Azure OpenAI Service REST API preview reference

This article provides details on the inference REST API endpoints for Azure OpenAI.

Managing and interacting with Azure OpenAI models and resources is divided across three primary API surfaces:

• Control plane
• Data plane - authoring
• Data plane - inference

Each API surface/specification encapsulates a different set of Azure OpenAI capabilities. Each API has its own unique set of preview and stable/generally available (GA) API releases. Preview releases currently tend to follow a monthly cadence.

Azure OpenAI provides two methods for authentication. You can use either API Keys or Microsoft Entra ID.

• API Key authentication: For this type of authentication, all API requests must include the API Key in the api-key HTTP header. The Quickstart provides guidance for how to make calls with this type of authentication.

• Microsoft Entra ID authentication: You can authenticate an API call using a Microsoft Entra token. Authentication tokens are included in a request as the Authorization header. The token provided must be preceded by Bearer, for example Bearer YOUR_AUTH_TOKEN. You can read our how-to guide on authenticating with Microsoft Entra ID.

The service APIs are versioned using the api-version query parameter. All versions follow the YYYY-MM-DD date structure. For example:

POST https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/chat/completions?api-version=2024-06-01

The rest of the article covers the latest preview release of the Azure OpenAI data plane inference specification, 2025-03-01-preview. This article includes documentation for the latest preview capabilities like assistants, threads, and vector stores.

If you're looking for documentation on the latest GA API release, refer to the latest GA data plane inference API

POST https://{endpoint}/openai/deployments/{deployment-id}/completions?api-version=2025-03-01-preview

Creates a completion for the provided prompt, parameters and chosen model.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Status Code: default

Description: Service unavailable

Creates a completion for the provided prompt, parameters and chosen model.

POST https://{endpoint}/openai/deployments/{deployment-id}/completions?api-version=2025-03-01-preview

{
 "prompt": [
  "tell me a joke about mango"
 ],
 "max_tokens": 32,
 "temperature": 1.0,
 "n": 1
}

Responses: Status Code: 200

{
  "body": {
    "id": "cmpl-7QmVI15qgYVllxK0FtxVGG6ywfzaq",
    "created": 1686617332,
    "choices": [
      {
        "text": "es\n\nWhat do you call a mango who's in charge?\n\nThe head mango.",
        "index": 0,
        "finish_reason": "stop",
        "logprobs": null
      }
    ],
    "usage": {
      "completion_tokens": 20,
      "prompt_tokens": 6,
      "total_tokens": 26
    }
  }
}

POST https://{endpoint}/openai/deployments/{deployment-id}/embeddings?api-version=2025-03-01-preview

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

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Return the embeddings for a given prompt.

POST https://{endpoint}/openai/deployments/{deployment-id}/embeddings?api-version=2025-03-01-preview

{
 "input": [
  "this is a test"
 ]
}

Responses: Status Code: 200

{
  "body": {
    "data": [
      {
        "index": 0,
        "embedding": [
          -0.012838088,
          -0.007421397,
          -0.017617522,
          -0.028278312,
          -0.018666342,
          0.01737855,
          -0.01821495,
          -0.006950092,
          -0.009937238,
          -0.038580645,
          0.010674067,
          0.02412286,
          -0.013647936,
          0.013189907,
          0.0021125758,
          0.012406612,
          0.020790534,
          0.00074595667,
          0.008397198,
          -0.00535031,
          0.008968075,
          0.014351576,
          -0.014086051,
          0.015055214,
          -0.022211088,
          -0.025198232,
          0.0065186154,
          -0.036350243,
          0.009180495,
          -0.009698266,
          0.009446018,
          -0.008463579,
          -0.0040426035,
          -0.03443847,
          -0.00091273896,
          -0.0019217303,
          0.002349888,
          -0.021560553,
          0.016515596,
          -0.015572986,
          0.0038666942,
          -8.432463e-05,
          0.0032178196,
          -0.020365695,
        ]
      }
    ],
    "usage": {
      "prompt_tokens": 4,
      "total_tokens": 4
    }
  }
}

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

Creates a completion for the chat message

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Status Code: default

Description: Service unavailable

Creates a completion for the provided prompt, parameters and chosen model.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "system",
   "content": "you are a helpful assistant that talks like a pirate"
  },
  {
   "role": "user",
   "content": "can you tell me how to care for a parrot?"
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Ahoy matey! So ye be wantin' to care for a fine squawkin' parrot, eh? Well, shiver me timbers, let ol' Cap'n Assistant share some wisdom with ye! Here be the steps to keepin' yer parrot happy 'n healthy:\n\n1. Secure a sturdy cage: Yer parrot be needin' a comfortable place to lay anchor! Be sure ye get a sturdy cage, at least double the size of the bird's wingspan, with enough space to spread their wings, yarrrr!\n\n2. Perches 'n toys: Aye, parrots need perches of different sizes, shapes, 'n textures to keep their feet healthy. Also, a few toys be helpin' to keep them entertained 'n their minds stimulated, arrrh!\n\n3. Proper grub: Feed yer feathered friend a balanced diet of high-quality pellets, fruits, 'n veggies to keep 'em strong 'n healthy. Give 'em fresh water every day, or ye\u00e2\u20ac\u2122ll have a scurvy bird on yer hands!\n\n4. Cleanliness: Swab their cage deck! Clean their cage on a regular basis: fresh water 'n food daily, the floor every couple of days, 'n a thorough scrubbing ev'ry few weeks, so the bird be livin' in a tidy haven, arrhh!\n\n5. Socialize 'n train: Parrots be a sociable lot, arrr! Exercise 'n interact with 'em daily to create a bond 'n maintain their mental 'n physical health. Train 'em with positive reinforcement, treat 'em kindly, yarrr!\n\n6. Proper rest: Yer parrot be needin' \u00e2\u20ac\u2122bout 10-12 hours o' sleep each night. Cover their cage 'n let them slumber in a dim, quiet quarter for a proper night's rest, ye scallywag!\n\n7. Keep a weather eye open for illness: Birds be hidin' their ailments, arrr! Be watchful for signs of sickness, such as lethargy, loss of appetite, puffin' up, or change in droppings, and make haste to a vet if need be.\n\n8. Provide fresh air 'n avoid toxins: Parrots be sensitive to draft and pollutants. Keep yer quarters well ventilated, but no drafts, arrr! Be mindful of toxins like Teflon fumes, candles, or air fresheners.\n\nSo there ye have it, me hearty! With proper care 'n commitment, yer parrot will be squawkin' \"Yo-ho-ho\" for many years to come! Good luck, sailor, and may the wind be at yer back!"
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion based on Azure Search data and system-assigned managed identity.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "index_name": "{index name}",
    "authentication": {
     "type": "system_assigned_managed_identity"
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion based on Azure Search image vector data.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "index_name": "{index name}",
    "query_type": "vector",
    "fields_mapping": {
     "image_vector_fields": [
      "image_vector"
     ]
    },
    "authentication": {
     "type": "api_key",
     "key": "{api key}"
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion."
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion based on Azure Search vector data, previous assistant message and user-assigned managed identity.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a cat?"
  },
  {
   "role": "assistant",
   "content": "Content of the completion [doc1].",
   "context": {
    "intent": "cat care"
   }
  },
  {
   "role": "user",
   "content": "how about dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "authentication": {
     "type": "user_assigned_managed_identity",
     "managed_identity_resource_id": "/subscriptions/{subscription-id}/resourceGroups/{resource-group}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{resource-name}"
    },
    "index_name": "{index name}",
    "query_type": "vector",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "in_scope": true,
    "top_n_documents": 5,
    "strictness": 3,
    "role_information": "You are an AI assistant that helps people find information.",
    "fields_mapping": {
     "content_fields_separator": "\\n",
     "content_fields": [
      "content"
     ],
     "filepath_field": "filepath",
     "title_field": "title",
     "url_field": "url",
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content 2.",
                "title": "Citation Title 2",
                "filepath": "contoso2.txt",
                "url": "https://contoso.blob.windows.net/container/contoso2.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion for the provided Azure Cosmos DB.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_cosmos_db",
   "parameters": {
    "authentication": {
     "type": "connection_string",
     "connection_string": "mongodb+srv://rawantest:{password}$@{cluster-name}.mongocluster.cosmos.azure.com/?tls=true&authMechanism=SCRAM-SHA-256&retrywrites=false&maxIdleTimeMS=120000"
    },
    "database_name": "vectordb",
    "container_name": "azuredocs",
    "index_name": "azuredocindex",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "content_fields": [
      "content"
     ],
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion for the provided Mongo DB.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "mongo_db",
   "parameters": {
    "authentication": {
     "type": "username_and_password",
     "username": "<username>",
     "password": "<password>"
    },
    "endpoint": "<endpoint_name>",
    "app_name": "<application name>",
    "database_name": "sampledb",
    "collection_name": "samplecollection",
    "index_name": "sampleindex",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "content_fields": [
      "content"
     ],
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion for the provided Elasticsearch.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "elasticsearch",
   "parameters": {
    "endpoint": "https://your-elasticsearch-endpoint.eastus.azurecontainer.io",
    "index_name": "{index name}",
    "authentication": {
     "type": "key_and_key_id",
     "key": "{key}",
     "key_id": "{key id}"
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Creates a completion for the provided Pinecone resource.

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-03-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "pinecone",
   "parameters": {
    "authentication": {
     "type": "api_key",
     "key": "{api key}"
    },
    "environment": "{environment name}",
    "index_name": "{index name}",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "title_field": "title",
     "url_field": "url",
     "filepath_field": "filepath",
     "content_fields": [
      "content"
     ],
     "content_fields_separator": "\n"
    }
   }
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-03-01-preview

Transcribes audio into the input language.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: multipart/form-data

Status Code: 200

Description: OK

Gets transcribed text and associated metadata from provided spoken audio data.

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "text": "A structured object when requesting json or verbose_json"
  }
}

Gets transcribed text and associated metadata from provided spoken audio data.

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-03-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

Responses: Status Code: 200

{
  "type": "string",
  "example": "plain text when requesting text, srt, or vtt"
}

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-03-01-preview

Transcribes and translates input audio into English text.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: multipart/form-data

Status Code: 200

Description: OK

Gets English language transcribed text and associated metadata from provided spoken audio data.

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-03-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

Responses: Status Code: 200

{
  "body": {
    "text": "A structured object when requesting json or verbose_json"
  }
}

Gets English language transcribed text and associated metadata from provided spoken audio data.

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-03-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

Responses: Status Code: 200

{
  "type": "string",
  "example": "plain text when requesting text, srt, or vtt"
}

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/speech?api-version=2025-03-01-preview

Generates audio from the input text.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: multipart/form-data

Status Code: 200

Description: OK

Synthesizes audio from the provided text.

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/speech?api-version=2025-03-01-preview

{
 "input": "Hi! What are you going to make?",
 "voice": "fable",
 "response_format": "mp3"
}

Responses: Status Code: 200

{
  "body": "101010101"
}

POST https://{endpoint}/openai/deployments/{deployment-id}/images/generations?api-version=2025-03-01-preview

Generates a batch of images from a text caption on a given DALLE model deployment

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: Ok

Status Code: default

Description: An error occurred.

Creates images given a prompt.

POST https://{endpoint}/openai/deployments/{deployment-id}/images/generations?api-version=2025-03-01-preview

{
 "prompt": "In the style of WordArt, Microsoft Clippy wearing a cowboy hat.",
 "n": 1,
 "style": "natural",
 "quality": "standard"
}

Responses: Status Code: 200

{
  "body": {
    "created": 1698342300,
    "data": [
      {
        "revised_prompt": "A vivid, natural representation of Microsoft Clippy wearing a cowboy hat.",
        "prompt_filter_results": {
          "sexual": {
            "severity": "safe",
            "filtered": false
          },
          "violence": {
            "severity": "safe",
            "filtered": false
          },
          "hate": {
            "severity": "safe",
            "filtered": false
          },
          "self_harm": {
            "severity": "safe",
            "filtered": false
          },
          "profanity": {
            "detected": false,
            "filtered": false
          },
          "custom_blocklists": {
            "filtered": false,
            "details": []
          }
        },
        "url": "https://dalletipusw2.blob.core.windows.net/private/images/e5451cc6-b1ad-4747-bd46-b89a3a3b8bc3/generated_00.png?se=2023-10-27T17%3A45%3A09Z&...",
        "content_filter_results": {
          "sexual": {
            "severity": "safe",
            "filtered": false
          },
          "violence": {
            "severity": "safe",
            "filtered": false
          },
          "hate": {
            "severity": "safe",
            "filtered": false
          },
          "self_harm": {
            "severity": "safe",
            "filtered": false
          }
        }
      }
    ]
  }
}

GET https://{endpoint}/openai/assistants?api-version=2025-03-01-preview

Returns a list of assistants.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of assistants.

GET https://{endpoint}/openai/assistants?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "asst_abc123",
        "object": "assistant",
        "created_at": 1707257477,
        "name": "Stock Analyst",
        "description": null,
        "model": "gpt-4-1106-preview",
        "instructions": "You are a financial analyst that analyzes stock market prices and other financial data present on user uploaded files or by calling external APIs.",
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      },
      {
        "id": "asst_abc456",
        "object": "assistant",
        "created_at": 1698982718,
        "name": "My Assistant",
        "description": null,
        "model": "gpt-4-turbo",
        "instructions": "You are a helpful assistant designed to make me better at coding!",
        "tools": [],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      },
      {
        "id": "asst_abc789",
        "object": "assistant",
        "created_at": 1698982643,
        "name": null,
        "description": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "tools": [],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      }
    ],
    "first_id": "asst_abc123",
    "last_id": "asst_abc789",
    "has_more": false
  }
}

POST https://{endpoint}/openai/assistants?api-version=2025-03-01-preview

Create an assistant with a model and instructions.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Create an assistant with a model and instructions.

POST https://{endpoint}/openai/assistants?api-version=2025-03-01-preview

{
 "name": "Math Tutor",
 "instructions": "When a customer asks about a specific math problem, use Python to evaluate their query.",
 "tools": [
  {
   "type": "code_interpreter"
  }
 ],
 "model": "gpt-4-1106-preview"
}

Responses: Status Code: 200

{
  "body": {
    "id": "asst_4nsG2qgNzimRPE7MazXTXbU7",
    "object": "assistant",
    "created_at": 1707295707,
    "name": "Math Tutor",
    "description": null,
    "model": "gpt-4-1106-preview",
    "instructions": "When a customer asks about a specific math problem, use Python to evaluate their query.",
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

GET https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

Retrieves an assistant.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves an assistant.

GET https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "asst_abc123",
    "object": "assistant",
    "created_at": 1699009709,
    "name": "HR Helper",
    "description": null,
    "model": "gpt-4-turbo",
    "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

POST https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

Modifies an assistant.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Modifies an assistant.

POST https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

{
 "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
 "tools": [
  {
   "type": "file_search"
  }
 ],
 "model": "gpt-4-turbo"
}

Responses: Status Code: 200

{
  "body": {
    "id": "asst_123",
    "object": "assistant",
    "created_at": 1699009709,
    "name": "HR Helper",
    "description": null,
    "model": "gpt-4-turbo",
    "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "tool_resources": {
      "file_search": {
        "vector_store_ids": []
      }
    },
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

DELETE https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

Delete an assistant.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Deletes an assistant.

DELETE https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "asst_4nsG2qgNzimRPE7MazXTXbU7",
    "object": "assistant.deleted",
    "deleted": true
  }
}

POST https://{endpoint}/openai/threads?api-version=2025-03-01-preview

Create a thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Creates a thread.

POST https://{endpoint}/openai/threads?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {}
  }
}

GET https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

Retrieves a thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves a thread.

GET https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {},
    "tool_resources": {
      "code_interpreter": {
        "file_ids": []
      }
    }
  }
}

POST https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

Modifies a thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Modifies a thread.

POST https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

{
 "metadata": {
  "modified": "true",
  "user": "abc123"
 }
}

Responses: Status Code: 200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {
      "modified": "true",
      "user": "abc123"
    },
    "tool_resources": {}
  }
}

DELETE https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

Delete a thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Deletes a thread.

DELETE https://{endpoint}/openai/threads/{thread_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread.deleted",
    "deleted": true
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-03-01-preview

Returns a list of messages for a given thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

List Messages

GET https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "msg_abc123",
        "object": "thread.message",
        "created_at": 1699016383,
        "assistant_id": null,
        "thread_id": "thread_abc123",
        "run_id": null,
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": {
              "value": "How does AI work? Explain it in simple terms.",
              "annotations": []
            }
          }
        ],
        "attachments": [],
        "metadata": {}
      },
      {
        "id": "msg_abc456",
        "object": "thread.message",
        "created_at": 1699016383,
        "assistant_id": null,
        "thread_id": "thread_abc123",
        "run_id": null,
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": {
              "value": "Hello, what is AI?",
              "annotations": []
            }
          }
        ],
        "attachments": [],
        "metadata": {}
      }
    ],
    "first_id": "msg_abc123",
    "last_id": "msg_abc456",
    "has_more": false
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-03-01-preview

Create a message.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Create a message.

POST https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-03-01-preview

{
 "role": "user",
 "content": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces."
}

Responses: Status Code: 200

{
  "body": {
    "id": "msg_as3XIk1tpVP3hdHjWBGg3uG4",
    "object": "thread.message",
    "created_at": 1707298421,
    "assistant_id": null,
    "thread_id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "run_id": null,
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces.",
          "annotations": []
        }
      }
    ],
    "attachments": [],
    "metadata": {}
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-03-01-preview

Retrieve a message.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieve a message.

GET https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "msg_as3XIk1tpVP3hdHjWBGg3uG4",
    "object": "thread.message",
    "created_at": 1707298421,
    "thread_id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces.",
          "annotations": []
        }
      }
    ],
    "file_ids": [],
    "assistant_id": null,
    "run_id": null,
    "metadata": {}
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-03-01-preview

Modifies a message.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Modify a message.

POST https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-03-01-preview

{
 "metadata": {
  "modified": "true",
  "user": "abc123"
 }
}

Responses: Status Code: 200

{
  "body": {
    "id": "msg_abc123",
    "object": "thread.message",
    "created_at": 1699017614,
    "assistant_id": null,
    "thread_id": "thread_abc123",
    "run_id": null,
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "How does AI work? Explain it in simple terms.",
          "annotations": []
        }
      }
    ],
    "file_ids": [],
    "metadata": {
      "modified": "true",
      "user": "abc123"
    }
  }
}

POST https://{endpoint}/openai/threads/runs?api-version=2025-03-01-preview

Create a thread and run it in one request.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Create a thread and run it in one request.

POST https://{endpoint}/openai/threads/runs?api-version=2025-03-01-preview

{
 "assistant_id": "asst_abc123",
 "thread": {
  "messages": [
   {
    "role": "user",
    "content": "Explain deep learning to a 5 year old."
   }
  ]
 }
}

Responses: Status Code: 200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699076792,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "queued",
    "started_at": null,
    "expires_at": 1699077392,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "required_action": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": "You are a helpful assistant.",
    "tools": [],
    "tool_resources": {},
    "metadata": {},
    "temperature": 1.0,
    "top_p": 1.0,
    "max_completion_tokens": null,
    "max_prompt_tokens": null,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "incomplete_details": null,
    "usage": null,
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-03-01-preview

Returns a list of runs belonging to a thread.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of runs belonging to a thread.

GET https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "run_abc123",
        "object": "thread.run",
        "created_at": 1699075072,
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "status": "completed",
        "started_at": 1699075072,
        "expires_at": null,
        "cancelled_at": null,
        "failed_at": null,
        "completed_at": 1699075073,
        "last_error": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "incomplete_details": null,
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {
          "code_interpreter": {
            "file_ids": [
              "file-abc123",
              "file-abc456"
            ]
          }
        },
        "metadata": {},
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        },
        "temperature": 1.0,
        "top_p": 1.0,
        "max_prompt_tokens": 1000,
        "max_completion_tokens": 1000,
        "truncation_strategy": {
          "type": "auto",
          "last_messages": null
        },
        "response_format": "auto",
        "tool_choice": "auto"
      },
      {
        "id": "run_abc456",
        "object": "thread.run",
        "created_at": 1699063290,
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "status": "completed",
        "started_at": 1699063290,
        "expires_at": null,
        "cancelled_at": null,
        "failed_at": null,
        "completed_at": 1699063291,
        "last_error": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "incomplete_details": null,
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {
          "code_interpreter": {
            "file_ids": [
              "file-abc123",
              "file-abc456"
            ]
          }
        },
        "metadata": {},
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        },
        "temperature": 1.0,
        "top_p": 1.0,
        "max_prompt_tokens": 1000,
        "max_completion_tokens": 1000,
        "truncation_strategy": {
          "type": "auto",
          "last_messages": null
        },
        "response_format": "auto",
        "tool_choice": "auto"
      }
    ],
    "first_id": "run_abc123",
    "last_id": "run_abc456",
    "has_more": false
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-03-01-preview

Create a run.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Create a run.

POST https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-03-01-preview

{
 "assistant_id": "asst_abc123"
}

Responses: Status Code: 200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699063290,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "queued",
    "started_at": 1699063290,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1699063291,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "incomplete_details": null,
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-03-01-preview

Retrieves a run.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Gets a run.

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "run_HsO8tYM4K5AAMAHgK0J3om8Q",
    "object": "thread.run",
    "created_at": 1707303196,
    "assistant_id": "asst_JtTwHk28cIocgFXZPCBxhOzl",
    "thread_id": "thread_eRNwflE3ncDYak1np6MdMHJh",
    "status": "completed",
    "started_at": 1707303197,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1707303201,
    "last_error": null,
    "model": "gpt-4-1106-preview",
    "instructions": "You are an AI model that empowers every person and every organization on the planet to achieve more.",
    "tools": [],
    "file_ids": [],
    "metadata": {}
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-03-01-preview

Modifies a run.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Modifies a run.

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-03-01-preview

{
 "metadata": {
  "user_id": "user_abc123"
 }
}

Responses: Status Code: 200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699075072,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "completed",
    "started_at": 1699075072,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1699075073,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "incomplete_details": null,
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "tool_resources": {
      "code_interpreter": {
        "file_ids": [
          "file-abc123",
          "file-abc456"
        ]
      }
    },
    "metadata": {
      "user_id": "user_abc123"
    },
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 456,
      "total_tokens": 579
    },
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/submit_tool_outputs?api-version=2025-03-01-preview

When a run has the status: "requires_action" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

When a run has the status: "requires_action" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/submit_tool_outputs?api-version=2025-03-01-preview

{
 "tool_outputs": [
  {
   "tool_call_id": "call_001",
   "output": "70 degrees and sunny."
  }
 ]
}

Responses: Status Code: 200

{
  "body": {
    "id": "run_123",
    "object": "thread.run",
    "created_at": 1699075592,
    "assistant_id": "asst_123",
    "thread_id": "thread_123",
    "status": "queued",
    "started_at": 1699075592,
    "expires_at": 1699076192,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              },
              "unit": {
                "type": "string",
                "enum": [
                  "celsius",
                  "fahrenheit"
                ]
              }
            },
            "required": [
              "location"
            ]
          }
        }
      }
    ],
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/cancel?api-version=2025-03-01-preview

Cancels a run that is in_progress.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Cancels a run that is in_progress.

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/cancel?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699076126,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "cancelling",
    "started_at": 1699076126,
    "expires_at": 1699076726,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": "You summarize books.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "tool_resources": {
      "file_search": {
        "vector_store_ids": [
          "vs_123"
        ]
      }
    },
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "response_format": "auto"
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps?api-version=2025-03-01-preview

Returns a list of run steps belonging to a run.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of run steps belonging to a run.

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "step_abc123",
        "object": "thread.run.step",
        "created_at": 1699063291,
        "run_id": "run_abc123",
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "type": "message_creation",
        "status": "completed",
        "cancelled_at": null,
        "completed_at": 1699063291,
        "expired_at": null,
        "failed_at": null,
        "last_error": null,
        "step_details": {
          "type": "message_creation",
          "message_creation": {
            "message_id": "msg_abc123"
          }
        },
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        }
      }
    ],
    "first_id": "step_abc123",
    "last_id": "step_abc456",
    "has_more": false
  }
}

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps/{step_id}?api-version=2025-03-01-preview

Retrieves a run step.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves a run step.

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps/{step_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "step_abc123",
    "object": "thread.run.step",
    "created_at": 1699063291,
    "run_id": "run_abc123",
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "type": "message_creation",
    "status": "completed",
    "cancelled_at": null,
    "completed_at": 1699063291,
    "expired_at": null,
    "failed_at": null,
    "last_error": null,
    "step_details": {
      "type": "message_creation",
      "message_creation": {
        "message_id": "msg_abc123"
      }
    },
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 456,
      "total_tokens": 579
    }
  }
}

GET https://{endpoint}/openai/vector_stores?api-version=2025-03-01-preview

Returns a list of vector stores.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of vector stores.

GET https://{endpoint}/openai/vector_stores?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "vs_abc123",
        "object": "vector_store",
        "created_at": 1699061776,
        "name": "Support FAQ",
        "bytes": 139920,
        "file_counts": {
          "in_progress": 0,
          "completed": 3,
          "failed": 0,
          "cancelled": 0,
          "total": 3
        }
      },
      {
        "id": "vs_abc456",
        "object": "vector_store",
        "created_at": 1699061776,
        "name": "Support FAQ v2",
        "bytes": 139920,
        "file_counts": {
          "in_progress": 0,
          "completed": 3,
          "failed": 0,
          "cancelled": 0,
          "total": 3
        }
      }
    ],
    "first_id": "vs_abc123",
    "last_id": "vs_abc456",
    "has_more": false
  }
}

POST https://{endpoint}/openai/vector_stores?api-version=2025-03-01-preview

Create a vector store.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Creates a vector store.

POST https://{endpoint}/openai/vector_stores?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776,
    "name": "Support FAQ",
    "bytes": 139920,
    "file_counts": {
      "in_progress": 0,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 3
    }
  }
}

GET https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

Retrieves a vector store.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves a vector store.

GET https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776
  }
}

POST https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

Modifies a vector store.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Modifies a vector store.

POST https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

{
 "name": "Support FAQ"
}

Responses: Status Code: 200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776,
    "name": "Support FAQ",
    "bytes": 139920,
    "file_counts": {
      "in_progress": 0,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 3
    }
  }
}

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

Delete a vector store.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Deletes a vector store.

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store.deleted",
    "deleted": true
  }
}

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-03-01-preview

Returns a list of vector store files.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of vector store files.

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "file-abc123",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      },
      {
        "id": "file-abc456",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      }
    ],
    "first_id": "file-abc123",
    "last_id": "file-abc456",
    "has_more": false
  }
}

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-03-01-preview

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

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

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

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-03-01-preview

{
 "file_id": "file-abc123"
}

Responses: Status Code: 200

{
  "body": {
    "id": "file-abc123",
    "object": "vector_store.file",
    "created_at": 1699061776,
    "usage_bytes": 1234,
    "vector_store_id": "vs_abcd",
    "status": "completed",
    "last_error": null
  }
}

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-03-01-preview

Retrieves a vector store file.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves a vector store file.

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "file-abc123",
    "object": "vector_store.file",
    "created_at": 1699061776,
    "vector_store_id": "vs_abcd",
    "status": "completed",
    "last_error": null
  }
}

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-03-01-preview

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint.

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "file_abc123",
    "object": "vector_store.file.deleted",
    "deleted": true
  }
}

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-03-01-preview

Update attributes on a vector store file.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}/content?api-version=2025-03-01-preview

Retrieve the parsed contents of a vector store file.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/search?api-version=2025-03-01-preview

Search a vector store for relevant chunks based on a query and file attributes filter.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches?api-version=2025-03-01-preview

Create a vector store file batch.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Content-Type: application/json

Status Code: 200

Description: OK

Create a vector store file batch.

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches?api-version=2025-03-01-preview

{
 "file_ids": [
  "file-abc123",
  "file-abc456"
 ]
}

Responses: Status Code: 200

{
  "id": "vsfb_abc123",
  "object": "vector_store.file_batch",
  "created_at": 1699061776,
  "vector_store_id": "vs_abc123",
  "status": "in_progress",
  "file_counts": {
    "in_progress": 1,
    "completed": 1,
    "failed": 0,
    "cancelled": 0,
    "total": 0
  }
}

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}?api-version=2025-03-01-preview

Retrieves a vector store file batch.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Retrieves a vector store file batch.

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "vsfb_abc123",
    "object": "vector_store.file_batch",
    "created_at": 1699061776,
    "vector_store_id": "vs_abc123",
    "status": "in_progress",
    "file_counts": {
      "in_progress": 1,
      "completed": 1,
      "failed": 0,
      "cancelled": 0,
      "total": 0
    }
  }
}

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel?api-version=2025-03-01-preview

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "id": "vsfb_abc123",
    "object": "vector_store.file_batch",
    "created_at": 1699061776,
    "vector_store_id": "vs_abc123",
    "status": "cancelling",
    "file_counts": {
      "in_progress": 12,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 15
    }
  }
}

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/files?api-version=2025-03-01-preview

Returns a list of vector store files in a batch.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Returns a list of vector store files.

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/files?api-version=2025-03-01-preview

Responses: Status Code: 200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "file-abc123",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      },
      {
        "id": "file-abc456",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      }
    ],
    "first_id": "file-abc123",
    "last_id": "file-abc456",
    "has_more": false
  }
}

POST https://{endpoint}/openai/responses?api-version=2025-03-01-preview

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like file search to use your own data as input for the model's response.

Content-Type: application/json

Status Code: 200

Description: OK

Status Code: default

Description: Service unavailable

GET https://{endpoint}/openai/responses/{response_id}?api-version=2025-03-01-preview

Retrieves a model response with the given ID.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Status Code: default

Description: Service unavailable

DELETE https://{endpoint}/openai/responses/{response_id}?api-version=2025-03-01-preview

Deletes a model response with the given ID.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure.

Status Code: 200

Description: OK

Status Code: 404

Description: Not Found

Status Code: default

Description: Service unavailable

GET https://{endpoint}/openai/responses/{response_id}/input_items?api-version=2025-03-01-preview

Returns a list of input items for a given response.

Use either token based authentication or API key. Authenticating with token based authentication is recommended and more secure..**

Status Code: 200

Description: OK

Inner error with additional details.

Error codes for the inner error object.

Inner error with additional details.

Describes a span within generated completion text. Offset 0 is the first UTF32 code point of the completion text.

Information about the content filtering results.

Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.

Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about third party text and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.

Content filtering results with a detail of content filter ids for the filtered segments.

Content filtering results for a single prompt in the request.

Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders.

No properties defined for this component.

Information about the content filtering results.

Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.

Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).

User security context contains several parameters that describe the AI application itself, and the end user that interacts with the AI application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. Learn more about protecting AI applications using Microsoft Defender for Cloud.

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

The parameters the functions accepts, described as a JSON Schema object. See the guide/ for examples, and the JSON Schema reference for documentation about the format.

No properties defined for this component.

This component can be one of the following:

• ChatCompletionRequestDeveloperMessage
• chatCompletionRequestSystemMessage
• chatCompletionRequestUserMessage
• chatCompletionRequestAssistantMessage
• chatCompletionRequestToolMessage
• chatCompletionRequestFunctionMessage

Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, developer messages replace the previous system messages.

This component can be one of the following:

• chatCompletionRequestMessageContentPartText

This component can be one of the following:

• chatCompletionRequestMessageContentPartText

This component can be one of the following:

• chatCompletionRequestMessageContentPartText
• chatCompletionRequestMessageContentPartImage
• chatCompletionRequestMessageContentPartAudio

This component can be one of the following:

• chatCompletionRequestMessageContentPartText
• chatCompletionRequestMessageContentPartRefusal

This component can be one of the following:

• chatCompletionRequestMessageContentPartText

A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat completions request that should use Azure OpenAI chat extensions to augment the response behavior. The use of this configuration is compatible only with Azure OpenAI.

This component uses the property type to discriminate between different types:

A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat completions request that should use Azure OpenAI chat extensions to augment the response behavior. The use of this configuration is compatible only with Azure OpenAI.

A specific representation of configurable options for Azure Search when using it as an Azure OpenAI chat extension.

Parameters for Azure Search when used as an Azure OpenAI chat extension.

Optional settings to control how fields are processed when using a configured Azure Search resource.

The type of Azure Search retrieval query that should be executed when using it as an Azure OpenAI chat extension.

A specific representation of configurable options for Azure Cosmos DB when using it as an Azure OpenAI chat extension.

Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Azure Cosmos DB for MongoDB vCore.

Optional settings to control how fields are processed when using a configured Azure Cosmos DB resource.

A specific representation of configurable options for Elasticsearch when using it as an Azure OpenAI chat extension.

Parameters to use when configuring Elasticsearch® as an Azure OpenAI chat extension.

Optional settings to control how fields are processed when using a configured Elasticsearch® resource.

The type of Elasticsearch® retrieval query that should be executed when using it as an Azure OpenAI chat extension.

A specific representation of configurable options for Mongo DB when using it as an Azure OpenAI chat extension.

Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Mongo DB.

Optional settings to control how fields are processed when using a configured Mongo DB resource.

A specific representation of configurable options for Pinecone when using it as an Azure OpenAI chat extension.

Parameters for configuring Azure OpenAI Pinecone chat extensions.

Optional settings to control how fields are processed when using a configured Pinecone resource.

The authentication options for Azure OpenAI On Your Data.

This component uses the property type to discriminate between different types:

The context property.

The authentication types supported with Azure OpenAI On Your Data.

The authentication options for Azure OpenAI On Your Data when using an API key.

The authentication options for Azure OpenAI On Your Data when using a connection string.

The authentication options for Azure OpenAI On Your Data when using an Elasticsearch key and key ID pair.

The authentication options for Azure OpenAI On Your Data when using an Elasticsearch encoded API key.

The authentication options for Azure OpenAI On Your Data when using access token.

The authentication options for Azure OpenAI On Your Data when using a system-assigned managed identity.

The authentication options for Azure OpenAI On Your Data when using a user-assigned managed identity.

The authentication options for Azure OpenAI On Your Data when using a username and a password.

An abstract representation of a vectorization source for Azure OpenAI On Your Data with vector search.

This component uses the property type to discriminate between different types:

Represents the available sources Azure OpenAI On Your Data can use to configure vectorization of data for use with vector search.

The details of a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on a public Azure OpenAI endpoint call for embeddings.

The details of a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on an internal embeddings model deployment name in the same Azure OpenAI resource.

Represents the integrated vectorizer defined within the search resource.

The details of a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based on a search service model ID. Currently only supported by Elasticsearch®.

A representation of the additional context information available when Azure OpenAI chat extensions are involved in the generation of a corresponding chat completions response. This context information is only populated when using an Azure OpenAI request configured to use a matching extension.

citation information for a chat completions response message.

The retrieved document.

The filtering reason of the retrieved document.

The type of the tool call, in this case function.

Represents a chat completion response returned by model, based on the provided input.

Represents a streamed chunk of a chat completion response returned by model, based on the provided input.

A chat completion delta generated by streamed model responses.

Options for streaming response. Only set this when you set stream: true.

Log probability information for the choice.

A chat completion message generated by the model.

The role of the author of the response message.

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. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

This component can be one of the following:

• chatCompletionNamedToolChoice

Specifies a tool the model should use. Use to force the model to call a specific function.

Whether to enable parallel function calling during tool use.

No properties defined for this component.

Static predicted output content, such as the content of a text file that is being regenerated.

The tool calls generated by the model, such as function calls.

No properties defined for this component.

Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

No properties defined for this component.

Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.

Usage statistics for the completion request.

The parameters the functions accepts, described as a JSON Schema object. See the guide](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling) for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

No properties defined for this component.

The schema for the response format, described as a JSON Schema object.

No properties defined for this component.

Translation request.

Translation or transcription response when response_format was json

Translation or transcription response when response_format was verbose_json

Defines the format of the output.

Transcription request.

Transcription or translation segment.

Transcription or translation word.

Speech request.

The quality of the image that will be generated.

The format in which the generated images are returned.

The size of the generated images.

The style of the generated images.

The image url or encoded image if successful, and an error otherwise.

A content line object consisting of an adjacent sequence of content elements, such as words and selection marks.

A span object that represents a detected object and its bounding box information.

Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

This component can be one of the following:

• ResponseFormatText
• ResponseFormatJsonObject
• ResponseFormatJsonSchema

An object describing the expected output of the model. If json_object only function type tools are allowed to be passed to the Run. If text the model can return text or any value needed.

type Enum: AssistantsApiResponseFormat

Represents an assistant that can call the model and use tools.

object Enum: AssistantObjectType

object Enum: DeleteAssistantResponseState

type Enum: assistantToolsCodeType

type Enum: assistantToolsFileSearchType

type Enum: assistantToolsFileSearchType

type Enum: assistantToolsFunction

Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

type Enum: TruncationType

Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

This component can be one of the following:

• assistantsNamedToolChoice

Specifies a tool the model should use. Use to force the model to call a specific tool.

type Enum: AssistantsNamedToolChoiceType

Represents an execution run on a thread.

object Enum: runObjectType

status Enum: RunObjectStatus

Tool call objects

type Enum: RunToolCallObjectType

Represents a thread that contains messages.

object Enum: ThreadObjectType

object Enum: DeleteThreadResponseObjectState

Represents a message within a thread.

object Enum: MessageObjectType

status Enum: MessageObjectStatus

role Enum: MessageObjectRole

Represents a message delta i.e. any changed fields on a message during streaming.

object Enum: MessageDeltaObjectType

role Enum: CreateMessageRequestRole

object Enum: DeleteMessageResponseObject

References an image File in the content of a message.

type Enum: MessageContentImageFileObjectType

The text content that is part of a message.

type Enum: messageContentTextObjectType

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "retrieval" tool to search files.

type Enum: FileCitationObjectType

A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.

type Enum: FilePathObjectType

References an image File in the content of a message.

type Enum: MessageDeltaContentImageFileObjectType

The text content that is part of a message.

type Enum: MessageDeltaContentTextObjectType

A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.

type Enum: MessageDeltaContentTextAnnotationsFileCitationObjectType

A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.

type Enum: MessageDeltaContentTextAnnotationsFilePathObjectType

Represents a step in execution of a run.

object Enum: RunStepObjectType

type Enum: RunStepObjectType

status Enum: RunStepObjectStatus

Represents a run step delta i.e. any changed fields on a run step during streaming.

object Enum: RunStepDeltaObjectType

Details of the message creation by the run step.

type Enum: RunStepDetailsMessageCreationObjectType

Details of the message creation by the run step.

type Enum: RunStepDeltaStepDetailsMessageCreationObjectType

Details of the tool call.

type Enum: RunStepDetailsToolCallsObjectType

Details of the tool call.

type Enum: RunStepDeltaStepDetailsToolCallsObjectType

Details of the Code Interpreter tool call the run step was involved in.

type Enum: RunStepDetailsToolCallsCodeObjectType

Details of the Code Interpreter tool call the run step was involved in.

type Enum: RunStepDeltaStepDetailsToolCallsCodeObjectType

Text output from the Code Interpreter tool call as part of a run step.

type Enum: RunStepDetailsToolCallsCodeOutputLogsObjectType

Text output from the Code Interpreter tool call as part of a run step.

type Enum: RunStepDeltaStepDetailsToolCallsCodeOutputLogsObjectType

type Enum: RunStepDetailsToolCallsCodeOutputImageObjectType

type Enum: RunStepDeltaStepDetailsToolCallsCodeOutputImageObject

type Enum: RunStepDetailsToolCallsFileSearchObjectType

A result instance of the file search.

type Enum: RunStepDeltaStepDetailsToolCallsFileSearchObjectType

type Enum: RunStepDetailsToolCallsFunctionObjectType

type Enum: RunStepDetailsToolCallsFunctionObjectType

The expiration policy for a vector store.

anchor Enum: VectorStoreExpirationAfterAnchor

A vector store is a collection of processed files can be used by the file_search tool.

status Enum: VectorStoreObjectStatus

object Enum: DeleteVectorStoreResponseObject

A list of files attached to a vector store.

object Enum: VectorStoreFileObjectType

status Enum: VectorStoreFileObjectStatus

This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the chunking_strategy concept was introduced in the API.

type Enum: OtherChunkingStrategyResponseParamType

type Enum: StaticChunkingStrategyResponseParamType

The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

This component can be one of the following:

• autoChunkingStrategyRequestParam
• staticChunkingStrategyRequestParam

object Enum: DeleteVectorStoreFileResponseObject

A batch of files attached to a vector store.

object Enum: VectorStoreFileBatchObjectType

status Enum: VectorStoreFileBatchObjectStatus

Represents an event emitted when streaming a Run.

Each event in a server-sent events stream has an event and data property:

event: thread.created
data: {"id": "thread_123", "object": "thread", ...}

We emit events whenever a new object is created, transitions to a new state, or is being streamed in parts (deltas). For example, we emit thread.run.created when a new run is created, thread.run.completed when a run completes, and so on. When an Assistant chooses to create a message during a run, we emit a thread.message.created event, a thread.message.in_progress event, many thread.message.delta events, and finally a thread.message.completed event.

We may add additional events over time, so we recommend handling unknown events gracefully in your code.

This component can be one of the following:

• threadStreamEvent
• runStreamEvent
• runStepStreamEvent
• messageStreamEvent
• errorEvent
• doneEvent

This component can be one of the following:

Occurs when a new thread is created.

Data: threadObject

Event Enum: ThreadStreamEventEnum

---

This component can be one of the following:

Occurs when a new run is created.

Data: runObject

Event Enum: RunStreamEventCreated

---

Occurs when a run moves to a queued status.

Data: runObject

Event Enum: RunStreamEventQueued

---

Occurs when a run moves to an in_progress status.

Data: runObject

Event Enum: RunStreamEventInProgress

---

Occurs when a run moves to a requires_action status.

Data: runObject

Event Enum: RunStreamEventRequiresAction

---

Occurs when a run is completed.

Data: runObject

Event Enum: RunStreamEventCompleted

---

Occurs when a run fails.

Data: runObject

Event Enum: RunStreamEventFailed

---

Occurs when a run moves to a cancelling status.

Data: runObject

Event Enum: RunStreamEventCancelling

---

Occurs when a run is cancelled.

Data: runObject

Event Enum: RunStreamEventCancelled

---

Occurs when a run expires.

Data: runObject

Event Enum: RunStreamEventExpired

---

This component can be one of the following:

Occurs when a run step is created.

Data: runStepObject

Event Enum: RunStepStreamEventCreated

---

Occurs when a run step moves to an in_progress state.

Data: runStepObject

Event Enum: RunStepStreamEventInProgress

---

Occurs when parts of a run step are being streamed.

Data: runStepDeltaObject

Event Enum: RunStepStreamEventDelta

---

Occurs when a run step is completed.

Data: runStepObject

Event Enum: RunStepStreamEventCompleted

---

Occurs when a run step fails.

Data: runStepObject

Event Enum: RunStepStreamEventFailed

---

Occurs when a run step is cancelled.

Data: runStepObject

Event Enum: RunStepStreamEventCancelled

---

Occurs when a run step expires.

Data: runStepObject

Event Enum: RunStepStreamEventExpired

---

This component can be one of the following:

Occurs when a message is created.

Data: messageObject

Event Enum: MessageStreamEventCreated

---

Occurs when a message moves to an in_progress state.

Data: messageObject

Event Enum: MessageStreamEventInProgress

---

Occurs when parts of a message are being streamed.

Data: messageDeltaObject

Event Enum: MessageStreamEventDelta

---

Occurs when a message is completed.

Data: messageObject

Event Enum: MessageStreamEventCompleted

---

Occurs when a message ends before it is completed.

Data: messageObject

Event Enum: MessageStreamEventIncomplete

---

This component can be one of the following:

• FileCitation
• UrlCitation
• FilePath

A click action.

The output of a code interpreter tool call that is a file.

The output of a code interpreter tool call that is text.

A tool that runs code.

A tool call to run code.

This component can be one of the following:

• CodeInterpreterTextOutput
• CodeInterpreterFileOutput

A filter used to compare a specified attribute key to a given value using a defined comparison operation.

Combine multiple filters using and or or.

This component can be one of the following:

• Click
• DoubleClick
• Drag
• KeyPress
• Move
• Screenshot
• Scroll
• Type
• Wait

A computer screenshot image used with the computer use tool.

A tool that controls a virtual computer.

A tool call to a computer use tool.

The output of a computer tool call.

A pending safety check for the computer call.

Multi-modal input and output contents.

This component can be one of the following:

• InputContent
• OutputContent

An x/y coordinate pair, e.g. { x: 100, y: 200 }.

A double click action.

A drag action.

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role. Messages with the assistant role are presumed to have been generated by the model in previous interactions.

A citation to a file.

A path to a file.

The ranker to use for the file search. If not specified will use the auto ranker.

A tool that searches for relevant content from uploaded files.

The results of a file search tool call. See the

Defines a function in your own code the model can choose to call. Learn more about function calling.

A tool call to run a function. See the

The output of a function tool call.

Specify additional output data to include in the model response. Currently supported values are:

• file_search_call.results: Include the search results of the file search tool call.
• message.input_image.image_url: Include image urls from the input message.
• computer_call_output.output.image_url: Include image urls from the computer call output.

An audio input to the model.

This component can be one of the following:

• InputText
• InputImage
• InputFile

A file input to the model.

An image input to the model.

This component uses the property type to discriminate between different types:

This component can be one of the following:

• EasyInputMessage
• Item
• ItemReference

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.

A list of one or many input items to the model, containing different content types.

No properties defined for this component.

A text input to the model.

Content item used to generate a response.

This component can be one of the following:

• InputMessage
• OutputMessage
• FileSearchToolCall
• ComputerToolCall
• ComputerToolCallOutput
• FunctionToolCall
• FunctionToolCallOutput
• ReasoningItem

An internal identifier for an item to reference.

Content item used to generate a response.

This component can be one of the following:

• InputMessageResource
• OutputMessage
• FileSearchToolCall
• ComputerToolCall
• ComputerToolCallOutputResource
• FunctionToolCall
• FunctionToolCallOutputResource

A collection of keypresses the model would like to perform.

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

No properties defined for this component.

A mouse move action.

An audio output from the model.

This component can be one of the following:

• OutputText
• Refusal

An output message from the model.

A text output from the model.

o-series models only

Configuration options for reasoning models.

A description of the chain of thought used by a reasoning model while generating a response.

A refusal from the model.

Emitted when there is a partial audio response.

Emitted when the audio response is complete.

Emitted when there is a partial transcript of audio.

Emitted when the full audio transcript is completed.

Emitted when a partial code snippet is added by the code interpreter.

Emitted when code snippet output is finalized by the code interpreter.

Emitted when the code interpreter call is completed.

Emitted when a code interpreter call is in progress.

Emitted when the code interpreter is actively interpreting the code snippet.

Emitted when the model response is complete.

Emitted when a new content part is added.

Emitted when a content part is done.

An event that is emitted when a response is created.

An error object returned when the model fails to generate a Response.

The error code for the response.

Emitted when an error occurs.

An event that is emitted when a response fails.

Emitted when a file search call is completed (results found).

Emitted when a file search call is initiated.

Emitted when a file search is currently searching.

Emitted when there is a partial function-call arguments delta.

Emitted when function-call arguments are finalized.

Emitted when the response is in progress.

An event that is emitted when a response finishes as incomplete.

A list of Response items.

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

No properties defined for this component.

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

This API will soon support other output modalities, including audio and images.

No properties defined for this component.

Emitted when a new output item is added.

Emitted when an output item is marked done.

Emitted when there is a partial refusal text.

Emitted when refusal text is finalized.

Emitted when a text annotation is added.

Emitted when there is an additional text delta.

Emitted when text content is finalized.

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.

A screenshot action.

A scroll action.

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

This component can be one of the following:

An object specifying the format that the model must output.

Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema.

The default format is { "type": "text" } with no additional options.

Not recommended for gpt-4o and newer models:

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

This component can be one of the following:

• ResponseFormatText
• TextResponseFormatJsonSchema
• ResponseFormatJsonObject

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

This component can be one of the following:

• FileSearchTool
• FunctionTool
• ComputerTool

Use this option to force the model to call a specific function.

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.

Indicates that the model should use a built-in tool to generate a response.

An action to type in text.

A citation for a web resource used to generate a model response.

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.

No properties defined for this component.

Represents the parsed content of a vector store file.

A wait action.

o-series models only

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Occurs when an error occurs. This can happen due to an internal server error or a timeout.

event Enum: ErrorEventEnum

Occurs when a stream ends.

event Enum: DoneEventEnum

data Enum: DoneEventDataEnum

Learn about Models, and fine-tuning with the REST API. Learn more about the underlying models that power Azure OpenAI.