision).
    RealtimeSessionCreateRequestGA:
      type: object
      title: Realtime session configuration
      description: Realtime session object configuration.
      properties:
        type:
          type: string
          description: 'The type of session to create. Always `realtime` for the Realtime API.

            '
          enum:
          - realtime
          x-stainless-const: true
        output_modalities:
          type: array
          description: 'The set of modalities the model can respond with. It defaults to `["audio"]`, indicating

            that the model will respond with audio plus a transcript. `["text"]` can be used to make

            the model respond with text only. It is not possible to request both `text` and `audio` at the same time.

            '
          default:
          - audio
          items:
            type: string
            enum:
            - text
            - audio
        model:
          anyOf:
          - type: string
          - type: string
            enum:
            - gpt-realtime
            - gpt-realtime-1.5
            - gpt-realtime-2
            - gpt-realtime-2025-08-28
            - gpt-4o-realtime-preview
            - gpt-4o-realtime-preview-2024-10-01
            - gpt-4o-realtime-preview-2024-12-17
            - gpt-4o-realtime-preview-2025-06-03
            - gpt-4o-mini-realtime-preview
            - gpt-4o-mini-realtime-preview-2024-12-17
            - gpt-realtime-mini
            - gpt-realtime-mini-2025-10-06
            - gpt-realtime-mini-2025-12-15
            - gpt-audio-1.5
            - gpt-audio-mini
            - gpt-audio-mini-2025-10-06
            - gpt-audio-mini-2025-12-15
          description: 'The Realtime model used for this session.

            '
        instructions:
          type: string
          description: '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.

            '
        audio:
          type: object
          description: 'Configuration for input and output audio.

            '
          properties:
            input:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                  description: The format of the input audio.
                transcription:
                  description: '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 [the /audio/transcriptions endpoint](/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

                    '
                  $ref: '#/components/schemas/AudioTranscription'
                noise_reduction:
                  type: object
                  default: null
                  description: 'Configuration for input audio noise reduction. This can be set to `null` to turn off.

                    Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.

                    Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

                    '
                  properties:
                    type:
                      $ref: '#/components/schemas/NoiseReductionType'
                turn_detection:
                  $ref: '#/components/schemas/RealtimeTurnDetection'
            output:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                  description: The format of the output audio.
                voice:
                  $ref: '#/components/schemas/VoiceIdsOrCustomVoice'
                  default: alloy
                  description: 'The voice the model uses to respond. Supported built-in voices are

                    `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,

                    `marin`, and `cedar`. You may also provide a custom voice object with

                    an `id`, for example `{ "id": "voice_1234" }`. Voice cannot be changed

                    during the session once the model has responded with audio at least once.

                    We recommend `marin` and `cedar` for best quality.

                    '
                speed:
                  type: number
                  default: 1
                  maximum: 1.5
                  minimum: 0.25
                  description: 'The speed of the model''s spoken response as a multiple of the original speed.

                    1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.


                    This parameter is a post-processing adjustment to the audio after it is generated, it''s

                    also possible to prompt the model to speak faster or slower.

                    '
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'Additional fields to include in server outputs.


            `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.

            '
        tracing:
          title: Tracing Configuration
          default: null
          description: 'Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once

            tracing is enabled for a session, the configuration cannot be modified.


            `auto` will create a trace for the session with default values for the

            workflow name, group id, and metadata.

            '
          nullable: true
          oneOf:
          - type: string
            title: auto
            default: auto
            description: 'Enables tracing and sets default values for tracing configuration options. Always `auto`.

              '
            enum:
            - auto
            x-stainless-const: true
          - type: object
            title: Tracing Configuration
            description: 'Granular configuration for tracing.

              '
            properties:
              workflow_name:
                type: string
                description: 'The name of the workflow to attach to this trace. This is used to

                  name the trace in the Traces Dashboard.

                  '
              group_id:
                type: string
                description: 'The group id to attach to this trace to enable filtering and

                  grouping in the Traces Dashboard.

                  '
              metadata:
                type: object
                description: 'The arbitrary metadata to attach to this trace to enable

                  filtering in the Traces Dashboard.

                  '
        tools:
          type: array
          description: Tools available to the model.
          items:
            oneOf:
            - $ref: '#/components/schemas/RealtimeFunctionTool'
            - $ref: '#/components/schemas/MCPTool'
        tool_choice:
          description: 'How the model chooses tools. Provide one of the string modes or force a specific

            function/MCP tool.

            '
          oneOf:
          - $ref: '#/components/schemas/ToolChoiceOptions'
          - $ref: '#/components/schemas/ToolChoiceFunction'
          - $ref: '#/components/schemas/ToolChoiceMCP'
          default: auto
        parallel_tool_calls:
          type: boolean
          description: 'Whether the model may call multiple tools in parallel. Only supported by

            reasoning Realtime models such as `gpt-realtime-2`.

            '
        reasoning:
          $ref: '#/components/schemas/RealtimeReasoning'
        max_output_tokens:
          oneOf:
          - type: integer
          - type: string
            enum:
            - inf
            x-stainless-const: true
          description: 'Maximum 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`.

            '
        truncation:
          $ref: '#/components/schemas/RealtimeTruncation'
        prompt:
          $ref: '#/components/schemas/Prompt'
      required:
      - type
    RealtimeReasoning:
      type: object
      title: Realtime reasoning configuration
      description: 'Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.

        '
      properties:
        effort:
          $ref: '#/components/schemas/RealtimeReasoningEffort'
    InputFileContent:
      properties:
        type:
          type: string
          enum:
          - input_file
          description: The type of the input item. Always `input_file`.
          default: input_file
          x-stainless-const: true
        file_id:
          anyOf:
          - type: string
            description: The ID of the file to be sent to the model.
          - type: 'null'
        filename:
          type: string
          description: The name of the file to be sent to the model.
        file_data:
          type: string
          description: 'The content of the file to be sent to the model.

            '
        file_url:
          type: string
          format: uri
          description: The URL of the file to be sent to the model.
        detail:
          $ref: '#/components/schemas/FileInputDetail'
          description: The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`.
      type: object
      required:
      - type
      title: Input file
      description: A file input to the model.
    RealtimeTranslationClientSecretCreateResponse:
      type: object
      title: Realtime translation session and client secret
      description: 'Response from creating a translation session and client secret for the Realtime API.

        '
      properties:
        value:
          type: string
          description: The generated client secret value.
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the client secret, in seconds since epoch.
        session:
          $ref: '#/components/schemas/RealtimeTranslationSession'
      required:
      - value
      - expires_at
      - session
      x-oaiMeta:
        name: Translation session response object
        group: realtime
        example: "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"type\": \"translation\",\n    \"expires_at\": 1756310470,\n    \"model\": \"gpt-realtime-translate\",\n    \"audio\": {\n      \"input\": {\n        \"transcription\": null,\n        \"noise_reduction\": null\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
    RealtimeCreateClientSecretResponse:
      type: object
      title: Realtime session and client secret
      description: 'Response from creating a session and client secret for the Realtime API.

        '
      properties:
        value:
          type: string
          description: The generated client secret value.
        expires_at:
          type: integer
          format: unixtime
          description: Expiration timestamp for the client secret, in seconds since epoch.
        session:
          title: Session configuration
          description: 'The session configuration for either a realtime or transcription session.

            '
          oneOf:
          - $ref: '#/components/schemas/RealtimeSessionCreateResponseGA'
          - $ref: '#/components/schemas/RealtimeTranscriptionSessionCreateResponseGA'
          discriminator:
            propertyName: type
      required:
      - value
      - expires_at
      - session
      x-oaiMeta:
        name: Session response object
        group: realtime
        example: "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"model\": \"gpt-realtime-2025-08-25\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"You are a friendly assistant.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"truncation\": \"auto\",\n    \"prompt\": null,\n    \"expires_at\": 0,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n          \"threshold\": 0.5,\n          \"prefix_padding_ms\": 300,\n          \"silence_duration_ms\": 200,\n          \"idle_timeout_ms\": null,\n          \"create_response\": true,\n          \"interrupt_response\": true\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n      }\n    },\n    \"include\": null\n  }\n}\n"
    RealtimeTranscriptionSessionCreateRequestGA:
      type: object
      title: Realtime transcription session configuration
      description: Realtime transcription session object configuration.
      properties:
        type:
          type: string
          description: 'The type of session to create. Always `transcription` for transcription sessions.

            '
          enum:
          - transcription
          x-stainless-const: true
        audio:
          type: object
          description: 'Configuration for input and output audio.

            '
          properties:
            input:
              type: object
              properties:
                format:
                  $ref: '#/components/schemas/RealtimeAudioFormats'
                transcription:
                  description: '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 [the /audio/transcriptions endpoint](/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

                    '
                  $ref: '#/components/schemas/AudioTranscription'
                noise_reduction:
                  type: object
                  default: null
                  description: 'Configuration for input audio noise reduction. This can be set to `null` to turn off.

                    Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.

                    Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

                    '
                  properties:
                    type:
                      $ref: '#/components/schemas/NoiseReductionType'
                turn_detection:
                  $ref: '#/components/schemas/RealtimeTurnDetection'
        include:
          type: array
          items:
            type: string
            enum:
            - item.input_audio_transcription.logprobs
          description: 'Additional fields to include in server outputs.


            `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.

            '
      required:
      - type
    Prompt:
      anyOf:
      - type: object
        description: 'Reference to a prompt template and its variables.

          [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts).

          '
        required:
        - id
        properties:
          id:
            type: string
            description: The unique identifier of the prompt template to use.
          version:
            anyOf:
            - type: string
              description: Optional version of the prompt template.
            - type: 'null'
          variables:
            $ref: '#/components/schemas/ResponsePromptVariables'
      - type: 'null'
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
x-oaiMeta:
  groups:
  - id: audio
    title: Audio
    description: 'Learn how to turn audio into text or text into audio.


      Related guide: [Speech to text](/docs/guides/speech-to-text)

      '
    sections:
    - type: endpoint
      key: createSpeech
      path: createSpeech
    - type: endpoint
      key: createTranscription
      path: createTranscription
    - type: endpoint
      key: createTranslation
      path: createTranslation
  - id: chat
    title: Chat
    description: 'Given a list of messages comprising a conversation, the model will return a response.


      Related guide: [Chat Completions](/docs/guides/text-generation)

      '
    sections:
    - type: endpoint
      key: createChatCompletion
      path: create
    - type: object
      key: CreateChatCompletionResponse
      path: object
    - type: object
      key: CreateChatCompletionStreamResponse
      path: streaming
  - id: embeddings
    title: Embeddings
    description: 'Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.


      Related guide: [Embeddings](/docs/guides/embeddings)

      '
    sections:
    - type: endpoint
      key: createEmbedding
      path: create
    - type: object
      key: Embedding
      path: object
  - id: fine-tuning
    title: Fine-tuning
    description: 'Manage fine-tuning jobs to tailor a model to your specific training data.


      Related guide: [Fine-tune models](/docs/guides/fine-tuning)

      '
    sections:
    - type: endpoint
      key: createFineTuningJob
      path: create
    - type: endpoint
      key: listPaginatedFineTuningJobs
      path: list
    - type: endpoint
      key: listFineTuningEvents
      path: list-events
    - type: endpoint
      key: retrieveFineTuningJob
      path: retrieve
    - type: endpoint
      key: cancelFineTuningJob
      path: cancel
    - type: object
      key: FineTuningJob
      path: object
    - type: object
      key: FineTuningJobEvent
      path: event-object
  - id: files
    title: Files
    description: 'Files are used to upload documents that can be used with features like [Assistants](/docs/api-reference/assistants) and [Fine-tuning](/docs/api-reference/fine-tuning).

      '
    sections:
    - type: endpoint
      key: createFile
      path: create
    - type: endpoint
      key: listFiles
      path: list
    - type: endpoint
      key: retrieveFile
      path: retrieve
    - type: endpoint
      key: deleteFile
      path: delete
    - type: endpoint
      key: downloadFile
      path: retrieve-contents
    - type: object
      key: OpenAIFile
      path: object
  - id: images
    title: Images
    description: 'Given a prompt and/or an input image, the model will generate a new image.


      Related guide: [Image generation](/docs/guides/images)

      '
    sections:
    - type: endpoint
      key: createImage
      path: create
    - type: endpoint
      key: createImageEdit
      path: createEdit
    - type: endpoint
      key: createImageVariation
      path: createVariation
    - type: object
      key: Image
      path: object
  - id: models
    title: Models
    description: 'List and describe the various models available in the API. You can refer to the [Models](/docs/models) documentation to understand what models are available and the differences between them.

      '
    sections:
    - type: endpoint
      key: listModels
      path: list
    - type: endpoint
      key: retrieveModel
      path: retrieve
    - type: endpoint
      key: deleteModel
      path: delete
    - type: object
      key: Model
      path: object
  - id: moderations
    title: Moderations
    description: 'Given a input text, outputs if the model classifies it as violating OpenAI''s content policy.


      Related guide: [Moderations](/docs/guides/moderation)

      '
    sections:
    - type: endpoint
      key: createModeration
      path: create
    - type: object
      key: CreateModerationResponse
      path: object
  - id: assistants
    title: Assistants
    beta: true
    description: 'Build assistants that can call models and use tools to perform tasks.


      [Get started with the Assistants API](/docs/assistants)

      '
    sections:
    - type: endpoint
      key: createAssistant
      path: createAssistant
    - type: endpoint
      key: createAssistantFile
      path: createAssistantFile
    - type: endpoint
      key: listAssistants
      path: listAssistants
    - type: endpoint
      key: listAssistantFiles
      path: listAssistantFiles
    - type: endpoint
      key: getAssistant
      path: getAssistant
    - type: endpoint
      key: getAssistantFile
      path: getAssistantFile
    - type: endpoint
      key: modifyAssistant
      path: modifyAssistant
    - type: endpoint
      key: deleteAssistant
      path: deleteAssistant
    - type: endpoint
      key: deleteAssistantFile
      path: deleteAssistantFile
    - type: object
      key: AssistantObject
      path: object
    - type: object
      key: AssistantFileObject
      path: file-object
  - id: threads
    title: Threads
    beta: true
    description: 'Create threads that assistants can interact with.


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createThread
      path: createThread
    - type: endpoint
      key: getThread
      path: getThread
    - type: endpoint
      key: modifyThread
      path: modifyThread
    - type: endpoint
      key: deleteThread
      path: deleteThread
    - type: object
      key: ThreadObject
      path: object
  - id: messages
    title: Messages
    beta: true
    description: 'Create messages within threads


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createMessage
      path: createMessage
    - type: endpoint
      key: listMessages
      path: listMessages
    - type: endpoint
      key: listMessageFiles
      path: listMessageFiles
    - type: endpoint
      key: getMessage
      path: getMessage
    - type: endpoint
      key: getMessageFile
      path: getMessageFile
    - type: endpoint
      key: modifyMessage
      path: modifyMessage
    - type: object
      key: MessageObject
      path: object
    - type: object
      key: MessageFileObject
      path: file-object
  - id: runs
    title: Runs
    beta: true
    description: 'Represents an execution run on a thread.


      Related guide: [Assistants](/docs/assistants/overview)

      '
    sections:
    - type: endpoint
      key: createRun
      path: createRun
    - type: endpoint
      key: createThreadAndRun
      path: createThreadAndRun
    - type: endpoint
      key: listRuns
      path: listRuns
    - type: endpoint
      key: listRunSteps
      path: listRunSteps
    - type: endpoint
      key: getRun
      path: getRun
    - type: endpoint
      key: getRunStep
      path: getRunStep
    - type: endpoint
      key: modifyRun
      path: modifyRun
    - type: endpoint
      key: submitToolOuputsToRun
      path: submitToolOutputs
    - type: endpoint
      key: cancelRun
      path: cancelRun
    - type: object
      key: RunObject
      path: object
    - type: object
      key: RunStepObject
      path: step-object
  - id: completions
    title: Completions
    legacy: true
    description: 'Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](/docs/guides/text-generation/text-generation-models) to leverage our best and newest models. Most models that support the legacy Completions endpoint [will be shut off on January 4th, 2024](/docs/deprecations/2023-07-06-gpt-and-embeddings).

      '
    sections:
    - type: endpoint
      key: createCompletion
      path: create
    - type: object
      key: CreateCompletionResponse
      path: object