Azure OpenAI in Microsoft Foundry Models REST API authoring preview reference

Learn how to use Azure OpenAI’s latest authoring preview REST API. In this article, you learn about authorization options, how to structure a request and receive a response.

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.

There is now a new preview inference API. Learn more in our API lifecycle guide.

API	Latest preview release	Latest GA release	Specifications	Description
Control plane	2025-07-01-preview	2025-06-01	Spec files	The control plane API is used for operations like creating resources, model deployment, and other higher level resource management tasks. The control plane also governs what is possible to do with capabilities like Azure Resource Manager, Bicep, Terraform, and Azure CLI.
Data plane	v1 preview	v1	Spec files	The data plane API controls inference and authoring operations.

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 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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
after	query	No	string	Identifier for the last event from the previous pagination request.
limit	query	No	integer	Number of batches to retrieve. Defaults to 20.
$filter	query	No	string	The OData expression to describe the filtering conditions.
$orderby	query	No	string	The OData expression to describe the sorting order.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	BatchesList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
completion_window	string	The time frame within which the batch should be processed.	Yes
endpoint	string	The API endpoint used by the batch.	Yes
input_blob	string	The url of an Azure Storage blob to use as input for the batch.	No
input_file_id	string	The ID of the input file for the batch.	No
metadata	object	A set of key-value pairs that can be attached to the batch. This can be useful for storing additional information about the batch in a structured format.	No
output_expires_after	FileExpiresAfter	Defines an expiration for the file.	No
output_folder	BatchOutputReference	The Azure Storage folder to store output.	No

Responses

Status Code: 201

Description: The batch has been successfully created.

Content-Type	Type	Description
application/json	Batch

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
batch-id	path	Yes	string	The identifier of the batch.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	Batch

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
batch-id	path	Yes	string	The identifier of the batch.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The batch has been successfully canceled.

Content-Type	Type	Description
application/json	Batch

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
metadata	query	No	string	Filter by the (key, value) pair in stored completion.
model	query	No	string	Filter by model name.
after	query	No	string	Identifier for the last stored completion from the previous pagination request.
limit	query	No	integer	Number of stored completions to retrieve. Defaults to 20.
order	query	No	string	Order of the results by created time (ascending or descending). Default to desc.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	StoredCompletionList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
stored-completion-id	path	Yes	string	The identifier of the stored completion.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	StoredCompletionResponse

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
stored-completion-id	path	Yes	string	The identifier of the stored completion.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	object	Arbitrary key-value pairs for additional information.	No

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	StoredCompletion

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
stored-completion-id	path	Yes	string	The identifier of the stored completion.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The stored completion was successfully deleted.

Content-Type	Type	Description
application/json	StoredCompletionDelete

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
stored-completion-id	path	Yes	string	The identifier of the stored completion.
after	query	No	string	Identifier for the last stored completion message from the previous pagination request.
limit	query	No	integer	Number of stored completions messages to retrieve. Defaults to 20.
order	query	No	string	Order of the results by message index (ascending or descending). Default to asc.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	StoredCompletionMessages

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
after	query	No	string	Identifier for the last eval from the previous pagination request.
limit	query	No	integer	Number of evals to retrieve.
order	query	No	string Possible values: asc, desc	Sort order for evals by timestamp. Use asc for ascending order or desc for descending order.
order_by	query	No	string Possible values: created_at, updated_at	Evals can be ordered by creation time or last updated time. Use created_at for creation time or updated_at for last updated time.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: A list of evals

Content-Type	Type	Description
application/json	EvalList

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 201

Description: OK

Content-Type	Type	Description
application/json	Eval

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to delete.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Successfully deleted the evaluation.

Content-Type	Type	Description
application/json	object

Status Code: 404

Description: Evaluation not found.

Content-Type	Type	Description
application/json	Error

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to retrieve.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The evaluation

Content-Type	Type	Description
application/json	Eval

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to update.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The updated evaluation

Content-Type	Type	Description
application/json	Eval

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to retrieve runs for.
after	query	No	string	Identifier for the last run from the previous pagination request.
limit	query	No	integer	Number of runs to retrieve.
order	query	No	string Possible values: asc, desc	Sort order for runs by timestamp. Use asc for ascending order or desc for descending order. Defaults to asc.
status	query	No	string Possible values: queued, in_progress, completed, canceled, failed	Filter runs by status. Use “queued”, “in_progress”, “failed”, “completed”, “canceled”.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: A list of runs for the evaluation

Content-Type	Type	Description
application/json	EvalRunList

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to create a run for.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 201

Description: Successfully created a run for the evaluation

Content-Type	Type	Description
application/json	EvalRun

Status Code: 400

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

Content-Type	Type	Description
application/json	Error

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to delete the run from.
run-id	path	Yes	string	The ID of the run to delete.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Successfully deleted the eval run

Content-Type	Type	Description
application/json	object

Status Code: 404

Description: Run not found

Content-Type	Type	Description
application/json	Error

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to retrieve runs for.
run-id	path	Yes	string	The ID of the run to retrieve.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The evaluation run

Content-Type	Type	Description
application/json	EvalRun

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation whose run you want to cancel.
run-id	path	Yes	string	The ID of the run to cancel.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The canceled eval run object

Content-Type	Type	Description
application/json	EvalRun

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to retrieve runs for.
run-id	path	Yes	string	The ID of the run to retrieve output items for.
after	query	No	string	Identifier for the last output item from the previous pagination request.
limit	query	No	integer	Number of output items to retrieve.
status	query	No	string Possible values: fail, pass	Filter output items by status. Use failed to filter by failed output items or pass to filter by passed output items.
order	query	No	string Possible values: asc, desc	Sort order for output items by timestamp. Use asc for ascending order or desc for descending order. Defaults to asc.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: A list of output items for the evaluation run

Content-Type	Type	Description
application/json	EvalRunOutputItemList

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
eval-id	path	Yes	string	The ID of the evaluation to retrieve runs for.
run-id	path	Yes	string	The ID of the run to retrieve.
output-item-id	path	Yes	string	The ID of the output item to retrieve.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The evaluation run output item

Content-Type	Type	Description
application/json	EvalRunOutputItem

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
purpose	query	No	string Possible values: fine-tune, fine-tune-results, assistants, assistants_output, batch, batch_output, evals, evals_output	Only return files with the given purpose.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000.
after	query	No	string	A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.
order	query	No	string	Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	FileList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: multipart/form-data

Name	Type	Description	Required	Default
anchor	string	Defines the anchor relative to what time the absolute expiration should be generated from.	No
seconds	integer	Gets the relative expiration time in seconds.
Range: [1209600 - 2592000].	No
file	string	Gets or sets the file to upload into Azure OpenAI.	Yes
purpose	string	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

Responses

Status Code: 201

Description: The file has been successfully created.

Content-Type	Type	Description
application/json	File

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
content_url	string	The url to download the document from (can be SAS url of a blob or any other external url accessible with a GET request).	Yes
expires_after	FileExpiresAfter	Defines an expiration for the file.	No
filename	string	The name of the JSON Lines file to be uploaded.
If the purpose is set to “fine-tune”, each line is a JSON record with “prompt” and “completion” fields representing your training examples.	Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

Responses

Status Code: 201

Description: The file has been successfully created.

Content-Type	Type	Description
application/json	File

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
file-id	path	Yes	string	The identifier of the file.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	File

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
file-id	path	Yes	string	The identifier of the file.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The file was successfully deleted.

Content-Type	Type	Description
application/json	FileDelete

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
file-id	path	Yes	string	The identifier of the file.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/octet-stream	string
application/json	string

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/octet-stream	ErrorResponse
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
after	query	No	string	Identifier for the last event from the previous pagination request.
limit	query	No	integer	Number of events to retrieve. Defaults to 20.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	FineTuningJobList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
hyperparameters	FineTuningHyperParameters	The hyper parameter settings used in a fine tune job.	No
integrations	array	A list of configurations for integrations supporting the fine-tuning job. There are many integrations planned, so make sure to check and act on the integration type.	No
method	object	Method used for supervised fine-tuning	No
└─ type	FineTuningMethodType		No
model	string	The identifier (model-id) of the base model used for this fine-tune.	Yes
seed	integer	The seed used for the fine-tuning job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed isn’t specified, one will be generated for you.	No
suffix	string	The suffix used to identify the fine-tuned model. The suffix can contain up to 40 characters (a-z, A-Z, 0-9,- and _) that will be added to your fine-tuned model name.	No
training_file	string	The file identity (file-id) that is used for training this fine tuned model.	Yes
validation_file	string	The file identity (file-id) that is used to evaluate the fine tuned model during training.	No

Responses

Status Code: 201

Description: The fine tune has been successfully created.

Content-Type	Type	Description
application/json	FineTuningJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	FineTuningJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 204

Description: The fine tune was successfully deleted.

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The fine tune has been successfully canceled

Content-Type	Type	Description
application/json	FineTuningJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
after	query	No	string	Identifier for the last checkpoint ID from the previous pagination request.
limit	query	No	integer	Number of checkpoints to retrieve. Defaults to 10.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	FineTuningJobCheckpointList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
after	query	No	string	Identifier for the last event from the previous pagination request.
limit	query	No	integer	Number of events to retrieve. Defaults to 20.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	FineTuningJobEventList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The fine tune has been successfully paused.

Content-Type	Type	Description
application/json	FineTuningJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
fine-tuning-job-id	path	Yes	string	The identifier of the fine-tuning job.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: The fine tune has been successfully resumed.

Content-Type	Type	Description
application/json	FineTuningJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.
mgmt-user-token	header	No	string	The token used to access the workspace (needed only for user compute jobs).

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	IngestionJobList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.
job-id	path	Yes	string	The id of the job that will be created.
mgmt-user-token	header	No	string	The token used to access the workspace (needed only for user compute jobs).
aml-user-token	header	No	string	The token used to access the resources within the job in the workspace (needed only for user compute jobs).

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
jobId	string		No
kind	IngestionJobType	The job type.	Yes

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	IngestionJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.
job-id	path	Yes	string	The id of the job.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	IngestionJob

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.
job-id	path	Yes	string	The id of the job.
mgmt-user-token	header	No	string	The token used to access the workspace (needed only for user compute jobs).

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	IngestionJobRunList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.
job-id	path	Yes	string	The id of the job.
run-id	path	Yes	string	The id of the run.
mgmt-user-token	header	No	string	The token used to access the workspace (needed only for user compute jobs).

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	IngestionJobRun

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	ModelList

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
model-id	path	Yes	string	The identifier of the model.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	Model

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
bytes	integer		Yes
filename	string		Yes
mime_type	string		Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

Request Body

Content-Type: text/json

Name	Type	Description	Required	Default
bytes	integer		Yes
filename	string		Yes
mime_type	string		Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

Request Body

Content-Type: application/*+json

Name	Type	Description	Required	Default
bytes	integer		Yes
filename	string		Yes
mime_type	string		Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

Responses

Status Code: 200

Description: The upload has been successfully created.

Content-Type	Type	Description
application/json	UploadResource

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
upload-id	path	Yes	string	The identifier of the upload.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	UploadResource

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
upload-id	path	Yes	string	The identifier of the upload.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
md5	string		No
part_ids	array		Yes

Request Body

Content-Type: text/json

Name	Type	Description	Required	Default
md5	string		No
part_ids	array		Yes

Request Body

Content-Type: application/*+json

Name	Type	Description	Required	Default
md5	string		No
part_ids	array		Yes

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	UploadResource

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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

Name	In	Required	Type	Description
endpoint	path	Yes	string url	Supported Azure OpenAI endpoints (protocol and hostname, for example: https://aoairesource.openai.azure.com. Replace “aoairesource” with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com
upload-id	path	Yes	string	The identifier of the upload.
api-version	query	Yes	string	The requested API version.

Request Header

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

Name	Required	Type	Description
Authorization	True	string	Example: Authorization: Bearer {Azure_OpenAI_Auth_Token} To generate an auth token using Azure CLI: az account get-access-token --resource https://cognitiveservices.azure.com Type: oauth2 Authorization Url: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scope: https://ai.azure.com/.default
api-key	True	string	Provide Azure OpenAI API key here

Request Body

Content-Type: multipart/form-data

Name	Type	Description	Required	Default
data	string		Yes

Responses

Status Code: 200

Description: Success

Content-Type	Type	Description
application/json	UploadPartResource

Status Code: default

Description: An error occurred.

Content-Type	Type	Description
application/json	ErrorResponse

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.

Name	Type	Description	Required	Default
connectionId	string	The id of the connection pointing to the Azure AI Search Index.	No
kind	TargetType	The target type.	Yes

BaseConnection

A connection to a resource.

Discriminator for BaseConnection

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

Type Value	Schema

Name	Type	Description	Required	Default
kind	ConnectionType	The connection type.	Yes

Batch

Defines the values of a batch.

Name	Type	Description	Required	Default
cancelled_at	integer	A timestamp when this batch was cancelled (in unix epochs).	No
cancelling_at	integer	A timestamp when this batch started cancelling (in unix epochs).	No
completed_at	integer	A timestamp when this batch was completed (in unix epochs).	No
completion_window	string	The time frame within which the batch should be processed.	No
created_at	integer	A timestamp when this batch was created (in unix epochs).	No
endpoint	string	The API endpoint used by the batch.	No
error_blob	string	The blob url containing outputs of requests with errors.	No
error_file_id	string	The ID of the file containing outputs of requests with errors.	No
errors	BatchErrors	For batches that have failed, this will contain more information on the cause of the failures.	No
expired_at	integer	A timestamp when this batch expired (in unix epochs).	No
expires_at	integer	A timestamp when this batch will expire (in unix epochs).	No
failed_at	integer	A timestamp when this batch failed (in unix epochs).	No
finalizing_at	integer	A timestamp when this batch started finalizing (in unix epochs).	No
id	string	The identity of this item.	Yes
in_progress_at	integer	A timestamp when this batch started progressing (in unix epochs).	No
input_blob	string	The blob url containing the input file for the batch.	No
input_file_id	string	The ID of the input file for the batch.	Yes
metadata	object	A set of key-value pairs that can be attached to the batch. This can be useful for storing additional information about the batch in a structured format.	No
object	TypeDiscriminator	Defines the type of an object.	No
output_blob	string	The blob url containing outputs of successfully executed requests.	No
output_file_id	string	The ID of the file containing outputs of successfully executed requests.	No
request_counts	BatchRequestCounts	The request counts for different statuses within the batch.	No
status	BatchStatus	The status of a batch.	No

BatchCreateRequest

Defines the request to create a batch.

Name	Type	Description	Required	Default
completion_window	string	The time frame within which the batch should be processed.	Yes
endpoint	string	The API endpoint used by the batch.	Yes
input_blob	string	The url of an Azure Storage blob to use as input for the batch.	No
input_file_id	string	The ID of the input file for the batch.	No
metadata	object	A set of key-value pairs that can be attached to the batch. This can be useful for storing additional information about the batch in a structured format.	No
output_expires_after	FileExpiresAfter	Defines an expiration for the file.	No
output_folder	BatchOutputReference	The Azure Storage folder to store output.	No

BatchErrorData

Error information for a failure in batch.

Name	Type	Description	Required	Default
code	string	An error code identifying the error type.	No
line	string	The line number of the input file where the error occurred, if applicable (can be null).	No
message	string	A human-readable message providing more details about the error.	No
param	string	The name of the parameter that caused the error, if applicable (can be null).	No

BatchErrors

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

Name	Type	Description	Required	Default
data	BatchErrorData	Error information for a failure in batch.	No
object	string	The type of the errors object. This is always ‘list’.	No

BatchRequestCounts

The request counts for different statuses within the batch.

Name	Type	Description	Required	Default
completed	integer	The number of requests in the batch that have been completed successfully.	No
failed	integer	The number of requests in the batch that have failed.	No
total	integer	The total number of requests in the batch.	No

BatchOutputReference

The Azure Storage folder to store output.

Name	Type	Description	Required	Default
delimiter	string	Optional. The delimiter used in the folder path, by default /.	No
url	string	The url of the Azure Storage folder where the batch output would be saved.	No

BatchStatus

The status of a batch.

Property	Value
Description	The status of a batch.
Type	string
Values	validating failed in_progress finalizing completed expired cancelling cancelled

BatchesList

Represents a list of batches.

Name	Type	Description	Required	Default
data	array	The list of items.	No
first_id	string	The id of the first batch in the list of batches returned.	No
has_more	boolean	A value indicating whether the list contains more elements than returned.	No
last_id	string	The id of the last batch in the list of batches returned.	No
object	TypeDiscriminator	Defines the type of an object.	No

Capabilities

The capabilities of a base or fine tune model.

Name	Type	Description	Required	Default
chat_completion	boolean	A value indicating whether a model supports chat completion.	Yes
completion	boolean	A value indicating whether a model supports completion.	Yes
embeddings	boolean	A value indicating whether a model supports embeddings.	Yes
fine_tune	boolean	A value indicating whether a model can be used for fine tuning.	Yes
inference	boolean	A value indicating whether a model can be deployed.	Yes

Choice

Name	Type	Description	Required	Default
finish_reason	string	The reason the model stopped generating tokens.	No
index	integer	The index of the choice in the list of choices.	No
logprobs	object	Log probability information for the choice.	No
message	ChoiceMessage		No

ChoiceMessage

Name	Type	Description	Required	Default
content	string	The contents of the message.	No
role	string	The role of the entity that is creating the message.	No
tool_calls	array	A list of the relevant tool calls.	No

ChunkingSettings

Chunking settings

Name	Type	Description	Required	Default
maxChunkSizeInTokens	integer		No

CompletionAction

The completion action.

Property	Value
Description	The completion action.
Type	string
Values	cleanUpTempAssets keepAllAssets

ComputeType

The compute type.

Property	Value
Description	The compute type.
Type	string
Values	ServerlessCompute CustomCompute

ConnectionStringConnection

Connection string connection.

Name	Type	Description	Required	Default
connectionString	string	Connection string	No
kind	ConnectionType	The connection type.	Yes

ConnectionType

The connection type.

Property	Value
Description	The connection type.
Type	string
Values	EndpointWithKey ConnectionString EndpointWithManagedIdentity WorkspaceConnection RelativeConnection

CosmosDBIndex

CosmosDB Index.

Name	Type	Description	Required	Default
collectionName	string	The name of the cosmos DB collection.	No
connectionId	string	The id of the connection pointing to the cosmos DB.	No
databaseName	string	The name of the cosmos DB database.	No
kind	TargetType	The target type.	Yes

CrawlingSettings

Crawling settings

Name	Type	Description	Required	Default
maxCrawlDepth	integer		No
maxCrawlTimeInMins	integer		No
maxDownloadTimeInMins	integer		No
maxFileSize	integer		No
maxFiles	integer		No
maxRedirects	integer		No

CreateEvalCompletionsRunDataSource

A CompletionsRunDataSource object describing a model sampling configuration.

Name	Type	Description	Required	Default
input_messages	object		No
└─ item_reference	string	A reference to a variable in the ‘item’ namespace, e.g., ‘item.name’.	No
└─ template	array	A list of chat messages forming the prompt or context. May include variable references to the ‘item’ namespace, e.g., {{item.name}}.	No
└─ type	enum	The type of input messages. Either template or item_reference. Possible values: template, item_reference	No
model	string	The name of the model to use for generating completions (e.g., ‘o3-mini’).	No
sampling_params	object		No
└─ max_completion_tokens	integer	The maximum number of tokens in the generated output.	No
└─ seed	integer	A seed value to initialize the randomness, during sampling.	No	42
└─ temperature	number	A higher temperature increases randomness in the outputs.	No	1
└─ top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1
source	object		Yes
└─ type	enum	The type of source. Can be one of EvalJsonlFileContentSource, EvalJsonlFileIdSource, or EvalStoredCompletionsSource. Possible values: EvalJsonlFileContentSource, EvalJsonlFileIdSource, EvalStoredCompletionsSource	No
type	enum	The type of run data source. Always completions. Possible values: completions	Yes

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

Name	Type	Description	Required	Default
include_sample_schema	boolean	Whether the eval should expect you to populate the sample namespace (ie, by generating responses off of your data source)	No	False
item_schema	object	The json schema for each row in the data source.	Yes
type	enum	The type of data source. Always custom. Possible values: custom	Yes

CreateEvalItem

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

Name	Type	Description	Required	Default
content	[‘string’, ‘InputTextContent’, ‘object’]	Text inputs to the model - can contain template strings.	Yes
role	enum	The role of the message input. One of user, assistant, system, or developer. Possible values: user, assistant, system, developer	Yes
type	enum	The type of the message input. Always message. Possible values: message	No

CreateEvalJsonlRunDataSource

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

Name	Type	Description	Required	Default
source	object		Yes
└─ content	array	The content of the jsonl file.	No
└─ id	string	The identifier of the file.	No
└─ type	enum	The type of jsonl source. Always file_id. Possible values: file_id	No
type	enum	The type of data source. Always jsonl. Possible values: jsonl	Yes

CreateEvalLabelModelGrader

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

Name	Type	Description	Required	Default
input	array	A list of chat messages forming the prompt or context. May include variable references to the “item” namespace, ie {{item.name}}.	Yes
labels	array	The labels to classify to each item in the evaluation.	Yes
model	string	The model to use for the evaluation. Must support structured outputs.	Yes
name	string	The name of the grader.	Yes
passing_labels	array	The labels that indicate a passing result. Must be a subset of labels.	Yes
type	enum	The object type, which is always label_model. Possible values: label_model	Yes

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.

Name	Type	Description	Required	Default
metadata	object	Metadata filters for the logs data source.	No
type	enum	The type of data source. Always logs. Possible values: logs	Yes

CreateEvalRequest

Name	Type	Description	Required	Default
data_source_config	object	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	Yes
└─ include_sample_schema	boolean	Whether the eval should expect you to populate the sample namespace (ie, by generating responses off of your data source)	No	False
└─ item_schema	object	The json schema for each row in the data source.	No
└─ metadata	object	Metadata filters for the logs data source.	No
└─ type	enum	The type of data source. Always logs. Possible values: logs	No
metadata	Metadata	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
name	string	The name of the evaluation.	No
testing_criteria	array	A list of graders for all eval runs in this group.	Yes

CreateEvalRunRequest

Name	Type	Description	Required	Default
data_source	object	A JsonlRunDataSource object with that specifies a JSONL file that matches the eval	Yes
└─ input_messages	object		No
└─ item_reference	string	A reference to a variable in the ‘item’ namespace, e.g., ‘item.name’.	No
└─ template	array	A list of chat messages forming the prompt or context. May include variable references to the ‘item’ namespace, e.g., {{item.name}}.	No
└─ type	enum	The type of input messages. Either template or item_reference. Possible values: template, item_reference	No
└─ model	string	The name of the model to use for generating completions (e.g., ‘o3-mini’).	No
└─ sampling_params	object		No
└─ max_completion_tokens	integer	The maximum number of tokens in the generated output.	No
└─ seed	integer	A seed value to initialize the randomness, during sampling.	No	42
└─ temperature	number	A higher temperature increases randomness in the outputs.	No	1
└─ top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1
└─ source	object		No
└─ type	enum	The type of source. Can be one of EvalJsonlFileContentSource, EvalJsonlFileIdSource, or EvalStoredCompletionsSource. Possible values: EvalJsonlFileContentSource, EvalJsonlFileIdSource, EvalStoredCompletionsSource	No
└─ type	enum	The type of run data source. Always completions. Possible values: completions	No
metadata	Metadata	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
name	string	The name of the run.	No

CreateEvalStoredCompletionsRunDataSource

A StoredCompletionsRunDataSource configuration describing a set of filters

Name	Type	Description	Required	Default
created_after	integer	An optional Unix timestamp to filter items created after this time.	No
created_before	integer	An optional Unix timestamp to filter items created before this time.	No
limit	integer	An optional maximum number of items to return.	No
metadata	Metadata	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
model	string	An optional model to filter by (e.g., ‘gpt-4o’).	No
type	enum	The type of data source. Always stored_completions. Possible values: stored_completions	Yes

CustomCompute

Custom compute.

Name	Type	Description	Required	Default
computeId	string	Id of the custom compute	No
kind	ComputeType	The compute type.	Yes

DeploymentConnection

Relative deployment connection.

Name	Type	Description	Required	Default
kind	ConnectionType	The connection type.	Yes

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.

Name	Type	Description	Required	Default
fine_tune	integer	The end date of fine tune support of this model. Will be null for fine tune models.	No
inference	integer	The end date of inference support of this model.	Yes

DpoHyperparamsRequest

Hyperparameters for DPO method of fine-tuning

Name	Type	Description	Required	Default
batch_size	integer	The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass. In general, we’ve found that larger batch sizes tend to work better for larger datasets.The default value as well as the maximum value for this property are specific to a base model.	No
beta	number	DPO beta value.	No
l2_multiplier	number	L2 regularization multiplier	No
learning_rate_multiplier	number	The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pre-training multiplied by this value. Larger learning rates tend to perform better with larger batch sizes. We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results.	No
n_epochs	integer	The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.	No

DpoMethod

Request for DPO method fine-tuning

Name	Type	Description	Required	Default
dpo	DpoMethodConfigRequest	Configuration for dpo fine-tuning method. Includes DPO specific hyperparameters	Yes
type	FineTuningMethodType		Yes

DpoMethodConfigRequest

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

Name	Type	Description	Required	Default
hyperparameters	DpoHyperparamsRequest	Hyperparameters for DPO method of fine-tuning	No

DpoMethodRequest

Request for DPO method fine-tuning

Name	Type	Description	Required	Default
dpo	DpoMethodConfigRequest	Configuration for dpo fine-tuning method. Includes DPO specific hyperparameters	Yes
type	FineTuningMethodType		Yes

EndpointKeyConnection

Endpoint key connection.

Name	Type	Description	Required	Default
endpoint	string	Endpoint	No
key	string	Key	No
kind	ConnectionType	The connection type.	Yes

EndpointMIConnection

Endpoint Managed Identity connection.

Name	Type	Description	Required	Default
endpoint	string	Endpoint	No
kind	ConnectionType	The connection type.	Yes
resourceId	string	Resource Id	No

Error

Error content as defined in the Microsoft REST guidelines.

Name	Type	Description	Required	Default
code	ErrorCode	Error codes as defined in the Microsoft REST guidelines.	Yes
details	array	The error details if available.	No
innererror	InnerError	Inner error as defined in the Microsoft REST guidelines.	No
message	string	The message of this error.	Yes
target	string	The location where the error happened if available.	No

ErrorCode

Error codes as defined in the Microsoft REST guidelines.

Property	Value
Description	Error codes as defined in the Microsoft REST guidelines.
Type	string
Values	conflict invalidPayload forbidden notFound unexpectedEntityState itemDoesAlreadyExist serviceUnavailable internalFailure quotaExceeded jsonlValidationFailed fileImportFailed tooManyRequests unauthorized contentFilter

ErrorResponse

Error response as defined in the Microsoft REST guidelines.

Name	Type	Description	Required	Default
error	Error	Error content as defined in the Microsoft REST guidelines.	Yes

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

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the eval was created.	Yes
data_source_config	object	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	Yes
└─ metadata	Metadata	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
└─ schema	object	The json schema for the run data source items. Learn how to build JSON schemas here.	No
└─ type	enum	The type of data source. Always stored_completions. Possible values: stored_completions	No
id	string	Unique identifier for the evaluation.	Yes
metadata	Metadata	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.	Yes
name	string	The name of the evaluation.	Yes
object	enum	The object type. Possible values: eval	Yes
testing_criteria	array	A list of testing criteria.	Yes

EvalApiError

An object representing an error response from the Eval API.

Name	Type	Description	Required	Default
code	string	The error code.	Yes
message	string	The error message.	Yes

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

Name	Type	Description	Required	Default
schema	object	The json schema for the run data source items. Learn how to build JSON schemas here.	Yes
type	enum	The type of data source. Always custom. Possible values: custom	Yes

EvalFileRunDataSource

A FileRunDataSource configuration with a file id

Name	Type	Description	Required	Default
file_id	string	The identifier of the file.	Yes
type	enum	The type of data source. Always file. Possible values: file	Yes

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.

Name	Type	Description	Required	Default
content	object	A text input to the model.	Yes
└─ text	string	The text output from the model.	No
└─ type	enum	The type of the output text. Always output_text. Possible values: output_text	No
role	enum	The role of the message input. One of user, assistant, system, or developer. Possible values: user, assistant, system, developer	Yes
type	enum	The type of the message input. Always message. Possible values: message	No

EvalJsonlFileContentSource

Name	Type	Description	Required	Default
content	array	The content of the jsonl file.	Yes
type	enum	The type of jsonl source. Always file_content. Possible values: file_content	Yes

EvalJsonlFileIdSource

Name	Type	Description	Required	Default
id	string	The identifier of the file.	Yes
type	enum	The type of jsonl source. Always file_id. Possible values: file_id	Yes

EvalLabelModelGrader

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

Name	Type	Description	Required	Default
input	array		Yes
labels	array	The labels to assign to each item in the evaluation.	Yes
model	string	The model to use for the evaluation. Must support structured outputs.	Yes
name	string	The name of the grader.	Yes
passing_labels	array	The labels that indicate a passing result. Must be a subset of labels.	Yes
type	enum	The object type, which is always label_model. Possible values: label_model	Yes

EvalList

An object representing a list of evals.

Name	Type	Description	Required	Default
data	array	An array of eval objects.	Yes
first_id	string	The identifier of the first eval in the data array.	Yes
has_more	boolean	Indicates whether there are more evals available.	Yes
last_id	string	The identifier of the last eval in the data array.	Yes
object	enum	The type of this object. It’s always set to “list”. Possible values: list	Yes

EvalRun

A schema representing an evaluation run.

Name	Type	Description	Required	Default
created_at	integer	Unix timestamp (in seconds) when the evaluation run was created.	Yes
data_source	object	A JsonlRunDataSource object with that specifies a JSONL file that matches the eval	Yes
└─ input_messages	object		No
└─ item_reference	string	A reference to a variable in the ‘item’ namespace, e.g., ‘item.name’.	No
└─ template	array	A list of chat messages forming the prompt or context. May include variable references to the ‘item’ namespace, e.g., {{item.name}}.	No
└─ type	enum	The type of input messages. Either template or item_reference. Possible values: template, item_reference	No
└─ model	string	The name of the model to use for generating completions (e.g., ‘o3-mini’).	No
└─ sampling_params	object		No
└─ max_completion_tokens	integer	The maximum number of tokens in the generated output.	No
└─ seed	integer	A seed value to initialize the randomness, during sampling.	No	42
└─ temperature	number	A higher temperature increases randomness in the outputs.	No	1
└─ top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1
└─ source	object		No
└─ type	enum	The type of source. Can be one of EvalJsonlFileContentSource, EvalJsonlFileIdSource, or EvalStoredCompletionsSource. Possible values: EvalJsonlFileContentSource, EvalJsonlFileIdSource, EvalStoredCompletionsSource	No
└─ type	enum	The type of run data source. Always completions. Possible values: completions	No
error	EvalApiError	An object representing an error response from the Eval API.	Yes
eval_id	string	The identifier of the associated evaluation.	Yes
id	string	Unique identifier for the evaluation run.	Yes
metadata	Metadata	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.	Yes
model	string	The model that is evaluated, if applicable.	Yes
name	string	The name of the evaluation run.	Yes
object	enum	The type of the object. Always “eval.run”. Possible values: eval.run	Yes
per_model_usage	array	Usage statistics for each model during the evaluation run.	Yes
per_testing_criteria_results	array	Results per testing criteria applied during the evaluation run.	Yes
report_url	string	The URL to the rendered evaluation run report on the UI dashboard.	Yes
result_counts	object	Counters summarizing the outcomes of the evaluation run.	Yes
└─ errored	integer	Number of output items that resulted in an error.	No
└─ failed	integer	Number of output items that failed to pass the evaluation.	No
└─ passed	integer	Number of output items that passed the evaluation.	No
└─ total	integer	Total number of executed output items.	No
status	string	The status of the evaluation run.	Yes

EvalRunList

An object representing a list of runs for an evaluation.

Name	Type	Description	Required	Default
data	array	An array of eval run objects.	Yes
first_id	string	The identifier of the first eval run in the data array.	Yes
has_more	boolean	Indicates whether there are more evals available.	Yes
last_id	string	The identifier of the last eval run in the data array.	Yes
object	enum	The type of this object. It’s always set to “list”. Possible values: list	Yes

EvalRunOutputItem

A schema representing an evaluation run output item.

Name	Type	Description	Required	Default
created_at	integer	Unix timestamp (in seconds) when the evaluation run was created.	Yes
datasource_item	object	Details of the input data source item.	Yes
datasource_item_id	integer	The identifier for the data source item.	Yes
eval_id	string	The identifier of the evaluation group.	Yes
id	string	Unique identifier for the evaluation run output item.	Yes
object	enum	The type of the object. Always “eval.run.output_item”. Possible values: eval.run.output_item	Yes
results	array	A list of results from the evaluation run.	Yes
run_id	string	The identifier of the evaluation run associated with this output item.	Yes
sample	object	A sample containing the input and output of the evaluation run.	Yes
└─ error	EvalApiError	An object representing an error response from the Eval API.	No
└─ finish_reason	string	The reason why the sample generation was finished.	No
└─ input	array	An array of input messages.	No
└─ max_completion_tokens	integer	The maximum number of tokens allowed for completion.	No
└─ model	string	The model used for generating the sample.	No
└─ output	array	An array of output messages.	No
└─ seed	integer	The seed used for generating the sample.	No
└─ temperature	number	The sampling temperature used.	No
└─ top_p	number	The top_p value used for sampling.	No
└─ usage	object	Token usage details for the sample.	No
└─ cached_tokens	integer	The number of tokens retrieved from cache.	No
└─ completion_tokens	integer	The number of completion tokens generated.	No
└─ prompt_tokens	integer	The number of prompt tokens used.	No
└─ total_tokens	integer	The total number of tokens used.	No
status	string	The status of the evaluation run.	Yes

EvalRunOutputItemList

An object representing a list of output items for an evaluation run.

Name	Type	Description	Required	Default
data	array	An array of eval run output item objects.	Yes
first_id	string	The identifier of the first eval run output item in the data array.	Yes
has_more	boolean	Indicates whether there are more eval run output items available.	Yes
last_id	string	The identifier of the last eval run output item in the data array.	Yes
object	enum	The type of this object. It’s always set to “list”. Possible values: list	Yes

EvalScoreModelGrader

A ScoreModelGrader object that uses a model to assign a score to the input.

Name	Type	Description	Required	Default
input	array	The input text. This may include template strings.	Yes
model	string	The model to use for the evaluation.	Yes
name	string	The name of the grader.	Yes
pass_threshold	number	The threshold for the score.	No
range	array	The range of the score. Defaults to [0, 1].	No
sampling_params	object	The sampling parameters for the model.	No
type	enum	The object type, which is always score_model. Possible values: score_model	Yes

EvalStoredCompletionsDataSourceConfig

A StoredCompletionsDataSourceConfig which specifies the metadata property of your stored completions query. This is usually metadata like usecase=chatbot or prompt-version=v2, etc. The schema returned by this data source config is used to defined what variables are available in your evals. item and sample are both defined when using this data source config.

Name	Type	Description	Required	Default
metadata	Metadata	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
schema	object	The json schema for the run data source items. Learn how to build JSON schemas here.	Yes
type	enum	The type of data source. Always stored_completions. Possible values: stored_completions	Yes

EvalStoredCompletionsSource

A StoredCompletionsRunDataSource configuration describing a set of filters

Name	Type	Description	Required	Default
created_after	integer	An optional Unix timestamp to filter items created after this time.	No
created_before	integer	An optional Unix timestamp to filter items created before this time.	No
limit	integer	An optional maximum number of items to return.	No
metadata	Metadata	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
model	string	An optional model to filter by (e.g., ‘gpt-4o’).	No
type	enum	The type of source. Always stored_completions. Possible values: stored_completions	Yes

EvalStringCheckGrader

A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.

Name	Type	Description	Required	Default
input	string	The input text. This may include template strings.	Yes
name	string	The name of the grader.	Yes
operation	enum	The string check operation to perform. One of eq, ne, like, or ilike. Possible values: eq, ne, like, ilike	Yes
reference	string	The reference text. This may include template strings.	Yes
type	enum	The object type, which is always string_check. Possible values: string_check	Yes

EvalTextSimilarityGrader

A TextSimilarityGrader object which grades text based on similarity metrics.

Name	Type	Description	Required	Default
evaluation_metric	enum	The evaluation metric to use. One of fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l. Possible values: fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, rouge_l	Yes
input	string	The text being graded.	Yes
name	string	The name of the grader.	No
pass_threshold	number	A float score where a value greater than or equal indicates a passing grade.	Yes
reference	string	The text being graded against.	Yes
type	enum	The type of grader. Possible values: text_similarity	Yes

EventType

Defines the severity of a content filter result.

Property	Value
Description	Defines the severity of a content filter result.
Type	string
Values	message metrics

File

A file is a document usable for training and validation. It can also be a service generated document with result details.

Name	Type	Description	Required	Default
bytes	integer	The size of this file when available (can be null). File sizes larger than 2^53-1 aren’t supported to ensure compatibility with JavaScript integers.	No
created_at	integer	A timestamp when this job or item was created (in unix epochs).	No
expires_at	integer	A unix timestamp (the number of seconds that have elapsed since January 1, 1970) when the file is expired.	No
filename	string	The name of the file.	Yes
id	string	The identity of this item.	No
object	TypeDiscriminator	Defines the type of an object.	No
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes
status	FileState	The state of a file.	No
status_details	string	The error message with details in case processing of this file failed. Deprecated.	No

FileCreate

Defines a document to import from an external content url to be usable with Azure OpenAI.

Name	Type	Description	Required	Default
content_url	string	The url to download the document from (can be SAS url of a blob or any other external url accessible with a GET request).	Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

FileDelete

Defines the response for File Delete.

Name	Type	Description	Required	Default
deleted	boolean	A value indicating whether gets if the file was deleted.	Yes
id	string	The file-id that was deleted.	Yes
object	string	If the file was deleted.	Yes

FileDetails

A file detail is a document used by batch service to fetch file blob details.

Name	Type	Description	Required	Default
filename	string	The name of the file.	Yes
id	string	The identity of this item.	No
path	string	The the relative path to the file within the container.	No
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes
storage_account_uri	string	The storage account url of this file.	No
storage_container_name	string	The Storage Container Name of this file blob.	No

FileExpiresAfter

Defines an expiration for the file.

Name	Type	Description	Required	Default
anchor	FileExpiryAnchor	Defines the anchor relative to what time the absolute expiration should be generated from.	No
seconds	integer	The relative expiration time in seconds. Range: [1209600 - 2592000].	No

FileExpiryAnchor

Defines the anchor relative to what time the absolute expiration should be generated from.

Property	Value
Description	Defines the anchor relative to what time the absolute expiration should be generated from.
Type	string
Values	created_at

FileImport

Defines a document to import from an external content url to be usable with Azure OpenAI.

Name	Type	Description	Required	Default
content_url	string	The url to download the document from (can be SAS url of a blob or any other external url accessible with a GET request).	Yes
expires_after	FileExpiresAfter	Defines an expiration for the file.	No
filename	string	The name of the JSON Lines file to be uploaded. If the purpose is set to “fine-tune”, each line is a JSON record with “prompt” and “completion” fields representing your training examples.	Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

FileList

Represents a list of files.

Name	Type	Description	Required	Default
data	array	The list of items.	No
object	TypeDiscriminator	Defines the type of an object.	No

FileState

The state of a file.

Property	Value
Description	The state of a file.
Type	string
Values	uploaded pending running processed error deleting deleted

FineTuneMethod

Discriminator for FineTuneMethod

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

Type Value	Schema

Name	Type	Description	Required	Default
type	FineTuningMethodType		Yes

FineTuneMethodRequest

Discriminator for FineTuneMethodRequest

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

Type Value	Schema

Name	Type	Description	Required	Default
type	FineTuningMethodType		Yes

FineTuningHyperParameters

The hyper parameter settings used in a fine tune job.

Name	Type	Description	Required	Default
batch_size	integer	The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass. In general, we’ve found that larger batch sizes tend to work better for larger datasets. The default value as well as the maximum value for this property are specific to a base model.	No
learning_rate_multiplier	number	The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pre-training multiplied by this value. Larger learning rates tend to perform better with larger batch sizes. We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results.	No
n_epochs	integer	The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.	No

FineTuningJob

Defines the values of a fine tune job.

Name	Type	Description	Required	Default
created_at	integer	A timestamp when this job or item was created (in unix epochs).	No
error	FineTuningJobError	For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.	No
estimated_finish	integer	The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job isn’t running.	No
fine_tuned_model	string	The identifier (model-id) of the resulting fine tuned model. This property is only populated for successfully completed fine-tuning runs. Use this identifier to create a deployment for inferencing.	No
finished_at	integer	A timestamp when this job or item has finished successfully (in unix epochs).	No
hyperparameters	FineTuningHyperParameters	The hyper parameter settings used in a fine tune job.	No
id	string	The identity of this item.	No
integrations	array	A list of configurations for integrations supporting the fine-tuning job. There are many integrations planned, so make sure to check and act on the integration type.	No
method	object	Method used for supervised fine-tuning	No
└─ type	FineTuningMethodType		No
model	string	The identifier (model-id) of the base model used for the fine-tune.	Yes
object	TypeDiscriminator	Defines the type of an object.	No
organisation_id	string	The organization id of this fine tune job. Unused on Azure OpenAI; compatibility for OpenAI only.	No
result_files	array	The result file identities (file-id) containing training and evaluation metrics in csv format. The file is only available for successfully completed fine-tuning runs.	No
seed	integer	The seed used for the fine-tuning job.	No
status	FineTuningState	The state of a fine-tuning object or fine tuning job.	No
suffix	string	The suffix used to identify the fine-tuned model. The suffix can contain up to 40 characters (a-z, A-Z, 0-9,- and _) that will be added to your fine-tuned model name.	No
trained_tokens	integer	The total number of billable tokens processed by this fine tuning job.	No
training_file	string	The file which is used for training.	Yes
validation_file	string	The file which is used to evaluate the fine tuned model during training.	No

FineTuningJobCheckpoint

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the checkpoint was created.	Yes
fine_tuned_model_checkpoint	string	The name of the fine-tuned checkpoint model that is created.	Yes
fine_tuning_job_id	string	The name of the fine-tuning job that this checkpoint was created from.	Yes
id	string	The identity of this checkpoint.	No
metrics	object	The metrics at the step number during the fine-tuning job.	Yes
object	TypeDiscriminator	Defines the type of an object.	No
step_number	integer	The step number that the checkpoint was created at.	Yes

FineTuningJobCheckpointList

Represents a list of checkpoints.

Name	Type	Description	Required	Default
data	array	The list of items.	No
has_more	boolean	A value indicating whether the list contains more elements than returned.	No
object	TypeDiscriminator	Defines the type of an object.	No

FineTuningJobCreation

Defines the values of a fine tune job.

Name	Type	Description	Required	Default
hyperparameters	FineTuningHyperParameters	The hyper parameter settings used in a fine tune job.	No
integrations	array	A list of configurations for integrations supporting the fine-tuning job. There are many integrations planned, so make sure to check and act on the integration type.	No
method	object	Method used for supervised fine-tuning	No
└─ type	FineTuningMethodType		No
model	string	The identifier (model-id) of the base model used for this fine-tune.	Yes
seed	integer	The seed used for the fine-tuning job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed isn’t specified, one will be generated for you.	No
suffix	string	The suffix used to identify the fine-tuned model. The suffix can contain up to 40 characters (a-z, A-Z, 0-9,- and _) that will be added to your fine-tuned model name.	No
training_file	string	The file identity (file-id) that is used for training this fine tuned model.	Yes
validation_file	string	The file identity (file-id) that is used to evaluate the fine tuned model during training.	No

FineTuningJobError

For fine-tuning jobs that have failed, this will contain more information on the cause of the failure.

Name	Type	Description	Required	Default
code	string	The machine-readable error code.	No
message	string	The human-readable error message.	No
param	string	The parameter that was invalid, usually training_file or validation_file. This field will be null if the failure was not parameter-specific.	No

FineTuningJobEvent

Name	Type	Description	Required	Default
created_at	integer	A timestamp when this event was created (in unix epochs).	Yes
data		Machine readable data of this event.	No
id	string	The identity of this event.	No
level	LogLevel	The verbosity level of an event.	Yes
message	string	The message describing the event. This can be a change of state, e.g., enqueued, started, failed or completed, or other events like uploaded results.	Yes
object	TypeDiscriminator	Defines the type of an object.	No
type	EventType	Defines the severity of a content filter result.	Yes

FineTuningJobEventList

Represents a list of events.

Name	Type	Description	Required	Default
data	array	The list of items.	No
has_more	boolean	A value indicating whether the list contains more elements than returned.	No
object	TypeDiscriminator	Defines the type of an object.	No

FineTuningJobList

Represents a list of fine tunes.

Name	Type	Description	Required	Default
data	array	The list of items.	No
has_more	boolean	A value indicating whether the list contains more elements than returned.	No
object	TypeDiscriminator	Defines the type of an object.	No

FineTuningMethodType

Property	Value
Type	string
Values	dpo supervised

FineTuningState

The state of a fine-tuning object or fine tuning job.

Property	Value
Description	The state of a fine-tuning object or fine tuning job.
Type	string
Values	created pending running pausing paused resuming succeeded cancelled failed

FunctionCallFunction

Name	Type	Description	Required	Default
arguments	string	The arguments that the model expects you to pass to the function.	No
name	string	The name of the function.	No

FunctionDefinition

Name	Type	Description	Required	Default
description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
name	string	The name of the function to be called.	No
parameters		The parameters the functions accepts, described as a JSON Schema object.	No

GenericEmbeddingSettings

Connection Embedding Settings

Name	Type	Description	Required	Default
connection	BaseConnection	A connection to a resource.	No
deploymentName	string		No
modelName	string		No

IngestionError

The details of the ingestion error

Name	Type	Description	Required	Default
innerErrors	array		No
message	string		No

IngestionJob

Represents the details of a job.

Discriminator for IngestionJob

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

Type Value	Schema

Name	Type	Description	Required	Default
jobId	string		No
kind	IngestionJobType	The job type.	Yes

IngestionJobList

Represents a list of ingestion jobs.

Name	Type	Description	Required	Default
nextLink	string	The link to the next page.	No
value	array	The list of items.	No

IngestionJobProgress

Name	Type	Description	Required	Default
stageProgress	array		Yes

IngestionJobRun

The details of a job run

Name	Type	Description	Required	Default
error	IngestionError	The details of the ingestion error	No
jobId	string		No
progress	IngestionJobProgress		No
runId	string		No
status	OperationState	The state of a job or item.	No
warnings	array		No

IngestionJobRunList

Represents a list of ingestion job runs.

Name	Type	Description	Required	Default
nextLink	string	The link to the next page.	No
value	array	The list of items.	No

IngestionJobStageProgress

Name	Type	Description	Required	Default
name	string		No
processedItems	integer		No
state	OperationState	The state of a job or item.	No
subStageProgress	array		No
totalItems	integer		No

IngestionJobSystemCompute

Name	Type	Description	Required	Default
completionAction	CompletionAction	The completion action.	No
dataRefreshIntervalInHours	integer		No
datasource	SystemComputeDatasource		No
jobId	string		No
kind	IngestionJobType	The job type.	Yes
searchServiceConnection	BaseConnection	A connection to a resource.	No

IngestionJobType

The job type.

Property	Value
Description	The job type.
Type	string
Values	SystemCompute UserCompute

IngestionJobUserCompute

Name	Type	Description	Required	Default
compute	JobCompute	The compute settings of the job.	No
dataRefreshIntervalInHours	integer		No
datasource	UserComputeDatasource		No
jobId	string		No
kind	IngestionJobType	The job type.	Yes
target	TargetIndex	Information about the index to be created.	No
workspaceId	string		No

InnerError

Inner error as defined in the Microsoft REST guidelines.

Name	Type	Description	Required	Default
code	InnerErrorCode	Inner error codes as defined in the Microsoft REST guidelines.	No
innererror	InnerError	Inner error as defined in the Microsoft REST guidelines.	No

InnerErrorCode

Inner error codes as defined in the Microsoft REST guidelines.

Property	Value
Description	Inner error codes as defined in the Microsoft REST guidelines.
Type	string
Values	invalidPayload

InputMessage

Name	Type	Description	Required	Default
content	string	The contents of the message.	No
id	string	The identity of message.	No
name	string	An optional name for the participant. Provides the model information to differentiate between participants of the same role.	No
role	string	The role of the entity that is creating the message.	No

InputTextContent

A text input to the model.

Name	Type	Description	Required	Default
text	string	The text input to the model.	Yes
type	enum	The type of the input item. Always input_text. Possible values: input_text	Yes

IntegrationTypes

List of the fine-tuning integrations that are available.

Property	Value
Description	List of the fine-tuning integrations that are available.
Type	string
Values	wandb

JobCompute

The compute settings of the job.

Discriminator for JobCompute

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

Type Value	Schema

Name	Type	Description	Required	Default
kind	ComputeType	The compute type.	Yes

LifeCycleStatus

The life cycle status of a model.

Note: A model can be promoted from preview to generally-available, but never from generally-available to preview.

Property	Value
Description	The life cycle status of a model. Note: A model can be promoted from preview to generally-available, but never from generally-available to preview.
Type	string
Values	preview generally-available deprecating deprecated

LogLevel

The verbosity level of an event.

Property	Value
Description	The verbosity level of an event.
Type	string
Values	info warning error

Logprob

Name	Type	Description	Required	Default
logprob	number	The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.	No
token	string	The token.	No

Metadata

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.

Model

A model is either a base model or the result of a successful fine tune job.

Name	Type	Description	Required	Default
capabilities	Capabilities	The capabilities of a base or fine tune model.	Yes
created_at	integer	A timestamp when this job or item was created (in unix epochs).	No
deprecation	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.	Yes
fine_tune	string	The fine tune job identity (fine-tune-id) if this is a fine tune model; otherwise null.	No
id	string	The identity of this item.	No
lifecycle_status	LifeCycleStatus	The life cycle status of a model. Note: A model can be promoted from “preview” to generally-available, but never from generally-available to “preview”.	Yes
model	string	The base model identity (model-id) if this is a fine tune model; otherwise null.	No
object	TypeDiscriminator	Defines the type of an object.	No
status	FineTuningState	The state of a fine-tuning object or fine tuning job.	No

ModelList

Represents a list of models.

Name	Type	Description	Required	Default
data	array	The list of items.	No
object	TypeDiscriminator	Defines the type of an object.	No

OperationState

The state of a job or item.

Property	Value
Description	The state of a job or item.
Type	string
Values	notRunning running succeeded failed

Order

Defines the purpose of a file.

Property	Value
Description	Defines the purpose of a file.
Type	string
Values	desc asc

OrderByOrder

Property	Value
Type	string
Values	asc desc

PineconeIndex

Pinecone Index.

Name	Type	Description	Required	Default
connectionId	string	The id of the connection pointing to the pinecone.	No
kind	TargetType	The target type.	Yes

Purpose

The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.

Property	Value
Description	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.
Type	string
Values	fine-tune fine-tune-results assistants assistants_output batch batch_output evals evals_output

ServerlessCompute

Serverless compute.

Name	Type	Description	Required	Default
instanceCount	integer	The count of instances to run the job on.	No
kind	ComputeType	The compute type.	Yes
sku	string	SKU Level	No

StoredCompletion

Name	Type	Description	Required	Default
choices	array	A list of chat completion choices. Can be more than one if n is greater than 1.	No
created	integer	The Unix timestamp (in seconds) of when the chat completion was created.	No
frequency_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.	No
id	string	The identity of stored completion.	No
input_user	string	The input user for this request.	No
metadata	object	Arbitrary key-value pairs for additional information.	No
model	string	ID of the model to use.	No
presence_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.	No
request_id	string	A unique identifier for the OpenAI API request. Please include this request ID when contacting support.	No
seed	integer	If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism isn’t guaranteed, and you should refer to the
system_fingerprint response parameter to monitor changes in the backend.	No
service_tier	string	Specifies the latency tier to use for processing the request.	No
system_fingerprint	string	This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.	No
temperature	number	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.	No
tool_choice	string	Controls which (if any) tool is called by the model.	No
tools	array	A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.	No
top_p	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.	No
usage	Usage		No

StoredCompletionDelete

Name	Type	Description	Required	Default
deleted	boolean	A value indicating whether gets if the stored completion was deleted.	No
id	string	The stored completion id that was deleted.	No
object	string	If the stored completion was deleted.	Yes

StoredCompletionList

Name	Type	Description	Required	Default
data	array	The list of retrieved objects.	No
first_id	string	The first id in the retrieved list	No
has_more	boolean	The has_more property is used for pagination to indicate there are additional results.	No
last_id	string	The last id in the retrieved list	No
object	string	The object type, which is always list	No
total	integer	Total number of items.	No

StoredCompletionMessages

Name	Type	Description	Required	Default
data	array	The list of retrieved objects.	No
first_id	string	The first id in the retrieved list	No
has_more	boolean	The has_more property is used for pagination to indicate there are additional results.	No
last_id	string	The last id in the retrieved list	No
object	string	The object type, which is always list	No
total	integer	Total number of items.	No

StoredCompletionResponse

Name	Type	Description	Required	Default
choices	array	A list of chat completion choices. Can be more than one if n is greater than 1.	No
created	integer	The Unix timestamp (in seconds) of when the chat completion was created.	No
frequency_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.	No
id	string	The identity of stored completion.	No
input_user	string	The input user for this request.	No
metadata	object	Arbitrary key-value pairs for additional information.	No
model	string	ID of the model to use.	No
object	string	The type of this object.	No
presence_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.	No
request_id	string	A unique identifier for the OpenAI API request. Please include this request ID when contacting support.	No
seed	integer	If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seedand parameters should return the same result. Determinism isn’t guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.	No
service_tier	string	Specifies the latency tier to use for processing the request.	No
system_fingerprint	string	This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.	No
temperature	number	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.	No
tool_choice	string	Controls which (if any) tool is called by the model.	No
tools	array	A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.	No
top_p	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.	No
usage	Usage		No

SupervisedMethod

Method used for supervised fine-tuning

Name	Type	Description	Required	Default
type	FineTuningMethodType		Yes

SupervisedMethodRequest

Method used for supervised fine-tuning

Name	Type	Description	Required	Default
type	FineTuningMethodType		Yes

SystemComputeDatasource

Discriminator for SystemComputeDatasource

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

Type Value	Schema

Name	Type	Description	Required	Default
kind	SystemComputeDatasourceType	The datasource type.	Yes

SystemComputeDatasourceType

The datasource type.

Property	Value
Description	The datasource type.
Type	string
Values	Storage Urls

SystemComputeStorage

Storage account

Name	Type	Description	Required	Default
chunking	ChunkingSettings	Chunking settings	No
connection	BaseConnection	A connection to a resource.	No
containerName	string	container name	No
embeddings	array		No
kind	SystemComputeDatasourceType	The datasource type.	Yes

SystemComputeUrl

Urls

Name	Type	Description	Required	Default
chunking	ChunkingSettings	Chunking settings	No
connection	BaseConnection	A connection to a resource.	No
containerName	string	container name	No
crawling	CrawlingSettings	Crawling settings	No
embeddings	array		No
kind	SystemComputeDatasourceType	The datasource type.	Yes
urls	array		No

TargetIndex

Information about the index to be created.

Discriminator for TargetIndex

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

Type Value	Schema

Name	Type	Description	Required	Default
kind	TargetType	The target type.	Yes

TargetType

The target type.

Property	Value
Description	The target type.
Type	string
Values	AzureAISearch CosmosDB Pinecone

Tool

Name	Type	Description	Required	Default
function	FunctionDefinition		No
type	string	The type of tool call. This is always going to be function for this type of tool call.	No

ToolCall

Name	Type	Description	Required	Default
function	FunctionCallFunction		No
id	string	The ID of the tool call.	No
type	string	The type of tool call the output is required for. For now, this is always function.	No

TypeDiscriminator

Defines the type of an object.

Property	Value
Description	Defines the type of an object.
Type	string
Values	list fine_tuning.job file fine_tuning.job.event fine_tuning.job.checkpoint model upload upload.part batch wandb

UpdateStoredCompletionRequest

Name	Type	Description	Required	Default
metadata	object	Arbitrary key-value pairs for additional information.	No

UploadFileCompleteBody

Name	Type	Description	Required	Default
md5	string		No
part_ids	array		Yes

UploadFileStartBody

Name	Type	Description	Required	Default
bytes	integer		Yes
filename	string		Yes
mime_type	string		Yes
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	Yes

UploadPartResource

Name	Type	Description	Required	Default
azure_block_id	string		No
created_at	integer	A timestamp when this job or item was created (in unix epochs).	No
id	string	The identity of this item.	No
object	TypeDiscriminator	Defines the type of an object.	No
upload_id	string		No

UploadResource

Name	Type	Description	Required	Default
bytes	integer		No
created_at	integer	A timestamp when this job or item was created (in unix epochs).	No
expires_at	integer		No
file	File	A file is a document usable for training and validation. It can also be a service generated document with result details.	No
filename	string		No
id	string	The identity of this item.	No
object	TypeDiscriminator	Defines the type of an object.	No
purpose	Purpose	The intended purpose of the uploaded documents. Use “fine-tune” for fine-tuning. This allows us to validate the format of the uploaded file.	No
status	UploadStatus		No

UploadStatus

Property	Value
Type	string
Values	pending expired completed cancelled

Usage

Name	Type	Description	Required	Default
completion_tokens	integer	Number of tokens in the generated completion.	No
prompt_tokens	integer	Number of tokens in the prompt.	No
total_tokens	integer	Total number of tokens used in the request (prompt + completion).	No

UserComputeDataset

Storage account

Name	Type	Description	Required	Default
chunking	ChunkingSettings	Chunking settings	No
datasetId	string		No
datasetType	string		No
embeddings	array		No
kind	UserComputeDatasourceType	The datasource type.	Yes

UserComputeDatasource

Discriminator for UserComputeDatasource

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

Type Value	Schema

Name	Type	Description	Required	Default
kind	UserComputeDatasourceType	The datasource type.	Yes

UserComputeDatasourceType

The datasource type.

Property	Value
Description	The datasource type.
Type	string
Values	Dataset Urls

UserComputeUrl

Urls

Name	Type	Description	Required	Default
chunking	ChunkingSettings	Chunking settings	No
crawling	CrawlingSettings	Crawling settings	No
embeddings	array		No
kind	UserComputeDatasourceType	The datasource type.	Yes
urls	array		No

WandBIntegrationRequest

Name	Type	Description	Required	Default
entity	string		No
name	string		No
project	string		Yes
tags	array		No

WandBIntegrationRequestWrapper

Name	Type	Description	Required	Default
type	IntegrationTypes	List of fine-tuning integrations that are available.	Yes
wandb	WandBIntegrationRequest		Yes

WorkspaceConnection

AML Workspace connection.

Name	Type	Description	Required	Default
connectionId	string	ConnectionId	No
kind	ConnectionType	The connection type.	Yes

WorkspaceConnectionEmbeddingSettings

Connection id to the embedding model

Name	Type	Description	Required	Default
connectionId	string		No
deploymentName	string		No
modelName	string		No

Next steps

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