Azure OpenAI in Azure AI Foundry Models authoring REST API preview reference

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

API specs

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.

Authentication

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.

REST API versioning

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

Data plane authoring

The rest of the article covers the latest preview release of the Azure OpenAI data plane inference specification, 2025-04-01-preview.

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

Batch - List

GET {endpoint}/openai/batches?api-version=2025-04-01-preview

Gets a list of all batches owned by the Azure OpenAI resource.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/batches?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "has_more": false,
    "data": [
      {
        "object": "batch",
        "id": "batch_72a2792ef7d24ba7b82c7fe4a37e379f",
        "endpoint": "/chat/completions",
        "errors": null,
        "input_file_id": "file-b4fa7277f3eb4722ac18b90f46102c3f",
        "completion_window": "24h",
        "status": "completed",
        "output_file_id": "file-f2ddaf43-b48b-46dd-b264-90da10c7a85b",
        "error_file_id": "file-c3b563b0-ebc7-47da-93e3-a2fa694aef0c",
        "created_at": 1646126127,
        "in_progress_at": 1646126130,
        "expires_at": 1646126170,
        "finalizing_at": 1646126134,
        "completed_at": 1646126136,
        "failed_at": null,
        "expired_at": null,
        "cancelling_at": null,
        "cancelled_at": null,
        "request_counts": {
          "total": 500,
          "completed": 400,
          "failed": 100
        },
        "first_id": "batch_abc123",
        "last_id": "batch_abc456",
        "metadata": {
          "batch_description": "Evaluation job"
        }
      }
    ],
    "object": "list"
  }
}

Batch - Create

POST {endpoint}/openai/batches?api-version=2025-04-01-preview

Creates and executes a batch from an uploaded file of requests.

Response includes details of the enqueued job including job status.

The ID of the result file is added to the response once complete.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Responses

Status Code: 201

Description: The batch has been successfully created.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/batches?api-version=2025-04-01-preview

Responses: Status Code: 201

{
  "headers": {
    "deployment-enqueued-tokens": 1000,
    "deployment-maximum-enqueued-tokens": 5000
  },
  "body": {
    "object": "batch",
    "id": "batch_72a2792ef7d24ba7b82c7fe4a37e379f",
    "endpoint": "/chat/completions",
    "errors": null,
    "input_file_id": "file-b4fa7277f3eb4722ac18b90f46102c3f",
    "completion_window": "24h",
    "status": "validating",
    "output_file_id": null,
    "error_file_id": null,
    "created_at": 1646126127,
    "in_progress_at": null,
    "expires_at": null,
    "finalizing_at": null,
    "completed_at": null,
    "failed_at": null,
    "expired_at": null,
    "cancelling_at": null,
    "cancelled_at": null,
    "request_counts": {
      "total": 0,
      "completed": 0,
      "failed": 0
    },
    "metadata": {
      "batch_description": "Evaluation job"
    }
  }
}

Batch - Get

GET {endpoint}/openai/batches/{batch-id}?api-version=2025-04-01-preview

Gets details for a single batch specified by the given batch-id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/batches/{batch-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "batch",
    "id": "batch_72a2792ef7d24ba7b82c7fe4a37e379f",
    "endpoint": "/chat/completions",
    "errors": null,
    "input_file_id": "file-b4fa7277f3eb4722ac18b90f46102c3f",
    "completion_window": "24h",
    "status": "completed",
    "output_file_id": "file-f2ddaf43-b48b-46dd-b264-90da10c7a85b",
    "error_file_id": "file-c3b563b0-ebc7-47da-93e3-a2fa694aef0c",
    "created_at": 1646126127,
    "in_progress_at": 1646126130,
    "expires_at": 1646126170,
    "finalizing_at": 1646126134,
    "completed_at": 1646126136,
    "failed_at": null,
    "expired_at": null,
    "cancelling_at": null,
    "cancelled_at": null,
    "request_counts": {
      "total": 500,
      "completed": 400,
      "failed": 100
    },
    "metadata": {
      "batch_description": "Evaluation job"
    }
  }
}

Batch - Cancel

POST {endpoint}/openai/batches/{batch-id}/cancel?api-version=2025-04-01-preview

Cancels the processing of the batch specified by the given batch-id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The batch has been successfully canceled.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/batches/{batch-id}/cancel?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "batch",
    "id": "batch_72a2792ef7d24ba7b82c7fe4a37e379f",
    "endpoint": "/chat/completions",
    "errors": null,
    "input_file_id": "file-b4fa7277f3eb4722ac18b90f46102c3f",
    "completion_window": "24h",
    "status": "cancelling",
    "output_file_id": null,
    "error_file_id": null,
    "created_at": 1646126127,
    "in_progress_at": 1646126130,
    "expires_at": 1646126170,
    "finalizing_at": null,
    "completed_at": null,
    "failed_at": null,
    "expired_at": null,
    "cancelling_at": 1646126138,
    "cancelled_at": null,
    "request_counts": {
      "total": 500,
      "completed": 100,
      "failed": 5
    },
    "metadata": {
      "batch_description": "Evaluation job"
    }
  }
}

Stored completion - List

GET {endpoint}/openai/chat/completions?api-version=2025-04-01-preview

Gets list of stored completions.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/chat/completions?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "list",
    "data": [
      {
        "id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
        "model": "gpt-4o-mini-2024-07-18",
        "created": 1738193475,
        "request_id": "e539c139-a97d-4ee1-bde9-3be3d5c6edb5",
        "usage": {
          "total_tokens": 25,
          "completion_tokens": 7,
          "prompt_tokens": 18
        },
        "seed": 123,
        "top_p": 1,
        "temperature": 1,
        "presence_penalty": 0,
        "frequency_penalty": 0,
        "system_fingerprint": "fp_f3927aa00d",
        "metadata": {
          "key_1": "val_1",
          "key_2": "val_2"
        },
        "choices": [
          {
            "index": 0,
            "message": {
              "content": "Hello, how are you?",
              "role": "assistant"
            },
            "finish_reason": "stop"
          }
        ]
      }
    ],
    "total": 1,
    "first_id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "last_id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "has_more": false
  }
}

Stored completion - Get

GET {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Gets stored completion by the given stored completion id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "chat.completion",
    "id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "model": "gpt-4o-mini-2024-07-18",
    "created": 1738193475,
    "request_id": "e539c139-a97d-4ee1-bde9-3be3d5c6edb5",
    "usage": {
      "total_tokens": 25,
      "completion_tokens": 7,
      "prompt_tokens": 18
    },
    "seed": 123,
    "top_p": 1,
    "temperature": 1,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "system_fingerprint": "fp_f3927aa00d",
    "metadata": {
      "key_1": "val_1",
      "key_2": "val_2"
    },
    "choices": [
      {
        "index": 0,
        "message": {
          "content": "Hello, how are you?",
          "role": "assistant"
        },
        "finish_reason": "stop"
      }
    ]
  }
}

Stored completion - Update

POST {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Update stored completion by the given stored completion id.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "chat.completion",
    "id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "model": "gpt-4o-mini-2024-07-18",
    "created": 1738193475,
    "request_id": "e539c139-a97d-4ee1-bde9-3be3d5c6edb5",
    "usage": {
      "total_tokens": 25,
      "completion_tokens": 7,
      "prompt_tokens": 18
    },
    "seed": 123,
    "top_p": 1,
    "temperature": 1,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "system_fingerprint": "fp_f3927aa00d",
    "metadata": {
      "key_1": "val_1",
      "key_2": "val_2"
    },
    "choices": [
      {
        "index": 0,
        "message": {
          "content": "Hello, how are you?",
          "role": "assistant"
        },
        "finish_reason": "stop"
      }
    ]
  }
}

Stored completion - Delete

DELETE {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Delete stored completion by the given stored completion id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The stored completion was successfully deleted.

Status Code: default

Description: An error occurred.

Examples

DELETE {endpoint}/openai/chat/completions/{stored-completion-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "chat.completion.deleted",
    "id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "deleted": true
  }
}

Stored completion - Getmessages

GET {endpoint}/openai/chat/completions/{stored-completion-id}/messages?api-version=2025-04-01-preview

Gets stored completion messages by the given stored completion id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/chat/completions/{stored-completion-id}/messages?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "list",
    "data": [
      {
        "role": "user",
        "content": "Hello"
      }
    ],
    "total": 1,
    "first_id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "last_id": "chatcmpl-AvBCKqg2xqxVHCCEnUB4Bgj1Bjl7Y",
    "has_more": false
  }
}

Evaluation - Get list

GET {endpoint}/openai/evals?api-version=2025-04-01-preview

List evaluations for a project.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: A list of evals

Examples

GET {endpoint}/openai/evals?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "list",
    "data": [
      {
        "object": "eval",
        "id": "eval_6801694950848190b10968bb628b651d",
        "data_source_config": {
          "type": "custom",
          "schema": {
            "type": "object",
            "properties": {
              "item": {
                "type": "object",
                "properties": {
                  "question": {
                    "type": "string"
                  },
                  "A": {
                    "type": "string"
                  },
                  "B": {
                    "type": "string"
                  },
                  "C": {
                    "type": "string"
                  },
                  "D": {
                    "type": "string"
                  },
                  "answer": {
                    "type": "string"
                  }
                }
              }
            },
            "required": [
              "item"
            ]
          }
        },
        "testing_criteria": [
          {
            "name": "string check",
            "type": "string_check",
            "input": "{{sample.output_text}}",
            "reference": "{{item.answer}}",
            "operation": "eq"
          }
        ],
        "name": "Math Quiz",
        "created_at": 1744922953,
        "metadata": {}
      }
    ],
    "first_id": "eval_6801694950848190b10968bb628b651d",
    "last_id": "eval_6801694950848190b10968bb628b651d",
    "has_more": false
  }
}

Evaluation - Create

POST {endpoint}/openai/evals?api-version=2025-04-01-preview

Create the structure of an evaluation that can be used to test a model's performance. An evaluation is a set of testing criteria and a datasource. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources.

URI Parameters

Request Header

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

Responses

Status Code: 201

Description: OK

Examples

POST {endpoint}/openai/evals?api-version=2025-04-01-preview

{
 "name": "Math Quiz",
 "data_source_config": {
  "type": "custom",
  "include_sample_schema": true,
  "item_schema": {
   "type": "object",
   "properties": {
    "question": {
     "type": "string"
    },
    "A": {
     "type": "string"
    },
    "B": {
     "type": "string"
    },
    "C": {
     "type": "string"
    },
    "D": {
     "type": "string"
    },
    "answer": {
     "type": "string"
    }
   }
  }
 },
 "testing_criteria": [
  {
   "type": "string_check",
   "reference": "{{item.answer}}",
   "input": "{{sample.output_text}}",
   "operation": "eq",
   "name": "string check"
  }
 ]
}

Responses: Status Code: 201

{
  "headers": {},
  "body": {
    "object": "eval",
    "id": "eval_6801694950848190b10968bb628b651d",
    "data_source_config": {
      "type": "custom",
      "schema": {
        "type": "object",
        "properties": {
          "item": {
            "type": "object",
            "properties": {
              "question": {
                "type": "string"
              },
              "A": {
                "type": "string"
              },
              "B": {
                "type": "string"
              },
              "C": {
                "type": "string"
              },
              "D": {
                "type": "string"
              },
              "answer": {
                "type": "string"
              }
            }
          }
        },
        "required": [
          "item"
        ]
      }
    },
    "testing_criteria": [
      {
        "name": "string check",
        "type": "string_check",
        "input": "{{sample.output_text}}",
        "reference": "{{item.answer}}",
        "operation": "eq"
      }
    ],
    "name": "Math Quiz",
    "created_at": 1744922953,
    "metadata": {}
  }
}

Evaluation - Delete

DELETE {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

Delete an evaluation.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Successfully deleted the evaluation.

Status Code: 404

Description: Evaluation not found.

Examples

DELETE {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval.deleted",
    "deleted": true,
    "eval_id": "eval_6801694950848190b10968bb628b651d"
  }
}

Status Code: 404

{
  "headers": {},
  "body": {
    "code": "notFound",
    "message": "Evaluation with ID eval_6801694950848190b10968bb628b651d not found."
  }
}

Evaluation - Get

GET {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

Get an evaluation by ID.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The evaluation

Examples

GET {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval",
    "id": "eval_6801694950848190b10968bb628b651d",
    "data_source_config": {
      "type": "custom",
      "schema": {
        "type": "object",
        "properties": {
          "item": {
            "type": "object",
            "properties": {
              "question": {
                "type": "string"
              },
              "A": {
                "type": "string"
              },
              "B": {
                "type": "string"
              },
              "C": {
                "type": "string"
              },
              "D": {
                "type": "string"
              },
              "answer": {
                "type": "string"
              }
            }
          }
        },
        "required": [
          "item"
        ]
      }
    },
    "testing_criteria": [
      {
        "name": "string check",
        "type": "string_check",
        "input": "{{sample.output_text}}",
        "reference": "{{item.answer}}",
        "operation": "eq"
      }
    ],
    "name": "Math Quiz",
    "created_at": 1744922953,
    "metadata": {}
  }
}

Evaluation - Update

POST {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

Update certain properties of an evaluation.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The updated evaluation

Examples

POST {endpoint}/openai/evals/{eval-id}?api-version=2025-04-01-preview

{
 "name": "Updated Math Quiz",
 "metadata": {
  "description": "Updated description"
 }
}

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval",
    "id": "eval_6801694950848190b10968bb628b651d",
    "data_source_config": {
      "type": "custom",
      "schema": {
        "type": "object",
        "properties": {
          "item": {
            "type": "object",
            "properties": {
              "question": {
                "type": "string"
              },
              "A": {
                "type": "string"
              },
              "B": {
                "type": "string"
              },
              "C": {
                "type": "string"
              },
              "D": {
                "type": "string"
              },
              "answer": {
                "type": "string"
              }
            }
          }
        },
        "required": [
          "item"
        ]
      }
    },
    "testing_criteria": [
      {
        "name": "string check",
        "type": "string_check",
        "input": "{{sample.output_text}}",
        "reference": "{{item.answer}}",
        "operation": "eq"
      }
    ],
    "name": "Updated Math Quiz",
    "created_at": 1744922953,
    "metadata": {
      "description": "Updated description"
    }
  }
}

Evaluation - Getrunlist

GET {endpoint}/openai/evals/{eval-id}/runs?api-version=2025-04-01-preview

Get a list of runs for an evaluation.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: A list of runs for the evaluation

Examples

GET {endpoint}/openai/evals/{eval-id}/runs?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "list",
    "data": [
      {
        "object": "eval.run",
        "id": "evalrun_68016a056f0481909b9774447bdd1aa3",
        "eval_id": "eval_6801694950848190b10968bb628b651d",
        "report_url": "https://ai.azure.com/resource/evaluation",
        "status": "queued",
        "model": "gpt-4o-mini",
        "name": "Math quiz",
        "created_at": 1744923141,
        "result_counts": {
          "total": 0,
          "errored": 0,
          "failed": 0,
          "passed": 0
        },
        "per_model_usage": null,
        "per_testing_criteria_results": null,
        "data_source": {
          "type": "completions",
          "source": {
            "type": "file_content",
            "content": [
              {
                "item": {
                  "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
                  "A": "0",
                  "B": "4",
                  "C": "2",
                  "D": "6",
                  "answer": "B"
                }
              },
              {
                "item": {
                  "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
                  "A": "8",
                  "B": "2",
                  "C": "24",
                  "D": "120",
                  "answer": "C"
                }
              }
            ]
          },
          "input_messages": {
            "template": [
              {
                "type": "message",
                "role": "system",
                "content": {
                  "text": "Answer the question's with A, B, C, or D."
                }
              },
              {
                "type": "message",
                "role": "user",
                "content": {
                  "text": "Question: {{item.question}} A: {{item.A}} B: {{item.B}} C: {{item.C}} D: {{item.D}}."
                }
              }
            ]
          },
          "model": "gpt-4o-mini",
          "sampling_params": {
            "seed": 42,
            "temperature": 1,
            "top_p": 1
          }
        },
        "error": null,
        "metadata": {}
      }
    ],
    "first_id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "last_id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "has_more": false
  }
}

Evaluation - Create run

POST {endpoint}/openai/evals/{eval-id}/runs?api-version=2025-04-01-preview

Create a new evaluation run. This is the endpoint that will kick off grading.

URI Parameters

Request Header

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

Responses

Status Code: 201

Description: Successfully created a run for the evaluation

Status Code: 400

Description: Bad request (for example, missing eval object)

Examples

POST {endpoint}/openai/evals/{eval-id}/runs?api-version=2025-04-01-preview

{
 "name": "Math quiz",
 "data_source": {
  "type": "completions",
  "source": {
   "type": "file_content",
   "content": [
    {
     "item": {
      "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
      "A": "0",
      "B": "4",
      "C": "2",
      "D": "6",
      "answer": "B"
     }
    },
    {
     "item": {
      "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
      "A": "8",
      "B": "2",
      "C": "24",
      "D": "120",
      "answer": "C"
     }
    }
   ]
  },
  "input_messages": {
   "type": "template",
   "template": [
    {
     "type": "message",
     "role": "system",
     "content": {
      "text": "Answer the question's with A, B, C, or D."
     }
    },
    {
     "type": "message",
     "role": "user",
     "content": {
      "text": "Question: {{item.question}} A: {{item.A}} B: {{item.B}} C: {{item.C}} D: {{item.D}}."
     }
    }
   ]
  },
  "model": "gpt-4o-mini",
  "sampling_params": {
   "temperature": 1,
   "top_p": 1,
   "seed": 42
  }
 }
}

Responses: Status Code: 201

{
  "headers": {},
  "body": {
    "object": "eval.run",
    "id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "eval_id": "eval_6801694950848190b10968bb628b651d",
    "report_url": "https://ai.azure.com/resource/evaluation",
    "status": "queued",
    "model": "gpt-4o-mini",
    "name": "Math quiz",
    "created_at": 1744923141,
    "result_counts": {
      "total": 0,
      "errored": 0,
      "failed": 0,
      "passed": 0
    },
    "per_model_usage": null,
    "per_testing_criteria_results": null,
    "data_source": {
      "type": "completions",
      "source": {
        "type": "file_content",
        "content": [
          {
            "item": {
              "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
              "A": "0",
              "B": "4",
              "C": "2",
              "D": "6",
              "answer": "B"
            }
          },
          {
            "item": {
              "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
              "A": "8",
              "B": "2",
              "C": "24",
              "D": "120",
              "answer": "C"
            }
          }
        ]
      },
      "input_messages": {
        "type": "template",
        "template": [
          {
            "type": "message",
            "role": "system",
            "content": {
              "text": "Answer the question's with A, B, C, or D."
            }
          },
          {
            "type": "message",
            "role": "user",
            "content": {
              "text": "Question: {{item.question}} A: {{item.A}} B: {{item.B}} C: {{item.C}} D: {{item.D}}."
            }
          }
        ]
      },
      "model": "gpt-4o-mini",
      "sampling_params": {
        "seed": 42,
        "temperature": 1,
        "top_p": 1
      }
    },
    "error": null,
    "metadata": {}
  }
}

Evaluation - Delete run

DELETE {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Delete an eval run.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Successfully deleted the eval run

Status Code: 404

Description: Run not found

Examples

DELETE {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval.deleted",
    "deleted": true,
    "run_id": "evalrun_68016a056f0481909b9774447bdd1aa3"
  }
}

Status Code: 404

{
  "headers": {},
  "body": {
    "code": "notFound",
    "message": "Evaluation Run with ID evalrun_68016a056f0481909b9774447bdd1aa3 not found."
  }
}

Evaluation - Get run

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Get an evaluation run by ID.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The evaluation run

Examples

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval.run",
    "id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "eval_id": "eval_6801694950848190b10968bb628b651d",
    "report_url": "https://ai.azure.com/resource/evaluation",
    "status": "queued",
    "model": "gpt-4o-mini",
    "name": "Math quiz",
    "created_at": 1744923141,
    "result_counts": {
      "total": 0,
      "errored": 0,
      "failed": 0,
      "passed": 0
    },
    "per_model_usage": null,
    "per_testing_criteria_results": null,
    "data_source": {
      "type": "completions",
      "source": {
        "type": "file_content",
        "content": [
          {
            "item": {
              "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
              "A": "0",
              "B": "4",
              "C": "2",
              "D": "6",
              "answer": "B"
            }
          },
          {
            "item": {
              "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
              "A": "8",
              "B": "2",
              "C": "24",
              "D": "120",
              "answer": "C"
            }
          }
        ]
      },
      "input_messages": {
        "type": "template",
        "template": [
          {
            "type": "message",
            "role": "system",
            "content": {
              "text": "Answer the question's with A, B, C, or D."
            }
          },
          {
            "type": "message",
            "role": "user",
            "content": {
              "text": "Question: {{item.question}} A: {{item.A}} B: {{item.B}} C: {{item.C}} D: {{item.D}}."
            }
          }
        ]
      },
      "model": "gpt-4o-mini",
      "sampling_params": {
        "seed": 42,
        "temperature": 1,
        "top_p": 1
      }
    },
    "error": null,
    "metadata": {}
  }
}

Evaluation - Cancel run

POST {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Cancel an ongoing evaluation run.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The canceled eval run object

Examples

POST {endpoint}/openai/evals/{eval-id}/runs/{run-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval.run",
    "id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "eval_id": "eval_6801694950848190b10968bb628b651d",
    "report_url": "https://ai.azure.com/resource/evaluation",
    "status": "canceled",
    "model": "gpt-4o-mini",
    "name": "Math quiz",
    "created_at": 1744923141,
    "result_counts": {
      "total": 0,
      "errored": 0,
      "failed": 0,
      "passed": 0
    },
    "per_model_usage": null,
    "per_testing_criteria_results": null,
    "data_source": {
      "type": "completions",
      "source": {
        "type": "file_content",
        "content": [
          {
            "item": {
              "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
              "A": "0",
              "B": "4",
              "C": "2",
              "D": "6",
              "answer": "B"
            }
          },
          {
            "item": {
              "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
              "A": "8",
              "B": "2",
              "C": "24",
              "D": "120",
              "answer": "C"
            }
          }
        ]
      },
      "input_messages": {
        "type": "template",
        "template": [
          {
            "type": "message",
            "role": "system",
            "content": {
              "text": "Answer the question's with A, B, C, or D."
            }
          },
          {
            "type": "message",
            "role": "user",
            "content": {
              "text": "Question: {{item.question}} A: {{item.A}} B: {{item.B}} C: {{item.C}} D: {{item.D}}."
            }
          }
        ]
      },
      "model": "gpt-4o-mini",
      "sampling_params": {
        "seed": 42,
        "temperature": 1,
        "top_p": 1
      }
    },
    "error": null,
    "metadata": {}
  }
}

Evaluation - Getrunoutputitems

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}/output_items?api-version=2025-04-01-preview

Get a list of output items for an evaluation run.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: A list of output items for the evaluation run

Examples

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}/output_items?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "list",
    "data": [
      {
        "object": "eval.run.output_item",
        "id": "outputitem_68017251ff3881908bf5096bf4cd91c6",
        "created_at": 1744925265,
        "run_id": "evalrun_68016a056f0481909b9774447bdd1aa3",
        "eval_id": "eval_6801694950848190b10968bb628b651d",
        "status": "fail",
        "datasource_item_id": 1,
        "datasource_item": {
          "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
          "A": "8",
          "B": "2",
          "C": "24",
          "D": "120",
          "answer": "C"
        },
        "results": [
          {
            "name": "string check-63b1fffa-bee6-4c37-ae77-ed46e3dce2b7",
            "sample": null,
            "passed": false,
            "score": 0
          }
        ],
        "sample": {
          "input": [
            {
              "role": "system",
              "content": "Answer the question's with A, B, C, or D.",
              "function_call": null
            },
            {
              "role": "user",
              "content": "Question: Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5. A: 8 B: 2 C: 24 D: 120.",
              "function_call": null
            }
          ],
          "output": [
            {
              "role": "assistant",
              "content": "To find the index of the subgroup generated by the permutation \\( p = (1, 2, 5, 4)(2, 3) \\) in \\( S_5 \\), we first need to determine the order of \\( p \\).\n\n1. The cycle \\( (1, 2, 5, 4) \\) has length 4.\n2. The cycle \\( (2, 3) \\) has length 2.\n3. The least common multiple (LCM) of these lengths gives the order of the permutation \\( p \\).\n\nCalculating the LCM:\n\\[\n\\text{lcm}(4, 2) = 4\n\\]\nThus, the order of \\( p \\) is 4.\n\nNext, we find the size of the subgroup \\( \\langle p \\rangle \\):\n- The size of \\( \\langle p \\rangle \\) is equal to the order of \\( p \\), which is 4.\n\nNow, we know the size of \\( S_5 \\):\n\\[\n|S_5| = 5! = 120\n\\]\n\nFinally, to find the index of \\( \\langle p \\rangle \\) in \\( S_5 \\), we use the formula:\n\\[\n\\text{index} = \\frac{|S_5|}{|\\langle p \\rangle|} = \\frac{120}{4} = 30\n\\]\n\nHowever, the available answer choices do not include 30. There may be a mistake because the question expects an answer among A, B, C, and D.\n\nLet\u00e2\u20ac\u2122s assume we misunderstood \\( \\langle p \\rangle \\), and instead, we can deduce based solely on given answers looking for a relation to \\( S_5 \\) without delving into detailed subgroup tracks. \n\nSince \\( S_5 \\) has 30 different elements in a subgroup configuration, the closest answer physically relating as long as \\( p \\) covers two elements effectively would logically fit an answer of 120 / 60 which has no direct relationship.\n\nGiven the option choices and specific rank formulations as often made regarding elements in specific construct the subgroup at best reflects around a viable ratio of parts allowed through available indices. \n\nThus, after reasoning through which aligns most structurally geometrically yielding across all configurations possible integrated yet arrives leading \\( p \\) through neighborhood distributions leaving reflections outstanding:\n\n\n\nThe correct answer is:\n**C: 24**\n\nHowever per the discussion migrating \\( p \\) may leave various pathways leading ultimately toward that framing in modeling. Always a good suggestion confirming the elements group generating any possible in outputs rationales. ",
              "function_call": null
            }
          ],
          "finish_reason": "stop",
          "model": "gpt-4o-mini-2024-07-18",
          "usage": {
            "total_tokens": 627,
            "completion_tokens": 546,
            "prompt_tokens": 81,
            "cached_tokens": 0
          },
          "error": null,
          "temperature": 1,
          "top_p": 1,
          "seed": 42
        }
      },
      {
        "object": "eval.run.output_item",
        "id": "outputitem_6801724f54888190942ec66a197309dd",
        "created_at": 1744925263,
        "run_id": "evalrun_68016a056f0481909b9774447bdd1aa3",
        "eval_id": "eval_6801694950848190b10968bb628b651d",
        "status": "fail",
        "datasource_item_id": 0,
        "datasource_item": {
          "question": "Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q.",
          "A": "0",
          "B": "4",
          "C": "2",
          "D": "6",
          "answer": "B"
        },
        "results": [
          {
            "name": "string check-63b1fffa-bee6-4c37-ae77-ed46e3dce2b7",
            "sample": null,
            "passed": false,
            "score": 0
          }
        ],
        "sample": {
          "input": [
            {
              "role": "system",
              "content": "Answer the question's with A, B, C, or D.",
              "function_call": null
            },
            {
              "role": "user",
              "content": "Question: Find the degree for the given field extension Q(sqrt(2), sqrt(3), sqrt(18)) over Q. A: 0 B: 4 C: 2 D: 6.",
              "function_call": null
            }
          ],
          "output": [
            {
              "role": "assistant",
              "content": "To find the degree of the field extension \\(\\mathbb{Q}(\\sqrt{2}, \\sqrt{3}, \\sqrt{18})\\) over \\(\\mathbb{Q}\\), we can simplify \\(\\sqrt{18}\\) since \\(\\sqrt{18} = \\sqrt{9 \\cdot 2} = 3\\sqrt{2}\\). \n\nThus, the field can be rewritten as \\(\\mathbb{Q}(\\sqrt{2}, \\sqrt{3})\\).\n\nNext, we calculate the degree of the extensions step by step:\n\n1. The extension \\(\\mathbb{Q}(\\sqrt{2})\\) over \\(\\mathbb{Q}\\) has degree 2, since \\(\\sqrt{2}\\) is not in \\(\\mathbb{Q}\\) and satisfies the polynomial \\(x^2 - 2\\).\n\n2. Next, we consider the extension \\(\\mathbb{Q}(\\sqrt{2}, \\sqrt{3})\\) over \\(\\mathbb{Q}(\\sqrt{2})\\). The element \\(\\sqrt{3}\\) is also not in \\(\\mathbb{Q}(\\sqrt{2})\\) and satisfies the polynomial \\(x^2 - 3\\), which is irreducible over \\(\\mathbb{Q}(\\sqrt{2})\\). Hence, the degree of the extension \\(\\mathbb{Q}(\\sqrt{2}, \\sqrt{3})\\) over \\(\\mathbb{Q}(\\sqrt{2})\\) is also 2.\n\nNow we can combine these degrees:\n\n\\[\n[\\mathbb{Q}(\\sqrt{2}, \\sqrt{3}) : \\mathbb{Q}] = [\\mathbb{Q}(\\sqrt{2}, \\sqrt{3}) : \\mathbb{Q}(\\sqrt{2})] \\times [\\mathbb{Q}(\\sqrt{2}) : \\mathbb{Q}] = 2 \\times 2 = 4.\n\\]\n\nThus, the degree of the field extension \\(\\mathbb{Q}(\\sqrt{2}, \\sqrt{3}, \\sqrt{18})\\) over \\(\\mathbb{Q}\\) is 4.\n\nTherefore, the answer is:\n\n**B: 4**.",
              "function_call": null
            }
          ],
          "finish_reason": "stop",
          "model": "gpt-4o-mini-2024-07-18",
          "usage": {
            "total_tokens": 556,
            "completion_tokens": 487,
            "prompt_tokens": 69,
            "cached_tokens": 0
          },
          "error": null,
          "temperature": 1,
          "top_p": 1,
          "seed": 42
        }
      }
    ],
    "first_id": "outputitem_68017251ff3881908bf5096bf4cd91c6",
    "last_id": "outputitem_6801724f54888190942ec66a197309dd",
    "has_more": false
  }
}

Evaluation - Getrunoutputitem

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}/output_items/{output-item-id}?api-version=2025-04-01-preview

Get an evaluation run output item by ID.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The evaluation run output item

Examples

GET {endpoint}/openai/evals/{eval-id}/runs/{run-id}/output_items/{output-item-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "eval.run.output_item",
    "id": "outputitem_68017251ff3881908bf5096bf4cd91c6",
    "created_at": 1744925265,
    "run_id": "evalrun_68016a056f0481909b9774447bdd1aa3",
    "eval_id": "eval_6801694950848190b10968bb628b651d",
    "status": "fail",
    "datasource_item_id": 1,
    "datasource_item": {
      "question": "Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5.",
      "A": "8",
      "B": "2",
      "C": "24",
      "D": "120",
      "answer": "C"
    },
    "results": [
      {
        "name": "string check-63b1fffa-bee6-4c37-ae77-ed46e3dce2b7",
        "sample": null,
        "passed": false,
        "score": 0
      }
    ],
    "sample": {
      "input": [
        {
          "role": "system",
          "content": "Answer the question's with A, B, C, or D."
        },
        {
          "role": "user",
          "content": "Question: Let p = (1, 2, 5, 4)(2, 3) in S_5 . Find the index of <p> in S_5. A: 8 B: 2 C: 24 D: 120."
        }
      ],
      "output": [
        {
          "role": "assistant",
          "content": "To find the index of the subgroup generated by the permutation \\( p = (1, 2, 5, 4)(2, 3) \\) in \\( S_5 \\), we first need to determine the order of \\( p \\).\n\n1. The cycle \\( (1, 2, 5, 4) \\) has length 4.\n2. The cycle \\( (2, 3) \\) has length 2.\n3. The least common multiple (LCM) of these lengths gives the order of the permutation \\( p \\).\n\nCalculating the LCM:\n\\[\n\\text{lcm}(4, 2) = 4\n\\]\nThus, the order of \\( p \\) is 4.\n\nNext, we find the size of the subgroup \\( \\langle p \\rangle \\):\n- The size of \\( \\langle p \\rangle \\) is equal to the order of \\( p \\), which is 4.\n\nNow, we know the size of \\( S_5 \\):\n\\[\n|S_5| = 5! = 120\n\\]\n\nFinally, to find the index of \\( \\langle p \\rangle \\) in \\( S_5 \\), we use the formula:\n\\[\n\\text{index} = \\frac{|S_5|}{|\\langle p \\rangle|} = \\frac{120}{4} = 30\n\\]\n\nHowever, the available answer choices do not include 30. There may be a mistake because the question expects an answer among A, B, C, and D.\n\nLet\u00e2\u20ac\u2122s assume we misunderstood \\( \\langle p \\rangle \\), and instead, we can deduce based solely on given answers looking for a relation to \\( S_5 \\) without delving into detailed subgroup tracks. \n\nSince \\( S_5 \\) has 30 different elements in a subgroup configuration, the closest answer physically relating as long as \\( p \\) covers two elements effectively would logically fit an answer of 120 / 60 which has no direct relationship.\n\nGiven the option choices and specific rank formulations as often made regarding elements in specific construct the subgroup at best reflects around a viable ratio of parts allowed through available indices. \n\nThus, after reasoning through which aligns most structurally geometrically yielding across all configurations possible integrated yet arrives leading \\( p \\) through neighborhood distributions leaving reflections outstanding:\n\n\n\nThe correct answer is:\n**C: 24**\n\nHowever per the discussion migrating \\( p \\) may leave various pathways leading ultimately toward that framing in modeling. Always a good suggestion confirming the elements group generating any possible in outputs rationales. "
        }
      ],
      "finish_reason": "stop",
      "model": "gpt-4o-mini-2024-07-18",
      "usage": {
        "total_tokens": 627,
        "completion_tokens": 546,
        "prompt_tokens": 81,
        "cached_tokens": 0
      },
      "error": null,
      "temperature": 1,
      "top_p": 1,
      "seed": 42
    }
  }
}

Files - List

GET {endpoint}/openai/files?api-version=2025-04-01-preview

Gets a list of all files owned by the Azure OpenAI resource.

These include user uploaded content like files with purpose "fine-tune" for training or validation of fine-tunes models as well as files that are generated by the service such as "fine-tune-results" which contains various metrics for the corresponding fine-tuning job.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/files?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "data": [
      {
        "status": "processed",
        "bytes": 140,
        "purpose": "fine-tune",
        "filename": "puppy.jsonl",
        "id": "file-181a1cbdcdcf4677ada87f63a0928099",
        "created_at": 1646126127,
        "object": "file"
      },
      {
        "status": "processed",
        "bytes": 32423,
        "purpose": "fine-tune-results",
        "filename": "results.csv",
        "id": "file-181a1cbdcdcf4677ada87f63a0928099",
        "created_at": 1646126127,
        "object": "file"
      }
    ],
    "object": "list"
  }
}

Files - Upload

POST {endpoint}/openai/files?api-version=2025-04-01-preview

Creates a new file entity by uploading data from a local machine. Uploaded files can, for example, be used for training or evaluating fine-tuned models.

URI Parameters

Request Header

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

Request Body

Content-Type: multipart/form-data

Responses

Status Code: 201

Description: The file has been successfully created.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/files?api-version=2025-04-01-preview

Responses: Status Code: 201

{
  "headers": {
    "___location": "https://aoairesource.openai.azure.com/openai/files/file-181a1cbdcdcf4677ada87f63a0928099"
  },
  "body": {
    "status": "pending",
    "purpose": "fine-tune",
    "filename": "puppy.jsonl",
    "id": "file-181a1cbdcdcf4677ada87f63a0928099",
    "created_at": 1646126127,
    "object": "file"
  }
}

Files - Import

POST {endpoint}/openai/files/import?api-version=2025-04-01-preview

Creates a new file entity by importing data from a provided url. Uploaded files can, for example, be used for training or evaluating fine-tuned models.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Responses

Status Code: 201

Description: The file has been successfully created.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/files/import?api-version=2025-04-01-preview

Responses: Status Code: 201

{
  "headers": {
    "___location": "https://aoairesource.openai.azure.com/openai/files/file-181a1cbdcdcf4677ada87f63a0928099"
  },
  "body": {
    "status": "pending",
    "purpose": "fine-tune",
    "filename": "puppy.jsonl",
    "id": "file-181a1cbdcdcf4677ada87f63a0928099",
    "created_at": 1646126127,
    "object": "file"
  }
}

Files - Get

GET {endpoint}/openai/files/{file-id}?api-version=2025-04-01-preview

Gets details for a single file specified by the given file-id including status, size, purpose, etc.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/files/{file-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "status": "processed",
    "bytes": 140,
    "purpose": "fine-tune",
    "filename": "puppy.jsonl",
    "id": "file-181a1cbdcdcf4677ada87f63a0928099",
    "created_at": 1646126127,
    "object": "file"
  }
}

Files - Delete

DELETE {endpoint}/openai/files/{file-id}?api-version=2025-04-01-preview

Deletes the file with the given file-id.

Deletion is also allowed if a file was used, e.g., as training file in a fine-tuning job.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The file was successfully deleted.

Status Code: default

Description: An error occurred.

Examples

DELETE {endpoint}/openai/files/{file-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "object": "file",
    "deleted": true,
    "id": "file-181a1cbdcdcf4677ada87f63a0928099"
  }
}

Files - Get content

GET {endpoint}/openai/files/{file-id}/content?api-version=2025-04-01-preview

Gets the content of the file specified by the given file-id.

Files can be user uploaded content or generated by the service like result metrics of a fine-tuning job.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/files/{file-id}/content?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": "raw file content"
}

Fine-tuning - List

GET {endpoint}/openai/fine_tuning/jobs?api-version=2025-04-01-preview

Gets a list of all fine-tuning jobs owned by the Azure OpenAI resource.The details that are returned for each fine-tuning job contain besides its identifier the base model, training and validation files, hyper parameters, time stamps, status and events.

Events are created when the job status changes. For example, running or complete, and when results are uploaded.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/fine_tuning/jobs?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "has_more": false,
    "data": [
      {
        "hyperparameters": {
          "n_epochs": -1
        },
        "integrations": [
          {
            "type": "wandb",
            "wandb": {
              "project": "custom-wandb-project",
              "tags": [
                "project:tag",
                "lineage"
              ]
            }
          }
        ],
        "method": {
          "type": "supervised"
        },
        "status": "succeeded",
        "model": "curie",
        "fine_tuned_model": "curie.ft-72a2792ef7d24ba7b82c7fe4a37e379f",
        "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
        "result_files": [
          "file-181a1cbdcdcf4677ada87f63a0928099"
        ],
        "finished_at": 1646127311,
        "trained_tokens": 2342,
        "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
        "created_at": 1646126127,
        "object": "fine_tuning.job"
      }
    ],
    "object": "list"
  }
}

Fine-tuning - Create

POST {endpoint}/openai/fine_tuning/jobs?api-version=2025-04-01-preview

Creates a job that fine-tunes a specified model from a given training file.

Response includes details of the enqueued job including job status and hyper parameters.

The name of the fine-tuned model is added to the response once complete.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Responses

Status Code: 201

Description: The fine tune has been successfully created.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/fine_tuning/jobs?api-version=2025-04-01-preview

Responses: Status Code: 201

{
  "headers": {
    "___location": "https://aoairesource.openai.azure.com/openai/fine_tuning/jobs/ft-72a2792ef7d24ba7b82c7fe4a37e379f"
  },
  "body": {
    "hyperparameters": {
      "n_epochs": -1
    },
    "integrations": [
      {
        "type": "wandb",
        "wandb": {
          "project": "custom-wandb-project",
          "tags": [
            "project:tag",
            "lineage"
          ]
        }
      }
    ],
    "method": {
      "type": "supervised"
    },
    "status": "pending",
    "model": "curie",
    "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
    "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "fine_tuning.job"
  }
}

Fine-tuning - Get

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}?api-version=2025-04-01-preview

Gets details for a single fine-tuning job specified by the given fine-tune-id.

The details contain the base model, training and validation files, hyper parameters, time stamps, status and events.

Events are created when the job status changes, e.g. running or complete, and when results are uploaded.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "hyperparameters": {
      "n_epochs": -1
    },
    "integrations": [
      {
        "type": "wandb",
        "wandb": {
          "project": "custom-wandb-project",
          "tags": [
            "project:tag",
            "lineage"
          ]
        }
      }
    ],
    "method": {
      "type": "supervised"
    },
    "status": "succeeded",
    "model": "curie",
    "fine_tuned_model": "curie.ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
    "result_files": [
      "file-181a1cbdcdcf4677ada87f63a0928099"
    ],
    "finished_at": 1646127311,
    "trained_tokens": 2342,
    "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "fine_tuning.job"
  }
}

Fine-tuning - Delete

DELETE {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}?api-version=2025-04-01-preview

Deletes the fine-tuning job specified by the given fine-tune-id.

URI Parameters

Request Header

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

Responses

Status Code: 204

Description: The fine tune was successfully deleted.

Status Code: default

Description: An error occurred.

Examples

DELETE {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}?api-version=2025-04-01-preview

Responses: Status Code: 204

{
  "headers": {}
}

Fine-tuning - Cancel

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/cancel?api-version=2025-04-01-preview

Cancels the processing of the fine-tuning job specified by the given fine-tune-id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The fine tune has been successfully canceled

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/cancel?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "hyperparameters": {
      "n_epochs": -1
    },
    "integrations": [
      {
        "type": "wandb",
        "wandb": {
          "project": "custom-wandb-project",
          "tags": [
            "project:tag",
            "lineage"
          ]
        }
      }
    ],
    "method": {
      "type": "supervised"
    },
    "status": "cancelled",
    "model": "curie",
    "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
    "finished_at": 1646127311,
    "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "fine_tuning.job"
  }
}

Fine-tuning - Get checkpoints

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/checkpoints?api-version=2025-04-01-preview

Gets the checkpoints for the fine-tuning job specified by the given fine-tune-id.

Checkpoints are created at the end of successful epochs during training.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/checkpoints?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "has_more": false,
    "data": [
      {
        "id": "ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P",
        "created_at": 1646126127,
        "fine_tuned_model_checkpoint": "gpt-35-turbo-0613.ft-72a2792ef7d24ba7b82c7fe4a37e379f:ckpt-step-10",
        "step_number": 10,
        "metrics": {
          "step": 10,
          "train_loss": 0.478,
          "train_mean_token_accuracy": 0.924,
          "valid_loss": 10.112,
          "valid_mean_token_accuracy": 0.145,
          "full_valid_loss": 0.567,
          "full_valid_mean_token_accuracy": 0.944
        },
        "fine_tuning_job_id": "ftjob-72a2792ef7d24ba7b82c7fe4a37e379f",
        "object": "fine_tuning.job.checkpoint"
      },
      {
        "id": "ftckpt_frtXDR2453C4FG67t03MLPs5",
        "created_at": 1646126137,
        "fine_tuned_model_checkpoint": "gpt-35-turbo-0613.ft-72a2792ef7d24ba7b82c7fe4a37e379f:ckpt-step-20",
        "step_number": 20,
        "metrics": {
          "step": 20,
          "train_loss": 0.355,
          "train_mean_token_accuracy": 0.947,
          "valid_loss": 11.32,
          "valid_mean_token_accuracy": 0.122,
          "full_valid_loss": 0.317,
          "full_valid_mean_token_accuracy": 0.955
        },
        "fine_tuning_job_id": "ftjob-72a2792ef7d24ba7b82c7fe4a37e379f",
        "object": "fine_tuning.job.checkpoint"
      },
      {
        "id": "ftckpt_agLk6Gio560ORp14gl123fgd",
        "created_at": 1646126147,
        "fine_tuned_model_checkpoint": "gpt-35-turbo-0613.ft-72a2792ef7d24ba7b82c7fe4a37e379f:ckpt-step-30",
        "step_number": 30,
        "metrics": {
          "step": 30,
          "train_loss": 0.155,
          "train_mean_token_accuracy": 0.975,
          "valid_loss": 9.31,
          "valid_mean_token_accuracy": 0.092,
          "full_valid_loss": 0.114,
          "full_valid_mean_token_accuracy": 0.963
        },
        "fine_tuning_job_id": "ftjob-72a2792ef7d24ba7b82c7fe4a37e379f",
        "object": "fine_tuning.job.checkpoint"
      }
    ],
    "object": "list"
  }
}

Fine-tuning - Get events

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/events?api-version=2025-04-01-preview

Gets the events for the fine-tuning job specified by the given fine-tune-id.

Events are created when the job status changes, e.g. running or complete, and when results are uploaded.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/events?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "has_more": false,
    "data": [
      {
        "id": "ftevent-363dcd7cb4c74539bc53293c1dceef05",
        "created_at": 1646126127,
        "level": "info",
        "message": "Job enqueued. Waiting for jobs ahead to complete.",
        "type": "message",
        "object": "fine_tuning.job.event"
      },
      {
        "id": "ftevent-8c2a44999790437cb3230e543fa2cf0f",
        "created_at": 1646126169,
        "level": "info",
        "message": "Job started.",
        "type": "message",
        "object": "fine_tuning.job.event"
      },
      {
        "id": "ftevent-2d47d651d2f3484c8187c88c00078147",
        "created_at": 1646126192,
        "level": "info",
        "message": "Job succeeded.",
        "type": "message",
        "object": "fine_tuning.job.event"
      }
    ],
    "object": "list"
  }
}

Fine-tuning - Pause

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/pause?api-version=2025-04-01-preview

Pausing the processing of the fine-tuning job specified by the given fine-tune-id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The fine tune has been successfully paused.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/pause?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "hyperparameters": {
      "n_epochs": -1
    },
    "integrations": [
      {
        "type": "wandb",
        "wandb": {
          "project": "custom-wandb-project",
          "tags": [
            "project:tag",
            "lineage"
          ]
        }
      }
    ],
    "method": {
      "type": "supervised"
    },
    "status": "paused",
    "model": "curie",
    "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
    "finished_at": 1646127311,
    "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "fine_tuning.job"
  }
}

Fine-tuning - Resume

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/resume?api-version=2025-04-01-preview

Resumes the processing of the fine-tuning job specified by the given fine-tune-id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: The fine tune has been successfully resumed.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/fine_tuning/jobs/{fine-tuning-job-id}/resume?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "hyperparameters": {
      "n_epochs": -1
    },
    "integrations": [
      {
        "type": "wandb",
        "wandb": {
          "project": "custom-wandb-project",
          "tags": [
            "project:tag",
            "lineage"
          ]
        }
      }
    ],
    "method": {
      "type": "supervised"
    },
    "status": "resuming",
    "model": "curie",
    "training_file": "file-181a1cbdcdcf4677ada87f63a0928099",
    "finished_at": 1646127311,
    "id": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "fine_tuning.job"
  }
}

Ingestion jobs - List

GET {endpoint}/openai/ingestion/jobs?api-version=2025-04-01-preview

Lists the ingestion jobs.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/ingestion/jobs?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "body": {
    "value": [
      {
        "jobId": "usercompute-ingestion-job",
        "kind": "UserCompute",
        "workspaceId": "/subscriptions/f375b912-331c-4fc5-8e9f-2d7205e3e036/resourceGroups/adrama-copilot-demo/providers/Microsoft.MachineLearningServices/workspaces/adrama-rag-dev"
      },
      {
        "jobId": "syscompute-ingestion-job",
        "kind": "SystemCompute"
      }
    ]
  }
}

Ingestion jobs - Create

PUT {endpoint}/openai/ingestion/jobs/{job-id}?api-version=2025-04-01-preview

Creates an ingestion job with the specified job id.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

PUT {endpoint}/openai/ingestion/jobs/{job-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {
    "operation-___location": "https://aoairesource.openai.azure.com/openai/ingestion/jobs/ingestion-job/runs/72a2792ef7d24ba7b82c7fe4a37e379f?api-version=2025-04-01-preview"
  },
  "body": {
    "kind": "SystemCompute",
    "jobId": "ingestion-job",
    "searchServiceConnection": {
      "kind": "EndpointWithManagedIdentity",
      "endpoint": "https://aykame-dev-search.search.windows.net"
    },
    "datasource": {
      "kind": "Storage",
      "connection": {
        "kind": "EndpointWithManagedIdentity",
        "endpoint": "https://mystorage.blob.core.windows.net/",
        "resourceId": "/subscriptions/1234567-abcd-1234-5678-1234abcd/resourceGroups/my-resource/providers/Microsoft.Storage/storageAccounts/mystorage"
      },
      "containerName": "container",
      "chunking": {
        "maxChunkSizeInTokens": 2048
      },
      "embeddings": [
        {
          "connection": {
            "kind": "RelativeConnection"
          },
          "deploymentName": "Ada"
        }
      ]
    },
    "dataRefreshIntervalInHours": 24,
    "completionAction": "keepAllAssets"
  }
}

PUT {endpoint}/openai/ingestion/jobs/{job-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {
    "operation-___location": "https://aoairesource.openai.azure.com/openai/ingestion/jobs/ingestion-job/runs/72a2792ef7d24ba7b82c7fe4a37e379f?api-version=2025-04-01-preview"
  },
  "body": {
    "kind": "UserCompute",
    "jobId": "ingestion-job",
    "workspaceId": "/subscriptions/f375b912-331c-4fc5-8e9f-2d7205e3e036/resourceGroups/adrama-copilot-demo/providers/Microsoft.MachineLearningServices/workspaces/adrama-rag-dev",
    "compute": {
      "kind": "ServerlessCompute"
    },
    "target": {
      "kind": "AzureAISearch",
      "connectionId": "/subscriptions/f375b912-331c-4fc5-8e9f-2d7205e3e036/resourceGroups/adrama-copilot-demo/providers/Microsoft.MachineLearningServices/workspaces/adrama-rag-dev/connections/search-connection"
    },
    "datasource": {
      "kind": "Dataset",
      "datasetId": "azureml://locations/centraluseuap/workspaces/83317fe6-efa6-4e4a-b020-d0edd11ec382/data/PlainText/versions/1",
      "datasetType": "uri_folder"
    }
  }
}

Ingestion jobs - Get

GET {endpoint}/openai/ingestion/jobs/{job-id}?api-version=2025-04-01-preview

Gets the details of the specified job id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/ingestion/jobs/{job-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "body": {
    "kind": "UserCompute",
    "jobId": "ingestion-job",
    "workspaceId": "/subscriptions/f375b912-331c-4fc5-8e9f-2d7205e3e036/resourceGroups/adrama-copilot-demo/providers/Microsoft.MachineLearningServices/workspaces/adrama-rag-dev",
    "compute": {
      "kind": "ServerlessCompute"
    },
    "target": {
      "kind": "AzureAISearch",
      "connectionId": "/subscriptions/f375b912-331c-4fc5-8e9f-2d7205e3e036/resourceGroups/adrama-copilot-demo/providers/Microsoft.MachineLearningServices/workspaces/adrama-rag-dev/connections/search-connection"
    },
    "datasource": {
      "kind": "Dataset",
      "datasetId": "azureml://locations/centraluseuap/workspaces/83317fe6-efa6-4e4a-b020-d0edd11ec382/data/PlainText/versions/1",
      "datasetType": "uri_folder"
    }
  }
}

Ingestionjobruns - List

GET {endpoint}/openai/ingestion/jobs/{job-id}/runs?api-version=2025-04-01-preview

Lists the runs of the specified job id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/ingestion/jobs/{job-id}/runs?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "body": {
    "value": [
      {
        "jobId": "ingestion-job",
        "runId": "f375b912-331c-4fc5-8e9f-2d7205e3e036",
        "status": "succeeded"
      },
      {
        "jobId": "ingestion-job",
        "runId": "07f2d192-add7-4202-a2e3-858c2577f4fd",
        "status": "failed"
      },
      {
        "jobId": "ingestion-job",
        "runId": "5ef7a436-1147-4cbb-82e0-3d502bcc6a7b",
        "status": "running"
      }
    ]
  }
}

Ingestionjobruns - Get

GET {endpoint}/openai/ingestion/jobs/{job-id}/runs/{run-id}?api-version=2025-04-01-preview

Gets the details of the specified run id as part of the specified job id.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/ingestion/jobs/{job-id}/runs/{run-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "body": {
    "jobId": "ingestion-job",
    "runId": "5ef7a436-1147-4cbb-82e0-3d502bcc6a7b",
    "status": "running",
    "progress": {
      "stageProgress": [
        {
          "name": "Preprocessing",
          "totalItems": 14,
          "processedItems": 0,
          "state": "notRunning"
        },
        {
          "name": "Indexing",
          "state": "notRunning"
        }
      ]
    }
  }
}

Models - List

GET {endpoint}/openai/models?api-version=2025-04-01-preview

Gets a list of all models that are accessible by the Azure OpenAI resource.

These include base models as well as all successfully completed fine-tuned models owned by the Azure OpenAI resource.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/models?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "data": [
      {
        "status": "succeeded",
        "capabilities": {
          "fine_tune": true,
          "inference": true,
          "completion": true,
          "chat_completion": false,
          "embeddings": false
        },
        "lifecycle_status": `generally-available`,
        "deprecation": {
          "fine_tune": 1677662127,
          "inference": 1709284527
        },
        "id": "curie",
        "created_at": 1646126127,
        "object": "model"
      },
      {
        "status": "succeeded",
        "model": "curie",
        "fine_tune": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
        "capabilities": {
          "fine_tune": false,
          "inference": true,
          "completion": true,
          "chat_completion": false,
          "embeddings": false
        },
        "lifecycle_status": `generally-available`,
        "deprecation": {
          "inference": 1709284527
        },
        "id": "curie.ft-72a2792ef7d24ba7b82c7fe4a37e379f",
        "created_at": 1646126127,
        "object": "model"
      }
    ],
    "object": "list"
  }
}

Models - Get

GET {endpoint}/openai/models/{model-id}?api-version=2025-04-01-preview

Gets details for the model specified by the given modelId.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

GET {endpoint}/openai/models/{model-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "status": "succeeded",
    "capabilities": {
      "fine_tune": true,
      "inference": true,
      "completion": true,
      "chat_completion": false,
      "embeddings": false
    },
    "lifecycle_status": `generally-available`,
    "deprecation": {
      "fine_tune": 1677662127,
      "inference": 1709284527
    },
    "id": "curie",
    "created_at": 1646126127,
    "object": "model"
  }
}

GET {endpoint}/openai/models/{model-id}?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "status": "succeeded",
    "model": "curie",
    "fine_tune": "ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "capabilities": {
      "fine_tune": false,
      "inference": true,
      "completion": true,
      "chat_completion": false,
      "embeddings": false
    },
    "lifecycle_status": `generally-available`,
    "deprecation": {
      "inference": 1709284527
    },
    "id": "curie.ft-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "model"
  }
}

Upload file - Start

POST {endpoint}/openai/uploads?api-version=2025-04-01-preview

An intermediate Upload object is created, allowing you to add Parts to it. Currently, an Upload size can be a maximum of 9 GB in total and will expire two hours after being created.

After the Upload is completed a File object will be generated, containing all the uploaded parts. This File object can then be used across our platform just like any other file.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Request Body

Content-Type: text/json

Request Body

Content-Type: application/*+json

Responses

Status Code: 200

Description: The upload has been successfully created.

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/uploads?api-version=2025-04-01-preview

{
 "purpose": "fine-tune",
 "filename": "training_data_v21.jsonl",
 "bytes": 2097152,
 "mime_type": "application/json"
}

Responses: Status Code: 200

{
  "headers": {
    "___location": "https://aoairesource.openai.azure.com/openai/uploads/runs/fine-tune-72a2792ef7d24ba7b82c7fe4a37e379f"
  },
  "body": {
    "bytes": 2097152,
    "filename": "training_data_v21.jsonl",
    "purpose": "fine-tune",
    "status": "pending",
    "expires_at": 1646133327,
    "file": {
      "status": "pending",
      "bytes": 140,
      "purpose": "fine-tune",
      "filename": "puppy.jsonl",
      "id": "file-181a1cbdcdcf4677ada87f63a0928099",
      "created_at": 1646126127,
      "object": "file"
    },
    "id": "fine-tune-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "upload"
  }
}

Upload file - Cancel

POST {endpoint}/openai/uploads/{upload-id}/cancel?api-version=2025-04-01-preview

Cancels the Upload, and will lead to all uploaded parts to be deleted asynchronously.

No Parts may be added after an Upload is cancelled.

URI Parameters

Request Header

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

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/uploads/{upload-id}/cancel?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "bytes": 2097152,
    "filename": "training_data_v21.jsonl",
    "purpose": "fine-tune",
    "status": "cancelled",
    "expires_at": 1646133327,
    "file": {
      "status": "pending",
      "bytes": 140,
      "purpose": "fine-tune",
      "filename": "puppy.jsonl",
      "id": "file-181a1cbdcdcf4677ada87f63a0928099",
      "created_at": 1646126127,
      "object": "file"
    },
    "id": "fine-tune-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "upload"
  }
}

Upload file - Complete

POST {endpoint}/openai/uploads/{upload-id}/complete?api-version=2025-04-01-preview

This completes the Upload, and the returned Upload object contains a nested File object that is ready for use across the platform.

You can define the order of the Parts by providing an ordered list of Part IDs.

The total number of bytes uploaded must match the size originally specified when creating the Upload object.

After this operation no additional Parts can be added once the Upload is completed.

URI Parameters

Request Header

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

Request Body

Content-Type: application/json

Request Body

Content-Type: text/json

Request Body

Content-Type: application/*+json

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/uploads/{upload-id}/complete?api-version=2025-04-01-preview

{
 "part_ids": [
  "LnmictL3p0u4LH/ko343nw==",
  "LmmictL3p0u4LH/ko343nw=="
 ]
}

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "bytes": 2097152,
    "filename": "training_data_v21.jsonl",
    "purpose": "fine-tune",
    "status": "completed",
    "expires_at": 1646133327,
    "file": {
      "status": "processed",
      "bytes": 140,
      "purpose": "fine-tune",
      "filename": "puppy.jsonl",
      "id": "file-181a1cbdcdcf4677ada87f63a0928099",
      "created_at": 1646126127,
      "object": "file"
    },
    "id": "fine-tune-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "upload"
  }
}

Upload file - Part

POST {endpoint}/openai/uploads/{upload-id}/parts?api-version=2025-04-01-preview

Adds a Part to an Upload object, where each Part represents a segment of the file you're uploading.

Each Part can be up to the standard size limit for file upload, based on the File Purpose. You can continue adding Parts until reaching the Upload size limit of 9 GB.

URI Parameters

Request Header

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

Request Body

Content-Type: multipart/form-data

Responses

Status Code: 200

Description: Success

Status Code: default

Description: An error occurred.

Examples

POST {endpoint}/openai/uploads/{upload-id}/parts?api-version=2025-04-01-preview

Responses: Status Code: 200

{
  "headers": {},
  "body": {
    "upload_id": "fine-tune-72a2792ef7d24ba7b82c7fe4a37e379f",
    "azure_block_id": "LnmictL3p0u4LH/ko343nw==",
    "id": "uplprt-72a2792ef7d24ba7b82c7fe4a37e379f",
    "created_at": 1646126127,
    "object": "upload.part"
  }
}

Components

AzureAISearchIndex

Azure AI Search Index.

BaseConnection

A connection to a resource.

Discriminator for BaseConnection

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

Batch

Defines the values of a batch.

BatchCreateRequest

Defines the request to create a batch.

BatchErrorData

Error information for a failure in batch.

BatchErrors

For batches that have failed, this will contain more information on the cause of the failures.

BatchRequestCounts

The request counts for different statuses within the batch.

BatchOutputReference

The Azure Storage folder to store output.

BatchStatus

The status of a batch.

BatchesList

Represents a list of batches.

Capabilities

The capabilities of a base or fine tune model.

Choice

ChoiceMessage

ChunkingSettings

Chunking settings

CompletionAction

The completion action.

ComputeType

The compute type.

ConnectionStringConnection

Connection string connection.

ConnectionType

The connection type.

CosmosDBIndex

CosmosDB Index.

CrawlingSettings

Crawling settings

CreateEvalCompletionsRunDataSource

A CompletionsRunDataSource object describing a model sampling configuration.

CreateEvalCustomDataSourceConfig

A CustomDataSourceConfig object that defines the schema for the data source used for the evaluation runs. This schema is used to define the shape of the data that will be: - Used to define your testing criteria and - What data is required when creating a run

CreateEvalItem

A chat message that makes up the prompt or context. May include variable references to the "item" namespace, ie {{item.name}}.

CreateEvalJsonlRunDataSource

A JsonlRunDataSource object with that specifies a JSONL file that matches the eval

CreateEvalLabelModelGrader

A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.

CreateEvalLogsDataSourceConfig

A data source config which specifies the metadata property of your stored completions query. This is usually metadata like usecase=chatbot or prompt-version=v2, etc.

CreateEvalRequest

CreateEvalRunRequest

CreateEvalStoredCompletionsRunDataSource

A StoredCompletionsRunDataSource configuration describing a set of filters

CustomCompute

Custom compute.

DeploymentConnection

Relative deployment connection.

Deprecation

Defines the dates of deprecation for the different use cases of a model.

Usually base models support 1 year of fine tuning after creation. Inference is typically supported 2 years after creation of base or fine tuned models. The exact dates are specified in the properties.

DpoHyperparamsRequest

Hyperparameters for DPO method of fine-tuning

DpoMethod

Request for DPO method fine-tuning

DpoMethodConfigRequest

Configuration for dpo fine-tuning method. Includes DPO specific hyperparameters

DpoMethodRequest

Request for DPO method fine-tuning

EndpointKeyConnection

Endpoint key connection.

EndpointMIConnection

Endpoint Managed Identity connection.

Error

Error content as defined in the Microsoft REST guidelines.

ErrorCode

Error codes as defined in the Microsoft REST guidelines.

ErrorResponse

Error response as defined in the Microsoft REST guidelines.

Eval

An Eval object with a data source config and testing criteria. An Eval represents a task to be done for your LLM integration. Like:

• Improve the quality of my chatbot
• See how well my chatbot handles customer support
• Check if o3-mini is better at my use case than gpt-4o

EvalApiError

An object representing an error response from the Eval API.

EvalCustomDataSourceConfig

A CustomDataSourceConfig which specifies the schema of your item and optionally sample namespaces. The response schema defines the shape of the data that will be: - Used to define your testing criteria and - What data is required when creating a run

EvalFileRunDataSource

A FileRunDataSource configuration with a file id

EvalItem

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.

EvalJsonlFileContentSource

EvalJsonlFileIdSource

EvalLabelModelGrader

A LabelModelGrader object which uses a model to assign labels to each item in the evaluation.