Azure OpenAI in Microsoft Foundry Models v1 REST API reference

Learn how to use Azure OpenAI’s v1 REST API.

• v1 OpenAPI 3.0 spec

API Version: v1

Server Variables:

Variable	Default	Description
endpoint		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

Authentication

API key

Pass an API key with the api-key header.

Auth tokens

Pass an auth token with the authorization header.

Oauth2authoauth20

Flow: implicit

Authorization URL: https://login.microsoftonline.com/common/oauth2/v2.0/authorize

Scopes:

• https://ai.azure.com/.default

Batch

Create batch

POST {endpoint}/openai/v1/batches

Creates and executes a batch from an uploaded file of requests

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Header

Name	Required	Type	Description
accept	True	string Possible values: application/json

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
completion_window	enum	The time frame within which the batch should be processed. Currently only 24h is supported. Possible values: 24h	Yes
endpoint	enum	The endpoint to be used for all requests in the batch. Currently /v1/chat/completions is supported. Possible values: /v1/chat/completions, /v1/embeddings	Yes
input_file_id	string	The ID of an uploaded file that contains requests for the new batch. Your input file must be formatted as a JSON file, and must be uploaded with the purpose batch.	No

Responses

Status Code: 201

Description: The request has succeeded and a new resource has been created as a result.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List batches

GET {endpoint}/openai/v1/batches

List your organization’s batches.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
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.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

Request Header

Name	Required	Type	Description
accept	True	string Possible values: application/json

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListBatchesResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve batch

GET {endpoint}/openai/v1/batches/{batch_id}

Retrieves a batch.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
batch_id	path	Yes	string	The ID of the batch to retrieve.

Request Header

Name	Required	Type	Description
accept	True	string Possible values: application/json

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel batch

POST {endpoint}/openai/v1/batches/{batch_id}/cancel

Cancels an in-progress batch.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
batch_id	path	Yes	string	The ID of the batch to cancel.

Request Header

Name	Required	Type	Description
accept	True	string Possible values: application/json

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Chat

Create chat completion

POST {endpoint}/openai/v1/chat/completions

Creates a chat completion.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
audio	OpenAI.CreateChatCompletionRequestAudio or null	Parameters for audio output. Required when audio output is requested with modalities: ["audio"].	No
frequency_penalty	number or null	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
function_call	string or OpenAI.ChatCompletionFunctionCallOption	Deprecated in favor of tool_choice. Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"name": "my_function"} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.	No
functions	array of OpenAI.ChatCompletionFunctions	Deprecated in favor of tools. A list of functions the model may generate JSON inputs for.	No
logit_bias	object or null	Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.	No
logprobs	boolean or null	Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.	No
max_completion_tokens	integer or null	An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.	No
max_tokens	integer or null	The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API. This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.	No
messages	array of OpenAI.ChatCompletionRequestMessage	A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.	Yes
metadata	OpenAI.Metadata or null		No
modalities	OpenAI.ResponseModalities	Output types that you would like the model to generate. Most models are capable of generating text, which is the default: ["text"] The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: ["text", "audio"]	No
model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	Yes
n	integer or null	How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.	No
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	No
prediction	OpenAI.PredictionContent	Static predicted output content, such as the content of a text file that is being regenerated.	No
└─ content	string or array of OpenAI.ChatCompletionRequestMessageContentPartText	The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly.	Yes
└─ type	enum	The type of the predicted content you want to provide. This type is currently always content. Possible values: content	Yes
presence_penalty	number or null	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
prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
prompt_cache_retention	string or null		No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
response_format	OpenAI.CreateChatCompletionRequestResponseFormat	An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.	No
└─ type	OpenAI.CreateChatCompletionRequestResponseFormatType		Yes
safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
seed	integer or null	This feature is in Beta. 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 is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.	No
stop	OpenAI.StopConfiguration	Not supported with latest reasoning models o3 and o4-mini. Up to four sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.	No
store	boolean or null	Whether or not to store the output of this chat completion request for use in model distillation or evals products.	No
stream	boolean or null	If set to true, the model response data will be streamed to the client as it is generated using server-sent events.	No
stream_options	OpenAI.ChatCompletionStreamOptions or null		No
temperature	number or null		No
tool_choice	OpenAI.ChatCompletionToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.	No
tools	array of OpenAI.ChatCompletionTool or OpenAI.CustomToolChatCompletions	A list of tools the model may call. You can provide either custom tools or function tools.	No
top_logprobs	integer or null		No
top_p	number or null		No
user	string (deprecated)	A unique identifier representing your end-user, which can help to monitor and detect abuse.	No
user_security_context	AzureUserSecurityContext	User security context contains several parameters that describe the application itself, and the end user that interacts with the application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. Learn more about protecting AI applications using Microsoft Defender for Cloud.	No
verbosity	OpenAI.Verbosity	Constrains the verbosity of the model’s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object or object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/chat/completions

Completions

Create completion

POST {endpoint}/openai/v1/completions

Creates a completion.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
best_of	integer or null	Generates best_of completions server-side and returns the “best” (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n. Note:* Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.	No
echo	boolean or null	Echo back the prompt in addition to the completion	No
frequency_penalty	number or null	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. See more information about frequency and presence penalties.	No
logit_bias	object or null	Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.	No
logprobs	integer or null	Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the five most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5.	No
max_tokens	integer or null	The maximum number of tokensthat can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model’s context length. Example Python code for counting tokens.	No
model	string	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	Yes
n	integer or null	How many completions to generate for each prompt. Note:* Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.	No
presence_penalty	number or null	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. See more information about frequency and presence penalties.	No
prompt	string or array of string or null		No
seed	integer or null	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 is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.	No
stop	OpenAI.StopConfiguration	Not supported with latest reasoning models o3 and o4-mini. Up to four sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.	No
stream	boolean or null	Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.	No
stream_options	OpenAI.ChatCompletionStreamOptions or null		No
suffix	string or null	The suffix that comes after a completion of inserted text. This parameter is only supported for gpt-3.5-turbo-instruct.	No
temperature	number or null	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
top_p	number or null	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
user	string	Learn more.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/completions

Containers

List containers

GET {endpoint}/openai/v1/containers

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerListResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create container

POST {endpoint}/openai/v1/containers

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
expires_after	OpenAI.CreateContainerBodyExpiresAfter		No
└─ anchor	enum	Possible values: last_active_at	Yes
└─ minutes	integer		Yes
file_ids	array of string	IDs of files to copy to the container.	No
memory_limit	enum	Optional memory limit for the container. Defaults to 1g. Possible values: 1g, 4g, 16g, 64g	No
name	string	Name of the container to create.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve container

GET {endpoint}/openai/v1/containers/{container_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete container

DELETE {endpoint}/openai/v1/containers/{container_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List container files

GET {endpoint}/openai/v1/containers/{container_id}/files

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container to list files from.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerFileListResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create container file

POST {endpoint}/openai/v1/containers/{container_id}/files

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container to create a file in.

Request Body

Content-Type: multipart/form-data

Name	Type	Description	Required	Default
file		The File object (not file name) to be uploaded.	No
file_id	string	Name of the file to create.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerFileResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve container file

GET {endpoint}/openai/v1/containers/{container_id}/files/{file_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container.
file_id	path	Yes	string	The ID of the file to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ContainerFileResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete container file

DELETE {endpoint}/openai/v1/containers/{container_id}/files/{file_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container.
file_id	path	Yes	string	The ID of the file to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve container file content

GET {endpoint}/openai/v1/containers/{container_id}/files/{file_id}/content

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
container_id	path	Yes	string	The ID of the container.
file_id	path	Yes	string	The ID of the file to retrieve content from.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/octet-stream	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Conversations

Create conversation

POST {endpoint}/openai/v1/conversations

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
items	array of OpenAI.InputItem or null		No
metadata	OpenAI.Metadata or null		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve conversation

GET {endpoint}/openai/v1/conversations/{conversation_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Update conversation

POST {endpoint}/openai/v1/conversations/{conversation_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation to update.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null	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

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete conversation

DELETE {endpoint}/openai/v1/conversations/{conversation_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeletedConversationResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List conversation items

GET {endpoint}/openai/v1/conversations/{conversation_id}/items

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation to list items for.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	The order to return the input items in. Default is desc.
after	query	No	string	An item ID to list items after, used in pagination.
include	query	No	array	Specify additional output data to include in the model response.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationItemList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create conversation items

POST {endpoint}/openai/v1/conversations/{conversation_id}/items

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation to add the item to.
include	query	No	array	Additional fields to include in the response.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
items	array of OpenAI.InputItem		Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationItemList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve conversation item

GET {endpoint}/openai/v1/conversations/{conversation_id}/items/{item_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation that contains the item.
item_id	path	Yes	string	The ID of the item to retrieve.
include	query	No	array	Additional fields to include in the response.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationItem

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete conversation item

DELETE {endpoint}/openai/v1/conversations/{conversation_id}/items/{item_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
conversation_id	path	Yes	string	The ID of the conversation that contains the item.
item_id	path	Yes	string	The ID of the item to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ConversationResource

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Evals

List evals

GET {endpoint}/openai/v1/evals

List evaluations for a project.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
after	query	No	string	Identifier for the last eval from the previous pagination request.
limit	query	No	integer	A limit on the number of evals to be returned in a single pagination response.
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.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create eval

POST {endpoint}/openai/v1/evals

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	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
data_source_config	OpenAI.CreateEvalCustomDataSourceConfig or OpenAI.CreateEvalLogsDataSourceConfig or OpenAI.CreateEvalStoredCompletionsDataSourceConfig	The configuration for the data source used for the evaluation runs. Dictates the schema of the data used in the evaluation.	Yes
metadata	OpenAI.Metadata or null		No
name	string	The name of the evaluation.	No
statusCode	enum	Possible values: 201	Yes
testing_criteria	array of OpenAI.CreateEvalLabelModelGrader or OpenAI.EvalGraderStringCheck or OpenAI.EvalGraderTextSimilarity or OpenAI.EvalGraderPython or OpenAI.EvalGraderScoreModel or EvalGraderEndpoint	A list of graders for all eval runs in this group. Graders can reference variables in the data source using double curly braces notation, like {{item.variable_name}}. To reference the model’s output, use the sample namespace (ie, {{sample.output_text}}).	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.Eval

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get eval

GET {endpoint}/openai/v1/evals/{eval_id}

Retrieve an evaluation by its ID. Retrieves an evaluation by its ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.Eval

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Update eval

POST {endpoint}/openai/v1/evals/{eval_id}

Update select, mutable properties of a specified evaluation.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	OpenAI.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		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.Eval

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete eval

DELETE {endpoint}/openai/v1/evals/{eval_id}

Delete a specified evaluation.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get eval runs

GET {endpoint}/openai/v1/evals/{eval_id}/runs

Retrieve a list of runs for a specified evaluation.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
after	query	No	string
limit	query	No	integer
order	query	No	string Possible values: asc, desc
status	query	No	string Possible values: queued, in_progress, completed, canceled, failed

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalRunList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create eval run

POST {endpoint}/openai/v1/evals/{eval_id}/runs

Create a new evaluation run, beginning the grading process.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
data_source	OpenAI.CreateEvalJsonlRunDataSource or OpenAI.CreateEvalCompletionsRunDataSource or OpenAI.CreateEvalResponsesRunDataSource	Details about the run’s data source.	Yes
metadata	OpenAI.Metadata or null		No
name	string	The name of the run.	No

Responses

Status Code: 201

Description: The request has succeeded and a new resource has been created as a result.

Content-Type	Type	Description
application/json	OpenAI.EvalRun

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get eval run

GET {endpoint}/openai/v1/evals/{eval_id}/runs/{run_id}

Retrieve a specific evaluation run by its ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
run_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalRun

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel eval run

POST {endpoint}/openai/v1/evals/{eval_id}/runs/{run_id}

Cancel a specific evaluation run by its ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
run_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalRun

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete eval run

DELETE {endpoint}/openai/v1/evals/{eval_id}/runs/{run_id}

Delete a specific evaluation run by its ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
run_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get eval run output items

GET {endpoint}/openai/v1/evals/{eval_id}/runs/{run_id}/output_items

Get a list of output items for a specified evaluation run.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
run_id	path	Yes	string
after	query	No	string
limit	query	No	integer
status	query	No	string Possible values: fail, pass
order	query	No	string Possible values: asc, desc

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalRunOutputItemList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get eval run output item

GET {endpoint}/openai/v1/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}

Retrieve a specific output item from an evaluation run by its ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
eval_id	path	Yes	string
run_id	path	Yes	string
output_item_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.EvalRunOutputItem

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Files

Create file

POST {endpoint}/openai/v1/files

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: multipart/form-data

Name	Type	Description	Required	Default
expires_after	object		Yes
└─ anchor	AzureFileExpiryAnchor		Yes
└─ seconds	integer		Yes
file		The File object (not file name) to be uploaded.	Yes
purpose	enum	The intended purpose of the uploaded file. One of: - assistants: Used in the Assistants API - batch: Used in the Batch API - fine-tune: Used for fine-tuning - evals: Used for eval data sets Possible values: assistants, batch, fine-tune, evals	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/files

List files

GET {endpoint}/openai/v1/files

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
purpose	query	No	string
limit	query	No	integer
order	query	No	string Possible values: asc, desc
after	query	No	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListFilesResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve file

GET {endpoint}/openai/v1/files/{file_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
file_id	path	Yes	string	The ID of the file to use for this request.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete file

DELETE {endpoint}/openai/v1/files/{file_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
file_id	path	Yes	string	The ID of the file to use for this request.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteFileResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Download file

GET {endpoint}/openai/v1/files/{file_id}/content

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
file_id	path	Yes	string	The ID of the file to use for this request.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/octet-stream	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Embeddings

Create embedding

POST {endpoint}/openai/v1/embeddings

Creates an embedding vector representing the input text.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
dimensions	integer	The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models. Constraints: min: 1	No
encoding_format	enum	The format to return the embeddings in. Can be either float or base64. Possible values: float, base64	No
input	string or array of string or array of integer or array of array	Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8,192 tokens for all embedding models), cannot be an empty string, and any array must be 2,048 dimensions or less. Example Python code for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request.	Yes
model	string	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	Yes
user	string	Learn more.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.CreateEmbeddingResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/embeddings

Fine-tuning

Run grader

POST {endpoint}/openai/v1/fine_tuning/alpha/graders/run

Run a grader.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
grader	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderPython or OpenAI.GraderScoreModel or OpenAI.GraderMulti or GraderEndpoint	The grader used for the fine-tuning job.	Yes
item	OpenAI.RunGraderRequestItem		No
model_sample	string	The model sample to be evaluated. This value will be used to populate the sample namespace. See the guide for more details. The output_json variable will be populated if the model sample is a valid JSON string.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunGraderResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Validate grader

POST {endpoint}/openai/v1/fine_tuning/alpha/graders/validate

Validate a grader.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
grader	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderPython or OpenAI.GraderScoreModel or OpenAI.GraderMulti or GraderEndpoint		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ValidateGraderResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List fine tuning checkpoint permissions

GET {endpoint}/openai/v1/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions

List checkpoint permissions

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuned_model_checkpoint	path	Yes	string	The ID of the fine-tuned model checkpoint to get permissions for.
project_id	query	No	string	The ID of the project to get permissions for.
after	query	No	string	Identifier for the last permission ID from the previous pagination request.
limit	query	No	integer	Number of permissions to retrieve.
order	query	No	string Possible values: ascending, descending	The order in which to retrieve permissions.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListFineTuningCheckpointPermissionResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create fine tuning checkpoint permission

POST {endpoint}/openai/v1/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions

Create checkpoint permissions

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuned_model_checkpoint	path	Yes	string	The ID of the fine-tuned model checkpoint to create a permission for.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
project_ids	array of string	The project identifiers to grant access to.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListFineTuningCheckpointPermissionResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete fine tuning checkpoint permission

DELETE {endpoint}/openai/v1/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}

Delete checkpoint permission

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuned_model_checkpoint	path	Yes	string	The ID of the fine-tuned model checkpoint to delete a permission for.
permission_id	path	Yes	string	The ID of the fine-tuned model checkpoint permission to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteFineTuningCheckpointPermissionResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create fine tuning job

POST {endpoint}/openai/v1/fine_tuning/jobs

Creates a fine-tuning job which begins the process of creating a new model from a given dataset.

Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
hyperparameters	OpenAI.CreateFineTuningJobRequestHyperparameters		No
└─ batch_size	string or integer		No	auto
└─ learning_rate_multiplier	string or number		No
└─ n_epochs	string or integer		No	auto
integrations	array of OpenAI.CreateFineTuningJobRequestIntegrations or null	A list of integrations to enable for your fine-tuning job.	No
metadata	OpenAI.Metadata or null		No
method	OpenAI.FineTuneMethod	The method used for fine-tuning.	No
model	string (see valid models below)	The name of the model to fine-tune. You can select one of the supported models.	Yes
seed	integer or null	The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.	No
suffix	string or null	A string of up to 64 characters that will be added to your fine-tuned model name. For example, a suffix of “custom-model-name” would produce a model name like ft:gpt-4o-mini:openai:custom-model-name:7p4lURel.	No
training_file	string	The ID of an uploaded file that contains training data. See upload file for how to upload a file. Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose fine-tune. The contents of the file should differ depending on if the model uses the chat, completions format, or if the fine-tuning method uses the preference format. See the fine-tuning guide for more details.	Yes
validation_file	string or null	The ID of an uploaded file that contains validation data. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files. Your dataset must be formatted as a JSONL file. You must upload your file with the purpose fine-tune. See the fine-tuning guide for more details.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.FineTuningJob

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List paginated fine tuning jobs

GET {endpoint}/openai/v1/fine_tuning/jobs

List your organization’s fine-tuning jobs

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
after	query	No	string	Identifier for the last job from the previous pagination request.
limit	query	No	integer	Number of fine-tuning jobs to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListPaginatedFineTuningJobsResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve fine tuning job

GET {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}

Get info about a fine-tuning job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.FineTuningJob

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel fine tuning job

POST {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/cancel

Immediately cancel a fine-tune job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job to cancel.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.FineTuningJob

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List fine tuning job checkpoints

GET {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

List the checkpoints for a fine-tuning job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job to get checkpoints for.
after	query	No	string	Identifier for the last checkpoint ID from the previous pagination request.
limit	query	No	integer	Number of checkpoints to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListFineTuningJobCheckpointsResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Fine tuning - copy checkpoint

POST {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints/{fine_tuning_checkpoint_id}/copy

Creates a copy of a fine-tuning checkpoint at the given destination account and region.

NOTE: This Azure OpenAI API is in preview and subject to change.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string
fine_tuning_checkpoint_id	path	Yes	string

Request Header

Name	Required	Type	Description
aoai-copy-ft-checkpoints	True	string Possible values: preview	Enables access to checkpoint copy operations for models, an AOAI preview feature. This feature requires the ‘aoai-copy-ft-checkpoints’ header to be set to ‘preview’.
accept	True	string Possible values: application/json

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
destinationResourceId	string	The ID of the destination Resource to copy.	Yes
region	string	The region to copy the model to.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	CopyModelResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Fine tuning - get checkpoint

GET {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints/{fine_tuning_checkpoint_id}/copy

Gets the status of a fine-tuning checkpoint copy.

NOTE: This Azure OpenAI API is in preview and subject to change.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string
fine_tuning_checkpoint_id	path	Yes	string

Request Header

Name	Required	Type	Description
aoai-copy-ft-checkpoints	True	string Possible values: preview	Enables access to checkpoint copy operations for models, an AOAI preview feature. This feature requires the ‘aoai-copy-ft-checkpoints’ header to be set to ‘preview’.
accept	True	string Possible values: application/json

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	CopyModelResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List fine tuning events

GET {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/events

Get status updates for a fine-tuning job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job to get events for.
after	query	No	string	Identifier for the last event from the previous pagination request.
limit	query	No	integer	Number of events to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListFineTuningJobEventsResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Pause fine tuning job

POST {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/pause

Pause a fine-tune job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job to pause.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.FineTuningJob

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Resume fine tuning job

POST {endpoint}/openai/v1/fine_tuning/jobs/{fine_tuning_job_id}/resume

Resume a paused fine-tune job.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
fine_tuning_job_id	path	Yes	string	The ID of the fine-tuning job to resume.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.FineTuningJob

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Models

List models

GET {endpoint}/openai/v1/models

Lists the currently available models, and provides basic information about each one such as the owner and availability.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListModelsResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve model

GET {endpoint}/openai/v1/models/{model}

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
model	path	Yes	string	The ID of the model to use for this request.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.Model

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete model

DELETE {endpoint}/openai/v1/models/{model}

Deletes a model instance.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
model	path	Yes	string	The ID of the model to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteModelResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Realtime

Create real time call

POST {endpoint}/openai/v1/realtime/calls

Create a new Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: multipart/form-data

Name	Type	Description	Required	Default
sdp	string	WebRTC Session Description Protocol (SDP) offer generated by the caller.	Yes
session	OpenAI.RealtimeSessionCreateRequestGA	Realtime session object configuration.	No
└─ audio	OpenAI.RealtimeSessionCreateRequestGAAudio	Configuration for input and output audio.	No
└─ include	array of string	Additional fields to include in server outputs. item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.	No
└─ instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
└─ max_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
└─ model	string	The Realtime model used for this session.	No
└─ output_modalities	array of string	The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.	No	[‘audio’]
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ tool_choice	OpenAI.ToolChoiceOptions or OpenAI.ToolChoiceFunction or OpenAI.ToolChoiceMCP	How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.	No	auto
└─ tools	array of OpenAI.RealtimeFunctionTool or OpenAI.MCPTool	Tools available to the model.	No
└─ tracing	string or OpenAI.RealtimeSessionCreateRequestGATracing or null	"" Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No	auto
└─ truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
└─ type	enum	The type of session to create. Always realtime for the Realtime API. Possible values: realtime	Yes

Responses

Status Code: 201

Description: The request has succeeded and a new resource has been created as a result.

Content-Type	Type	Description
application/sdp	string

Response Headers:

Header	Type	Description
location	string	Relative URL containing the call ID for subsequent control requests.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Accept real time call

POST {endpoint}/openai/v1/realtime/calls/{call_id}/accept

Accept an incoming SIP call and configure the realtime session that will handle it.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
call_id	path	Yes	string	The identifier for the call provided in the realtime.call.incoming webhook.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
audio	OpenAI.RealtimeSessionCreateRequestGAAudio		No
└─ input	OpenAI.RealtimeSessionCreateRequestGAAudioInput		No
└─ output	OpenAI.RealtimeSessionCreateRequestGAAudioOutput		No
include	array of string	Additional fields to include in server outputs. item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.	No
instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
max_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
model	string	The Realtime model used for this session.	No
output_modalities	array of string	The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.	No	[‘audio’]
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
tool_choice	OpenAI.ToolChoiceOptions or OpenAI.ToolChoiceFunction or OpenAI.ToolChoiceMCP	How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.	No
tools	array of OpenAI.RealtimeFunctionTool or OpenAI.MCPTool	Tools available to the model.	No
tracing	string or OpenAI.RealtimeSessionCreateRequestGATracing or null	"" Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No
truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
type	enum	The type of session to create. Always realtime for the Realtime API. Possible values: realtime	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Hang up realtime call

POST {endpoint}/openai/v1/realtime/calls/{call_id}/hangup

End an active Realtime API call, whether it was initiated over SIP or WebRTC.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
call_id	path	Yes	string	The identifier for the call.

Responses

Status Code: 200

Description: The request has succeeded.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Refer real time call

POST {endpoint}/openai/v1/realtime/calls/{call_id}/refer

Transfer an active SIP call to a new destination using the SIP REFER verb.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
call_id	path	Yes	string	The identifier for the call provided in the realtime.call.incoming webhook.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
target_uri	string	URI that should appear in the SIP Refer-To header. Supports values like tel:[phone] or sip:agent\@example.com.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Reject real time call

POST {endpoint}/openai/v1/realtime/calls/{call_id}/reject

Decline an incoming SIP call by returning a SIP status code to the caller.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
call_id	path	Yes	string	The identifier for the call provided in the realtime.call.incoming webhook.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
status_code	integer	SIP response code to send back to the caller. Defaults to 603 (Decline) when omitted.	No

Responses

Status Code: 200

Description: The request has succeeded.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create real time client secret

POST {endpoint}/openai/v1/realtime/client_secrets

Create a Realtime client secret with an associated session configuration.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
expires_after	OpenAI.RealtimeCreateClientSecretRequestExpiresAfter		No
└─ anchor	enum	Possible values: created_at	No
└─ seconds	integer	Constraints: min: 10, max: 7200	No	600
session	OpenAI.RealtimeSessionCreateRequestUnion		No
└─ type	OpenAI.RealtimeSessionCreateRequestUnionType		Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RealtimeCreateClientSecretResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create real time session

POST {endpoint}/openai/v1/realtime/sessions

Create an ephemeral API token for use in client-side applications with the Realtime API.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
client_secret	OpenAI.RealtimeSessionCreateRequestClientSecret		Yes
└─ expires_at	integer		Yes
└─ value	string		Yes
input_audio_format	string	The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.	No
input_audio_transcription	OpenAI.RealtimeSessionCreateRequestInputAudioTranscription		No
└─ model	string		No
instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
max_response_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
modalities	array of string	The set of modalities the model can respond with. To disable audio, set this to [“text”].	No	[‘text’, ‘audio’]
output_audio_format	string	The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.	No
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
speed	number	The speed of the model’s spoken response. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. Constraints: min: 0.25, max: 1.5	No	1
temperature	number	Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.	No
tool_choice	string	How the model chooses tools. Options are auto, none, required, or specify a function.	No
tools	array of OpenAI.RealtimeSessionCreateRequestTools	Tools (functions) available to the model.	No
tracing	string or object	Configuration options for tracing. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No
truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
turn_detection	OpenAI.RealtimeSessionCreateRequestTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	string		No
type	enum	Possible values: realtime	Yes
voice	OpenAI.VoiceIdsShared		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RealtimeSessionCreateResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create real time transcription session

POST {endpoint}/openai/v1/realtime/transcription_sessions

Create an ephemeral API token for use in client-side applications with the Realtime API specifically for realtime transcriptions.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
include	array of string	The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs	No
input_audio_format	enum	The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24-kHz sample rate, single channel (mono), and little-endian byte order. Possible values: pcm16, g711_ulaw, g711_alaw	No
input_audio_noise_reduction	OpenAI.RealtimeTranscriptionSessionCreateRequestInputAudioNoiseReduction		No
└─ type	OpenAI.NoiseReductionType	Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.	No
input_audio_transcription	OpenAI.AudioTranscription		No
└─ language	string	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.	No
└─ model	string	The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.	No
└─ prompt	string	An optional text to guide the model’s style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example “expect words related to technology”.	No
turn_detection	OpenAI.RealtimeTranscriptionSessionCreateRequestTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	enum	Possible values: server_vad	No
type	enum	Possible values: transcription	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RealtimeTranscriptionSessionCreateResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Responses

Create response

POST {endpoint}/openai/v1/responses

Creates a model response.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
background	boolean or null		No
conversation	OpenAI.ConversationParam or null		No
include	array of OpenAI.IncludeEnum or null		No
input	OpenAI.InputParam	Text, image, or file inputs to the model, used to generate a response. Learn more: - Text inputs and outputs - Image inputs - File inputs - Conversation state - Function calling	No
instructions	string or null		No
max_output_tokens	integer or null		No
max_tool_calls	integer or null		No
metadata	OpenAI.Metadata or null		No
model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
parallel_tool_calls	boolean or null		No
previous_response_id	string or null		No
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
prompt_cache_retention	string or null		No
reasoning	OpenAI.Reasoning or null		No
safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
store	boolean or null		No
stream	boolean or null		No
stream_options	OpenAI.ResponseStreamOptions or null		No
temperature	number or null		No
text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
top_logprobs	integer or null		No
top_p	number or null		No
truncation	string or null		No
user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object
text/event-stream	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/responses

Get response

GET {endpoint}/openai/v1/responses/{response_id}

Retrieves a model response with the given ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
response_id	path	Yes	string
include[]	query	No	array	Additional fields to include in the response. See the include parameter for Response creation above for more information.
stream	query	No	boolean	If set to true, the model response data will be streamed to the client as it is generated using server-sent events.
starting_after	query	No	integer	The sequence number of the event after which to start streaming.
include_obfuscation	query	No	boolean	When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete response

DELETE {endpoint}/openai/v1/responses/{response_id}

Deletes a response by ID.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
response_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel response

POST {endpoint}/openai/v1/responses/{response_id}/cancel

Cancels a model response with the given ID. Only responses created with the background parameter set to true can be cancelled.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
response_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List input items

GET {endpoint}/openai/v1/responses/{response_id}/input_items

Returns a list of input items for a given response.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
response_id	path	Yes	string
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ResponseItemList

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Threads

Create thread

POST {endpoint}/openai/v1/threads

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
messages	array of OpenAI.CreateMessageRequest	A list of messages to start the thread with.	No
metadata	OpenAI.Metadata or null		No
tool_resources	OpenAI.CreateThreadRequestToolResources or null		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ThreadObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Createthread and run

POST {endpoint}/openai/v1/threads/runs

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
assistant_id	string	The ID of the assistant to use to execute this run.	Yes
instructions	string or null	Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.	No
max_completion_tokens	integer or null	The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
max_prompt_tokens	integer or null	The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
metadata	OpenAI.Metadata or null		No
model	string	The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.	No
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	No
response_format	OpenAI.AssistantsApiResponseFormatOption	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.	No
stream	boolean or null	If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.	No
temperature	number or null	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.	No
thread	OpenAI.CreateThreadRequest	Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.	No
tool_choice	OpenAI.AssistantsApiToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.	No
tool_resources	OpenAI.CreateThreadAndRunRequestToolResources or null	A set of resources that are used by the assistant’s tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.	No
tools	array of OpenAI.AssistantTool	Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.	No
top_p	number or null	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
truncation_strategy	OpenAI.TruncationObject	Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete thread

DELETE {endpoint}/openai/v1/threads/{thread_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteThreadResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve thread

GET {endpoint}/openai/v1/threads/{thread_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ThreadObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Modify thread

POST {endpoint}/openai/v1/threads/{thread_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No
tool_resources	OpenAI.ModifyThreadRequestToolResources or null		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ThreadObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List messages

GET {endpoint}/openai/v1/threads/{thread_id}/messages

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
limit	query	No	integer
order	query	No	string Possible values: asc, desc
after	query	No	string
before	query	No	string
run_id	query	No	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListMessagesResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create message

POST {endpoint}/openai/v1/threads/{thread_id}/messages

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
attachments	array of OpenAI.CreateMessageRequestAttachments or null		No
content	string or array of OpenAI.MessageContentImageFileObject or OpenAI.MessageContentImageUrlObject or OpenAI.MessageRequestContentTextObject		Yes
metadata	OpenAI.Metadata or null		No
role	enum	The role of the entity that is creating the message. Allowed values include: - user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. - assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. Possible values: user, assistant	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.MessageObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete message

DELETE {endpoint}/openai/v1/threads/{thread_id}/messages/{message_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
message_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteMessageResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve message

GET {endpoint}/openai/v1/threads/{thread_id}/messages/{message_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
message_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.MessageObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Modify message

POST {endpoint}/openai/v1/threads/{thread_id}/messages/{message_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
message_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.MessageObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create run

POST {endpoint}/openai/v1/threads/{thread_id}/runs

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
additional_instructions	string or null	Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.	No
additional_messages	array of OpenAI.CreateMessageRequest or null	Adds additional messages to the thread before creating the run.	No
assistant_id	string	The ID of the assistant to use to execute this run.	Yes
instructions	string or null	Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.	No
max_completion_tokens	integer or null	The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
max_prompt_tokens	integer or null	The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
metadata	OpenAI.Metadata or null		No
model	string	The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.	No
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
response_format	OpenAI.AssistantsApiResponseFormatOption	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.	No
stream	boolean or null	If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.	No
temperature	number or null	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.	No
tool_choice	OpenAI.AssistantsApiToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.	No
tools	array of OpenAI.AssistantTool	Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.	No
top_p	number or null	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
truncation_strategy	OpenAI.TruncationObject	Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List runs

GET {endpoint}/openai/v1/threads/{thread_id}/runs

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
limit	query	No	integer
order	query	No	string Possible values: asc, desc
after	query	No	string
before	query	No	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListRunsResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve run

GET {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Modify run

POST {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel run

POST {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}/cancel

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List run steps

GET {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}/steps

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string
limit	query	No	integer
order	query	No	string Possible values: asc, desc
after	query	No	string
before	query	No	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListRunStepsResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get run step

GET {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}/steps/{step_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string
step_id	path	Yes	string

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunStepObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Submit tool outputs to run

POST {endpoint}/openai/v1/threads/{thread_id}/runs/{run_id}/submit_tool_outputs

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
thread_id	path	Yes	string
run_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
stream	boolean or null		No
tool_outputs	array of OpenAI.SubmitToolOutputsRunRequestToolOutputs	A list of tools for which the outputs are being submitted.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.RunObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Vector Stores

List vector stores

GET {endpoint}/openai/v1/vector_stores

Returns a list of vector stores.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListVectorStoresResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create vector store

POST {endpoint}/openai/v1/vector_stores

Creates a vector store.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
description	string	A description for the vector store. Can be used to describe the vector store’s purpose.	No
expires_after	OpenAI.VectorStoreExpirationAfter	The expiration policy for a vector store.	No
file_ids	array of string	A list of File IDs that the vector store should use. Useful for tools like file_search that can access files.	No
metadata	OpenAI.Metadata or null		No
name	string	The name of the vector store.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Examples

Example

POST {endpoint}/openai/v1/vector_stores

Get vector store

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}

Retrieves a vector store.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store to retrieve.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Modify vector store

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}

Modifies a vector store.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store to modify.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
expires_after	OpenAI.VectorStoreExpirationAfter	The expiration policy for a vector store.	No
metadata	OpenAI.Metadata or null		No
name	string or null	The name of the vector store.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete vector store

DELETE {endpoint}/openai/v1/vector_stores/{vector_store_id}

Delete a vector store.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteVectorStoreResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create vector store file batch

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}/file_batches

Create a vector store file batch.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store for which to create a file batch.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
file_ids	array of string	A list of File IDs that the vector store should use. Useful for tools like file_search that can access files. If attributes or chunking_strategy are provided, they will be applied to all files in the batch. Mutually exclusive with files.	No
files	array of OpenAI.CreateVectorStoreFileRequest	A list of objects that each include a file_id plus optional attributes or chunking_strategy. Use this when you need to override metadata for specific files. The global attributes or chunking_strategy will be ignored and must be specified for each file. Mutually exclusive with file_ids.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileBatchObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get vector store file batch

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}

Retrieves a vector store file batch.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the file batch belongs to.
batch_id	path	Yes	string	The ID of the file batch being retrieved.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileBatchObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Cancel vector store file batch

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel

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

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the file batch belongs to.
batch_id	path	Yes	string	The ID of the file batch to cancel.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileBatchObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List files in vector store batch

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files

Returns a list of vector store files in a batch.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the file batch belongs to.
batch_id	path	Yes	string	The ID of the file batch that the files belong to.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.
filter	query	No	string Possible values: in_progress, completed, failed, cancelled	Filter by file status. One of in_progress, completed, failed, cancelled.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListVectorStoreFilesResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

List vector store files

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}/files

Returns a list of vector store files.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the files belong to.
limit	query	No	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
order	query	No	string Possible values: asc, desc	Sort order by the created_at timestamp of the objects. asc for ascending order anddesc for descending order.
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.
before	query	No	string	A cursor for use in pagination. before 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 before=obj_foo in order to fetch the previous page of the list.
filter	query	No	string Possible values: in_progress, completed, failed, cancelled	Filter by file status. One of in_progress, completed, failed, cancelled.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.ListVectorStoreFilesResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Create vector store file

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}/files

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

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store for which to create a File.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
file_id	string	A File ID that the vector store should use. Useful for tools like file_search that can access files.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Get vector store file

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}/files/{file_id}

Retrieves a vector store file.

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the file belongs to.
file_id	path	Yes	string	The ID of the file being retrieved.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Update vector store file attributes

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}/files/{file_id}

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string
file_id	path	Yes	string

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreFileObject

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Delete vector store file

DELETE {endpoint}/openai/v1/vector_stores/{vector_store_id}/files/{file_id}

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

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store that the file belongs to.
file_id	path	Yes	string	The ID of the file to delete.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.DeleteVectorStoreFileResponse

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Retrieve vector store file content

GET {endpoint}/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content

Retrieve vector store file content

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store to search.
file_id	path	Yes	string	The ID of the file to retrieve content for.

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreSearchResultsPage

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Search vector store

POST {endpoint}/openai/v1/vector_stores/{vector_store_id}/search

Search vector store

URI Parameters

Name	In	Required	Type	Description
endpoint	path	Yes	string	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	No	string	The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.
vector_store_id	path	Yes	string	The ID of the vector store to search.

Request Body

Content-Type: application/json

Name	Type	Description	Required	Default
filters	OpenAI.ComparisonFilter or OpenAI.CompoundFilter	A filter to apply based on file attributes.	No
max_num_results	integer	The maximum number of results to return. This number should be between 1 and 50 inclusive. Constraints: min: 1, max: 50	No	10
query	string or array of string	A query string for a search	Yes
ranking_options	OpenAI.VectorStoreSearchRequestRankingOptions		No
└─ ranker	enum	Possible values: none, auto, default-2024-11-15	No
└─ score_threshold	number	Constraints: min: 0, max: 1	No
rewrite_query	boolean	Whether to rewrite the natural language query for vector search.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	OpenAI.VectorStoreSearchResultsPage

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	object

Response Headers:

Header	Type	Description
apim-request-id	string	A request ID used for troubleshooting purposes.

Components

AudioSegment

Name	Type	Description	Required	Default
avg_logprob	number	The average log probability associated with this audio segment.	Yes
compression_ratio	number	The compression ratio of this audio segment.	Yes
end	number	The time at which this segment ended relative to the beginning of the translated audio.	Yes
id	integer	The 0-based index of this segment within a translation.	Yes
no_speech_prob	number	The probability of no speech detection within this audio segment.	Yes
seek	integer	The seek position associated with the processing of this audio segment. Seek positions are expressed as hundredths of seconds. The model may process several segments from a single seek position, so while the seek position will never represent a later time than the segment’s start, the segment’s start may represent a significantly later time than the segment’s associated seek position.	Yes
start	number	The time at which this segment started relative to the beginning of the translated audio.	Yes
temperature	number	The temperature score associated with this audio segment.	Yes
text	string	The translated text that was part of this audio segment.	Yes
tokens	array of integer	The token IDs matching the translated text in this audio segment.	Yes

AudioTaskLabel

Defines the possible descriptors for available audio operation responses.

Property	Value
Description	Defines the possible descriptors for available audio operation responses.
Type	string
Values	transcribe translate

AudioTranslationSegment

Extended information about a single segment of translated audio data. Segments generally represent roughly 5-10 seconds of speech. Segment boundaries typically occur between words but not necessarily sentences.

Name	Type	Description	Required	Default
avg_logprob	number	The average log probability associated with this audio segment.	Yes
compression_ratio	number	The compression ratio of this audio segment.	Yes
end	number	The time at which this segment ended relative to the beginning of the translated audio.	Yes
id	integer	The 0-based index of this segment within a translation.	Yes
no_speech_prob	number	The probability of no speech detection within this audio segment.	Yes
seek	integer	The seek position associated with the processing of this audio segment. Seek positions are expressed as hundredths of seconds. The model may process several segments from a single seek position, so while the seek position will never represent a later time than the segment’s start, the segment’s start may represent a significantly later time than the segment’s associated seek position.	Yes
start	number	The time at which this segment started relative to the beginning of the translated audio.	Yes
temperature	number	The temperature score associated with this audio segment.	Yes
text	string	The translated text that was part of this audio segment.	Yes
tokens	array of integer	The token IDs matching the translated text in this audio segment.	Yes

AzureAIFoundryModelsApiVersion

Property	Value
Type	string
Values	v1 preview

AzureAudioTranscriptionResponse

Result information for an operation that transcribed spoken audio into written text.

Name	Type	Description	Required	Default
duration	number	The total duration of the audio processed to produce accompanying transcription information.	No
language	string	The spoken language that was detected in the transcribed audio data. This is expressed as a two-letter ISO-639-1 language code like ‘en’ or ‘fr’.	No
segments	array of OpenAI.TranscriptionSegment	A collection of information about the timing, probabilities, and other detail of each processed audio segment.	No
task	AudioTaskLabel	Defines the possible descriptors for available audio operation responses.	No
text	string	The transcribed text for the provided audio data.	Yes
words	array of OpenAI.TranscriptionWord	A collection of information about the timing of each processed word.	No

AzureAudioTranslationResponse

Result information for an operation that translated spoken audio into written text.

Name	Type	Description	Required	Default
duration	number	The total duration of the audio processed to produce accompanying translation information.	No
language	string	The spoken language that was detected in the translated audio data. This is expressed as a two-letter ISO-639-1 language code like ‘en’ or ‘fr’.	No
segments	array of AudioTranslationSegment	A collection of information about the timing, probabilities, and other detail of each processed audio segment.	No
task	AudioTaskLabel	Defines the possible descriptors for available audio operation responses.	No
text	string	The translated text for the provided audio data.	Yes

AzureCompletionsSamplingParams

Sampling parameters for controlling the behavior of completions.

Name	Type	Description	Required	Default
max_completion_tokens	integer		No
max_tokens	integer	The maximum number of tokens in the generated output.	No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
response_format	OpenAI.ResponseFormatText or OpenAI.ResponseFormatJsonSchema or OpenAI.ResponseFormatJsonObject		No
seed	integer	A seed value initializes the randomness during sampling.	No	42
temperature	number	A higher temperature increases randomness in the outputs.	No	1
tools	array of OpenAI.ChatCompletionTool		No
top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1

AzureContentFilterBlocklistIdResult

A content filter result item that associates an existing custom blocklist ID with a value indicating whether or not the corresponding blocklist resulted in content being filtered.

Name	Type	Description	Required	Default
filtered	boolean	Whether the associated blocklist resulted in the content being filtered.	Yes
id	string	The ID of the custom blocklist associated with the filtered status.	Yes

AzureContentFilterBlocklistResult

A collection of true/false filtering results for configured custom blocklists.

Name	Type	Description	Required	Default
details	array of object	The pairs of individual blocklist IDs and whether they resulted in a filtering action.	No
filtered	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.	Yes

AzureContentFilterCompletionTextSpan

A representation of a span of completion text as used by Azure OpenAI content filter results.

Name	Type	Description	Required	Default
completion_end_offset	integer	Offset of the first UTF32 code point which is excluded from the span. This field is always equal to completion_start_offset for empty spans. This field is always larger than completion_start_offset for non-empty spans.	Yes
completion_start_offset	integer	Offset of the UTF32 code point which begins the span.	Yes

AzureContentFilterCompletionTextSpanDetectionResult

Name	Type	Description	Required	Default
details	array of AzureContentFilterCompletionTextSpan	Detailed information about the detected completion text spans.	Yes
detected	boolean	Whether the labeled content category was detected in the content.	Yes
filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes

AzureContentFilterCustomTopicIdResult

A content filter result item that associates an existing custom topic ID with a value indicating whether or not the corresponding topic resulted in content being detected.

Name	Type	Description	Required	Default
detected	boolean	Whether the associated custom topic resulted in the content being detected.	Yes
id	string	The ID of the custom topic associated with the detected status.	Yes

AzureContentFilterCustomTopicResult

A collection of true/false filtering results for configured custom topics.

Name	Type	Description	Required	Default
details	array of object	The pairs of individual topic IDs and whether they are detected.	No
filtered	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.	Yes

AzureContentFilterDetectionResult

A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.

Name	Type	Description	Required	Default
detected	boolean	Whether the labeled content category was detected in the content.	Yes
filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes

AzureContentFilterForResponsesAPI

Name	Type	Description	Required	Default
blocked	boolean	Indicate if the response is blocked.	Yes
content_filter_offsets	AzureContentFilterResultOffsets		Yes
content_filter_results	AzureContentFilterResultsForResponsesAPI		Yes
└─ custom_blocklists	AzureContentFilterBlocklistResult	A collection of binary filtering outcomes for configured custom blocklists.	No
└─ custom_topics	AzureContentFilterCustomTopicResult	A collection of binary filtering outcomes for configured custom topics.	No
└─ error	object	If present, details about an error that prevented content filtering from completing its evaluation.	No
└─ code	integer	A distinct, machine-readable code associated with the error.	Yes
└─ message	string	A human-readable message associated with the error.	Yes
└─ hate	AzureContentFilterSeverityResult	A content filter category that can refer to any content that attacks or uses pejorative or discriminatory language with reference to a person or identity group based on certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size.	No
└─ indirect_attack	AzureContentFilterDetectionResult	A detection result that describes attacks on systems powered by Generative AI models that can happen every time an application processes information that wasn’t directly authored by either the developer of the application or the user.	No
└─ jailbreak	AzureContentFilterDetectionResult	A detection result that describes user prompt injection attacks, where malicious users deliberately exploit system vulnerabilities to elicit unauthorized behavior from the LLM. This could lead to inappropriate content generation or violations of system-imposed restrictions.	Yes
└─ personally_identifiable_information	AzureContentFilterPersonallyIdentifiableInformationResult	A detection result that describes matches against Personal Identifiable Information with configurable subcategories.	No
└─ profanity	AzureContentFilterDetectionResult	A detection result that identifies whether crude, vulgar, or otherwise objection language is present in the content.	No
└─ protected_material_code	object	A detection result that describes a match against licensed code or other protected source material.	No
└─ citation	object	If available, the citation details describing the associated license and its location.	No
└─ URL	string	The URL associated with the license.	No
└─ license	string	The name or identifier of the license associated with the detection.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
└─ protected_material_text	AzureContentFilterDetectionResult	A detection result that describes a match against text protected under copyright or other status.	No
└─ self_harm	AzureContentFilterSeverityResult	A content filter category that describes language related to physical actions intended to purposely hurt, injure, damage one’s body or kill oneself.	No
└─ sexual	AzureContentFilterSeverityResult	A content filter category for language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, pregnancy, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one’s will, prostitution, pornography, and abuse.	No
└─ task_adherence	AzureContentFilterDetectionResult	A detection result that indicates if the execution flow still sticks the plan.	Yes
└─ ungrounded_material	AzureContentFilterCompletionTextSpanDetectionResult		No
└─ violence	AzureContentFilterSeverityResult	A content filter category for language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, guns and related entities, such as manufactures, associations, legislation, and so on.	No
source_type	string	The name of the source type of the message.	Yes

AzureContentFilterHarmExtensions

Extensions for harm categories, providing additional configuration options.

Name	Type	Description	Required	Default
pii_sub_categories	array of AzurePiiSubCategory	Configuration for PIIHarmSubCategory(s).	No

AzureContentFilterImagePromptResults

A content filter result for an image generation operation’s input request content.

Name	Type	Description	Required	Default
custom_blocklists	AzureContentFilterBlocklistResult	A collection of true/false filtering results for configured custom blocklists.	No
└─ details	array of object	The pairs of individual blocklist IDs and whether they resulted in a filtering action.	No
└─ filtered	boolean	A value indicating whether the blocklist produced a filtering action.	Yes
└─ id	string	The ID of the custom blocklist evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.	Yes
custom_topics	AzureContentFilterCustomTopicResult	A collection of true/false filtering results for configured custom topics.	No
└─ details	array of object	The pairs of individual topic IDs and whether they are detected.	No
└─ detected	boolean	A value indicating whether the topic is detected.	Yes
└─ id	string	The ID of the custom topic evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.	Yes
hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
jailbreak	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	Yes
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
profanity	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes

AzureContentFilterImageResponseResults

A content filter result for an image generation operation’s output response content.

Name	Type	Description	Required	Default
hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes

AzureContentFilterPersonallyIdentifiableInformationResult

A content filter detection result for Personally Identifiable Information that includes harm extensions.

Name	Type	Description	Required	Default
detected	boolean	Whether the labeled content category was detected in the content.	Yes
filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
redacted_text	string	The redacted text with PII information removed or masked.	No
sub_categories	array of AzurePiiSubCategoryResult	Detailed results for individual PIIHarmSubCategory(s).	No

AzureContentFilterResultForChoice

A content filter result for a single response item produced by a generative AI system.

Name	Type	Description	Required	Default
custom_blocklists	AzureContentFilterBlocklistResult	A collection of true/false filtering results for configured custom blocklists.	No
└─ details	array of object	The pairs of individual blocklist IDs and whether they resulted in a filtering action.	No
└─ filtered	boolean	A value indicating whether the blocklist produced a filtering action.	Yes
└─ id	string	The ID of the custom blocklist evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.	Yes
custom_topics	AzureContentFilterCustomTopicResult	A collection of true/false filtering results for configured custom topics.	No
└─ details	array of object	The pairs of individual topic IDs and whether they are detected.	No
└─ detected	boolean	A value indicating whether the topic is detected.	Yes
└─ id	string	The ID of the custom topic evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.	Yes
error	object	If present, details about an error that prevented content filtering from completing its evaluation.	No
└─ code	integer	A distinct, machine-readable code associated with the error.	Yes
└─ message	string	A human-readable message associated with the error.	Yes
hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
personally_identifiable_information	AzureContentFilterPersonallyIdentifiableInformationResult	A content filter detection result for Personally Identifiable Information that includes harm extensions.	No
└─ redacted_text	string	The redacted text with PII information removed or masked.	No
└─ sub_categories	array of AzurePiiSubCategoryResult	Detailed results for individual PIIHarmSubCategory(s).	No
profanity	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
protected_material_code	object	A detection result that describes a match against licensed code or other protected source material.	No
└─ citation	object	If available, the citation details describing the associated license and its location.	No
└─ URL	string	The URL associated with the license.	No
└─ license	string	The name or identifier of the license associated with the detection.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
protected_material_text	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
ungrounded_material	AzureContentFilterCompletionTextSpanDetectionResult		No
violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes

AzureContentFilterResultForPrompt

A content filter result associated with a single input prompt item into a generative AI system.

Name	Type	Description	Required	Default
content_filter_results	object	The content filter category details for the result.	No
└─ custom_blocklists	AzureContentFilterBlocklistResult	A collection of true/false filtering results for configured custom blocklists.	No
└─ details	array of object	The pairs of individual blocklist IDs and whether they resulted in a filtering action.	No
└─ filtered	boolean	A value indicating whether the blocklist produced a filtering action.	Yes
└─ id	string	The ID of the custom blocklist evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.	Yes
└─ custom_topics	AzureContentFilterCustomTopicResult	A collection of true/false filtering results for configured custom topics.	No
└─ details	array of object	The pairs of individual topic IDs and whether they are detected.	No
└─ detected	boolean	A value indicating whether the topic is detected.	Yes
└─ id	string	The ID of the custom topic evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.	Yes
└─ error	object	If present, details about an error that prevented content filtering from completing its evaluation.	No
└─ code	integer	A distinct, machine-readable code associated with the error.	Yes
└─ message	string	A human-readable message associated with the error.	Yes
└─ hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
└─ indirect_attack	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	Yes
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
└─ jailbreak	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	Yes
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
└─ profanity	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
└─ self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
└─ sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
└─ violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
prompt_index	integer	The index of the input prompt associated with the accompanying content filter result categories.	No

AzureContentFilterResultOffsets

Name	Type	Description	Required	Default
check_offset	integer		Yes
end_offset	integer		Yes
start_offset	integer		Yes

AzureContentFilterResultsForResponsesAPI

Name	Type	Description	Required	Default
custom_blocklists	AzureContentFilterBlocklistResult	A collection of true/false filtering results for configured custom blocklists.	No
└─ details	array of object	The pairs of individual blocklist IDs and whether they resulted in a filtering action.	No
└─ filtered	boolean	A value indicating whether the blocklist produced a filtering action.	Yes
└─ id	string	The ID of the custom blocklist evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed blocklists resulted in a filtering action.	Yes
custom_topics	AzureContentFilterCustomTopicResult	A collection of true/false filtering results for configured custom topics.	No
└─ details	array of object	The pairs of individual topic IDs and whether they are detected.	No
└─ detected	boolean	A value indicating whether the topic is detected.	Yes
└─ id	string	The ID of the custom topic evaluated.	Yes
└─ filtered	boolean	A value indicating whether any of the detailed topics resulted in a filtering action.	Yes
error	object	If present, details about an error that prevented content filtering from completing its evaluation.	No
└─ code	integer	A distinct, machine-readable code associated with the error.	Yes
└─ message	string	A human-readable message associated with the error.	Yes
hate	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
indirect_attack	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
jailbreak	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	Yes
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
personally_identifiable_information	AzureContentFilterPersonallyIdentifiableInformationResult	A content filter detection result for Personally Identifiable Information that includes harm extensions.	No
└─ redacted_text	string	The redacted text with PII information removed or masked.	No
└─ sub_categories	array of AzurePiiSubCategoryResult	Detailed results for individual PIIHarmSubCategory(s).	No
profanity	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
protected_material_code	object	A detection result that describes a match against licensed code or other protected source material.	No
└─ citation	object	If available, the citation details describing the associated license and its location.	No
└─ URL	string	The URL associated with the license.	No
└─ license	string	The name or identifier of the license associated with the detection.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
protected_material_text	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	No
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
self_harm	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
sexual	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes
task_adherence	AzureContentFilterDetectionResult	A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.	Yes
└─ detected	boolean	Whether the labeled content category was detected in the content.	Yes
└─ filtered	boolean	Whether the content detection resulted in a content filtering action.	Yes
ungrounded_material	AzureContentFilterCompletionTextSpanDetectionResult		No
violence	AzureContentFilterSeverityResult	A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.	No
└─ filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
└─ severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes

AzureContentFilterSeverityResult

A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.

Name	Type	Description	Required	Default
filtered	boolean	Whether the content severity resulted in a content filtering action.	Yes
severity	enum	The labeled severity of the content. Possible values: safe, low, medium, high	Yes

AzureFileExpiryAnchor

Property	Value
Type	string
Values	created_at

AzureFineTuneReinforcementMethod

Name	Type	Description	Required	Default
grader	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderScoreModel or OpenAI.GraderMulti or GraderEndpoint		Yes
hyperparameters	OpenAI.FineTuneReinforcementHyperparameters	The hyperparameters used for the reinforcement fine-tuning job.	No
response_format	ResponseFormatJSONSchemaRequest		No
└─ json_schema	object	JSON Schema for the response format	Yes
└─ type	enum	Type of response format Possible values: json_schema	Yes

AzurePiiSubCategory

Configuration for individual PIIHarmSubCategory(s) within the harm extensions framework.

Name	Type	Description	Required	Default
detect	boolean	Whether detection is enabled for this subcategory.	Yes
filter	boolean	Whether content containing this subcategory should be blocked.	Yes
redact	boolean	Whether content containing this subcategory should be redacted.	Yes
sub_category	string	The PIIHarmSubCategory being configured.	Yes

AzurePiiSubCategoryResult

Result details for individual PIIHarmSubCategory(s).

Name	Type	Description	Required	Default
detected	boolean	Whether the labeled content subcategory was detected in the content.	Yes
filtered	boolean	Whether the content detection resulted in a content filtering action for this subcategory.	Yes
redacted	boolean	Whether the content was redacted for this subcategory.	Yes
sub_category	string	The PIIHarmSubCategory that was evaluated.	Yes

AzureResponsesSamplingParams

Sampling parameters for controlling the behavior of responses.

Name	Type	Description	Required	Default
max_tokens	integer	The maximum number of tokens in the generated output.	No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
seed	integer	A seed value initializes the randomness during sampling.	No	42
temperature	number	A higher temperature increases randomness in the outputs.	No	1
text	OpenAI.CreateEvalResponsesRunDataSourceSamplingParamsText		No
tools	array of OpenAI.Tool		No
top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1

AzureUserSecurityContext

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

Name	Type	Description	Required	Default
application_name	string	The name of the application. Sensitive personal information should not be included in this field.	No
end_user_id	string	This identifier is the Microsoft Entra ID (formerly Azure Active Directory) user object ID used to authenticate end-users within the generative AI application. Sensitive personal information should not be included in this field.	No
end_user_tenant_id	string	The Microsoft 365 tenant ID the end user belongs to. It’s required when the generative AI application is multitenant.	No
source_ip	string	Captures the original client’s IP address.	No

CopiedAccountDetails

Name	Type	Description	Required	Default
destinationResourceId	string	The ID of the destination resource where the model was copied to.	Yes
region	string	The region where the model was copied to.	Yes
status	enum	The status of the copy operation. Possible values: Completed, Failed, InProgress	Yes

CopyModelRequest

Name	Type	Description	Required	Default
destinationResourceId	string	The ID of the destination Resource to copy.	Yes
region	string	The region to copy the model to.	Yes

CopyModelResponse

Name	Type	Description	Required	Default
checkpointedModelName	string	The ID of the copied model.	Yes
copiedAccountDetails	array of CopiedAccountDetails	The ID of the destination resource id where it was copied	Yes
fineTuningJobId	string	The ID of the fine-tuning job that the checkpoint was copied from.	Yes

CreateVideoBody

Name	Type	Description	Required	Default
model	string	The name of the deployment to use for this request.	Yes
prompt	string	Text prompt that describes the video to generate. Constraints: minLength: 1	Yes
seconds	VideoSeconds	Supported clip durations, measured in seconds.	No	4
size	VideoSize	Output dimensions formatted as {width}x{height}.	No	720x1280

CreateVideoBodyWithInputReference

The properties of a video generation job request with media files.

Name	Type	Description	Required	Default
input_reference	object	Optional image reference that guides generation.	Yes
model	object	The name of the deployment to use for this request.	Yes
prompt	object	Text prompt that describes the video to generate.	Yes
seconds	object	Clip duration in seconds. Defaults to 4 seconds.	No
size	object	Output resolution formatted as width x height. Defaults to 720x1280.	No

CreateVideoRemixBody

Parameters for remixing an existing generated video.

Name	Type	Description	Required	Default
prompt	string	Updated text prompt that directs the remix generation. Constraints: minLength: 1	Yes

DeletedVideoResource

Confirmation payload returned after deleting a video.

Name	Type	Description	Required	Default
deleted	boolean	Indicates that the video resource was deleted.	Yes	True
id	string	Identifier of the deleted video.	Yes
object	string	The object type that signals the deletion response.	Yes	video.deleted

Error

Name	Type	Description	Required	Default
code	string		Yes
message	string		Yes

EvalGraderEndpoint

Name	Type	Description	Required	Default
headers	object or null	Optional HTTP headers to include in requests to the endpoint	No
name	string	The name of the grader	Yes
pass_threshold	number or null	Optional threshold score above which the grade is considered passing If not specified, all scores are considered valid	No
rate_limit	integer or null	Optional rate limit for requests per second to the endpoint Must be a positive integer	No
type	enum	Possible values: endpoint	Yes
url	string	The HTTPS URL of the endpoint to call for grading Constraints: pattern: ^https://	Yes

GraderEndpoint

Endpoint grader configuration for external HTTP endpoint evaluation

Name	Type	Description	Required	Default
headers	object or null	Optional HTTP headers to include in requests to the endpoint	No
name	string	The name of the grader	Yes
pass_threshold	number or null	Optional threshold score above which the grade is considered passing If not specified, all scores are considered valid	No
rate_limit	integer or null	Optional rate limit for requests per second to the endpoint Must be a positive integer	No
type	enum	Possible values: endpoint	Yes
url	string	The HTTPS URL of the endpoint to call for grading Constraints: pattern: ^https://	Yes

OpenAI.Annotation

An annotation that applies to a span of output text.

Discriminator for OpenAI.Annotation

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

Type Value	Schema
file_citation	OpenAI.FileCitationBody
url_citation	OpenAI.UrlCitationBody
container_file_citation	OpenAI.ContainerFileCitationBody
file_path	OpenAI.FilePath

Name	Type	Description	Required	Default
type	OpenAI.AnnotationType		Yes

OpenAI.AnnotationType

Property	Value
Type	string
Values	file_citation url_citation container_file_citation file_path

OpenAI.ApplyPatchCallOutputStatus

Property	Value
Type	string
Values	completed failed

OpenAI.ApplyPatchCallStatus

Property	Value
Type	string
Values	in_progress completed

OpenAI.ApplyPatchCreateFileOperation

Instruction describing how to create a file via the apply_patch tool.

Name	Type	Description	Required	Default
diff	string	Diff to apply.	Yes
path	string	Path of the file to create.	Yes
type	enum	Create a new file with the provided diff. Possible values: create_file	Yes

OpenAI.ApplyPatchDeleteFileOperation

Instruction describing how to delete a file via the apply_patch tool.

Name	Type	Description	Required	Default
path	string	Path of the file to delete.	Yes
type	enum	Delete the specified file. Possible values: delete_file	Yes

OpenAI.ApplyPatchFileOperation

One of the create_file, delete_file, or update_file operations applied via apply_patch.

Discriminator for OpenAI.ApplyPatchFileOperation

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

Type Value	Schema
create_file	OpenAI.ApplyPatchCreateFileOperation
delete_file	OpenAI.ApplyPatchDeleteFileOperation
update_file	OpenAI.ApplyPatchUpdateFileOperation

Name	Type	Description	Required	Default
type	OpenAI.ApplyPatchFileOperationType		Yes

OpenAI.ApplyPatchFileOperationType

Property	Value
Type	string
Values	create_file delete_file update_file

OpenAI.ApplyPatchToolParam

Allows the assistant to create, delete, or update files using unified diffs.

Name	Type	Description	Required	Default
type	enum	The type of the tool. Always apply_patch. Possible values: apply_patch	Yes

OpenAI.ApplyPatchUpdateFileOperation

Instruction describing how to update a file via the apply_patch tool.

Name	Type	Description	Required	Default
diff	string	Diff to apply.	Yes
path	string	Path of the file to update.	Yes
type	enum	Update an existing file with the provided diff. Possible values: update_file	Yes

OpenAI.ApproximateLocation

Name	Type	Description	Required	Default
city	string or null		No
country	string or null		No
region	string or null		No
timezone	string or null		No
type	enum	The type of location approximation. Always approximate. Possible values: approximate	Yes

OpenAI.AssistantTool

Discriminator for OpenAI.AssistantTool

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

Type Value	Schema
code_interpreter	OpenAI.AssistantToolsCode
file_search	OpenAI.AssistantToolsFileSearch
function	OpenAI.AssistantToolsFunction

Name	Type	Description	Required	Default
type	OpenAI.AssistantToolType		Yes

OpenAI.AssistantToolType

Property	Value
Type	string
Values	code_interpreter file_search function

OpenAI.AssistantToolsCode

Name	Type	Description	Required	Default
type	enum	The type of tool being defined: code_interpreter Possible values: code_interpreter	Yes

OpenAI.AssistantToolsFileSearch

Name	Type	Description	Required	Default
file_search	OpenAI.AssistantToolsFileSearchFileSearch		No
└─ max_num_results	integer	Constraints: min: 1, max: 50	No
└─ ranking_options	OpenAI.FileSearchRankingOptions	The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0. See the file search tool documentation for more information.	No
type	enum	The type of tool being defined: file_search Possible values: file_search	Yes

OpenAI.AssistantToolsFileSearchFileSearch

Name	Type	Description	Required	Default
max_num_results	integer	Constraints: min: 1, max: 50	No
ranking_options	OpenAI.FileSearchRankingOptions	The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0. See the file search tool documentation for more information.	No

OpenAI.AssistantToolsFileSearchTypeOnly

Name	Type	Description	Required	Default
type	enum	The type of tool being defined: file_search Possible values: file_search	Yes

OpenAI.AssistantToolsFunction

Name	Type	Description	Required	Default
function	OpenAI.FunctionObject		Yes
type	enum	The type of tool being defined: function Possible values: function	Yes

OpenAI.AssistantsApiResponseFormatOption

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

Type: string or OpenAI.ResponseFormatText or OpenAI.ResponseFormatJsonObject or OpenAI.ResponseFormatJsonSchema

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

OpenAI.AssistantsApiToolChoiceOption

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

Type: string or OpenAI.AssistantsNamedToolChoice

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

OpenAI.AssistantsNamedToolChoice

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

Name	Type	Description	Required	Default
function	OpenAI.AssistantsNamedToolChoiceFunction		No
type	enum	The type of the tool. If type is function, the function name must be set Possible values: function, code_interpreter, file_search	Yes

OpenAI.AssistantsNamedToolChoiceFunction

Name	Type	Description	Required	Default
name	string		Yes

OpenAI.AudioTranscription

Name	Type	Description	Required	Default
language	string	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.	No
model	string	The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.	No
prompt	string	An optional text to guide the model’s style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example “expect words related to technology”.	No

OpenAI.AutoChunkingStrategyRequestParam

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

Name	Type	Description	Required	Default
type	enum	Always auto. Possible values: auto	Yes

OpenAI.Batch

Name	Type	Description	Required	Default
cancelled_at	integer	The Unix timestamp (in seconds) for when the batch was cancelled.	No
cancelling_at	integer	The Unix timestamp (in seconds) for when the batch started cancelling.	No
completed_at	integer	The Unix timestamp (in seconds) for when the batch was completed.	No
completion_window	string	The time frame within which the batch should be processed.	Yes
created_at	integer	The Unix timestamp (in seconds) for when the batch was created.	Yes
endpoint	string	The OpenAI API endpoint used by the batch.	Yes
error_file_id	string	The ID of the file containing the outputs of requests with errors.	No
errors	OpenAI.BatchErrors		No
expired_at	integer	The Unix timestamp (in seconds) for when the batch expired.	No
expires_at	integer	The Unix timestamp (in seconds) for when the batch will expire.	No
failed_at	integer	The Unix timestamp (in seconds) for when the batch failed.	No
finalizing_at	integer	The Unix timestamp (in seconds) for when the batch started finalizing.	No
id	string		Yes
in_progress_at	integer	The Unix timestamp (in seconds) for when the batch started processing.	No
input_file_id	string or null		No
metadata	OpenAI.Metadata or null		No
model	string	Model ID used to process the batch, like gpt-5-2025-08-07. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
object	enum	The object type, which is always batch. Possible values: batch	Yes
output_file_id	string	The ID of the file containing the outputs of successfully executed requests.	No
request_counts	OpenAI.BatchRequestCounts	The request counts for different statuses within the batch.	No
status	enum	The current status of the batch. Possible values: validating, failed, in_progress, finalizing, completed, expired, cancelling, cancelled	Yes
usage	OpenAI.BatchUsage		No
└─ input_tokens	integer		Yes
└─ input_tokens_details	OpenAI.BatchUsageInputTokensDetails		Yes
└─ output_tokens	integer		Yes
└─ output_tokens_details	OpenAI.BatchUsageOutputTokensDetails		Yes
└─ total_tokens	integer		Yes

OpenAI.BatchError

Name	Type	Description	Required	Default
code	string	An error code identifying the error type.	No
line	integer or null		No
message	string	A human-readable message providing more details about the error.	No
param	string or null		No

OpenAI.BatchErrors

Name	Type	Description	Required	Default
data	array of OpenAI.BatchError		No
object	string		No

OpenAI.BatchRequestCounts

The request counts for different statuses within the batch.

Name	Type	Description	Required	Default
completed	integer	Number of requests that have been completed successfully.	Yes
failed	integer	Number of requests that have failed.	Yes
total	integer	Total number of requests in the batch.	Yes

OpenAI.BatchUsage

Name	Type	Description	Required	Default
input_tokens	integer		Yes
input_tokens_details	OpenAI.BatchUsageInputTokensDetails		Yes
output_tokens	integer		Yes
output_tokens_details	OpenAI.BatchUsageOutputTokensDetails		Yes
total_tokens	integer		Yes

OpenAI.BatchUsageInputTokensDetails

Name	Type	Description	Required	Default
cached_tokens	integer		Yes

OpenAI.BatchUsageOutputTokensDetails

Name	Type	Description	Required	Default
reasoning_tokens	integer		Yes

OpenAI.ChatCompletionAllowedTools

Constrains the tools available to the model to a predefined set.

Name	Type	Description	Required	Default
mode	enum	Constrains the tools available to the model to a predefined set. auto allows the model to pick from among the allowed tools and generate a message. required requires the model to call one or more of the allowed tools. Possible values: auto, required	Yes
tools	array of object	A list of tool definitions that the model should be allowed to call. For the Chat Completions API, the list of tool definitions might look like: json<br /> [<br /> { "type": "function", "function": { "name": "get_weather" } },<br /> { "type": "function", "function": { "name": "get_time" } }<br /> ]<br />	Yes

OpenAI.ChatCompletionAllowedToolsChoice

Constrains the tools available to the model to a predefined set.

Name	Type	Description	Required	Default
allowed_tools	OpenAI.ChatCompletionAllowedTools	Constrains the tools available to the model to a predefined set.	Yes
type	enum	Allowed tool configuration type. Always allowed_tools. Possible values: allowed_tools	Yes

OpenAI.ChatCompletionFunctionCallOption

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

Name	Type	Description	Required	Default
name	string	The name of the function to call.	Yes

OpenAI.ChatCompletionFunctions

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. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.	Yes
parameters	OpenAI.FunctionParameters	The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.	No

OpenAI.ChatCompletionMessageCustomToolCall

A call to a custom tool created by the model.

Name	Type	Description	Required	Default
custom	OpenAI.ChatCompletionMessageCustomToolCallCustom		Yes
└─ input	string		Yes
└─ name	string		Yes
id	string	The ID of the tool call.	Yes
type	enum	The type of the tool. Always custom. Possible values: custom	Yes

OpenAI.ChatCompletionMessageCustomToolCallCustom

Name	Type	Description	Required	Default
input	string		Yes
name	string		Yes

OpenAI.ChatCompletionMessageToolCall

A call to a function tool created by the model.

Name	Type	Description	Required	Default
function	OpenAI.ChatCompletionMessageToolCallFunction		Yes
└─ arguments	string		Yes
└─ name	string		Yes
id	string	The ID of the tool call.	Yes
type	enum	The type of the tool. Currently, only function is supported. Possible values: function	Yes

OpenAI.ChatCompletionMessageToolCallChunk

Name	Type	Description	Required	Default
function	OpenAI.ChatCompletionMessageToolCallChunkFunction		No
id	string	The ID of the tool call.	No
index	integer		Yes
type	enum	The type of the tool. Currently, only function is supported. Possible values: function	No

OpenAI.ChatCompletionMessageToolCallChunkFunction

Name	Type	Description	Required	Default
arguments	string		No
name	string		No

OpenAI.ChatCompletionMessageToolCallFunction

Name	Type	Description	Required	Default
arguments	string		Yes
name	string		Yes

OpenAI.ChatCompletionMessageToolCalls

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

OpenAI.ChatCompletionMessageToolCallsItem

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

OpenAI.ChatCompletionNamedToolChoice

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

Name	Type	Description	Required	Default
function	OpenAI.ChatCompletionNamedToolChoiceFunction		Yes
type	enum	For function calling, the type is always function. Possible values: function	Yes

OpenAI.ChatCompletionNamedToolChoiceCustom

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

Name	Type	Description	Required	Default
custom	OpenAI.ChatCompletionNamedToolChoiceCustomCustom		Yes
type	enum	For custom tool calling, the type is always custom. Possible values: custom	Yes

OpenAI.ChatCompletionNamedToolChoiceCustomCustom

Name	Type	Description	Required	Default
name	string		Yes

OpenAI.ChatCompletionNamedToolChoiceFunction

Name	Type	Description	Required	Default
name	string		Yes

OpenAI.ChatCompletionRequestAssistantMessage

Messages sent by the model in response to user messages.

Name	Type	Description	Required	Default
audio	OpenAI.ChatCompletionRequestAssistantMessageAudio or null	Data about a previous audio response from the model.	No
content	string or array of OpenAI.ChatCompletionRequestAssistantMessageContentPart or null		No
function_call	OpenAI.ChatCompletionRequestAssistantMessageFunctionCall or null		No
name	string	An optional name for the participant. Provides the model information to differentiate between participants of the same role.	No
refusal	string or null		No
role	enum	The role of the messages author, in this case assistant. Possible values: assistant	Yes
tool_calls	OpenAI.ChatCompletionMessageToolCalls	The tool calls generated by the model, such as function calls.	No

OpenAI.ChatCompletionRequestAssistantMessageAudio

Name	Type	Description	Required	Default
id	string		Yes

OpenAI.ChatCompletionRequestAssistantMessageContentPart

Discriminator for OpenAI.ChatCompletionRequestAssistantMessageContentPart

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

Type Value	Schema
refusal	OpenAI.ChatCompletionRequestMessageContentPartRefusal
text	OpenAI.ChatCompletionRequestAssistantMessageContentPartChatCompletionRequestMessageContentPartText

Name	Type	Description	Required	Default
type	OpenAI.ChatCompletionRequestAssistantMessageContentPartType		Yes

OpenAI.ChatCompletionRequestAssistantMessageContentPartChatCompletionRequestMessageContentPartText

Learn about text inputs.

Name	Type	Description	Required	Default
text	string	The text content.	Yes
type	enum	The type of the content part. Possible values: text	Yes

OpenAI.ChatCompletionRequestAssistantMessageContentPartType

Property	Value
Type	string
Values	text refusal

OpenAI.ChatCompletionRequestAssistantMessageFunctionCall

Name	Type	Description	Required	Default
arguments	string		Yes
name	string		Yes

OpenAI.ChatCompletionRequestDeveloperMessage

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

Name	Type	Description	Required	Default
content	string or array of OpenAI.ChatCompletionRequestMessageContentPartText	The contents of the developer message.	Yes
name	string	An optional name for the participant. Provides the model information to differentiate between participants of the same role.	No
role	enum	The role of the messages author, in this case developer. Possible values: developer	Yes

OpenAI.ChatCompletionRequestFunctionMessage

Name	Type	Description	Required	Default
content	string or null		Yes
name	string	The name of the function to call.	Yes
role	enum	The role of the messages author, in this case function. Possible values: function	Yes

OpenAI.ChatCompletionRequestMessage

Discriminator for OpenAI.ChatCompletionRequestMessage

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

Type Value	Schema
assistant	OpenAI.ChatCompletionRequestAssistantMessage
developer	OpenAI.ChatCompletionRequestDeveloperMessage
function	OpenAI.ChatCompletionRequestFunctionMessage
system	OpenAI.ChatCompletionRequestSystemMessage
user	OpenAI.ChatCompletionRequestUserMessage
tool	OpenAI.ChatCompletionRequestToolMessage

Name	Type	Description	Required	Default
role	OpenAI.ChatCompletionRequestMessageType		Yes

OpenAI.ChatCompletionRequestMessageContentPartAudio

Name	Type	Description	Required	Default
input_audio	OpenAI.ChatCompletionRequestMessageContentPartAudioInputAudio		Yes
type	enum	The type of the content part. Always input_audio. Possible values: input_audio	Yes

OpenAI.ChatCompletionRequestMessageContentPartAudioInputAudio

Name	Type	Description	Required	Default
data	string		Yes
format	enum	Possible values: wav, mp3	Yes

OpenAI.ChatCompletionRequestMessageContentPartFile

Learn about file inputs for text generation.

Name	Type	Description	Required	Default
file	OpenAI.ChatCompletionRequestMessageContentPartFileFile		Yes
└─ file_data	string		No
└─ file_id	string		No
└─ filename	string		No
type	enum	The type of the content part. Always file. Possible values: file	Yes

OpenAI.ChatCompletionRequestMessageContentPartFileFile

Name	Type	Description	Required	Default
file_data	string		No
file_id	string		No
filename	string		No

OpenAI.ChatCompletionRequestMessageContentPartImage

Name	Type	Description	Required	Default
image_url	OpenAI.ChatCompletionRequestMessageContentPartImageImageUrl		Yes
type	enum	The type of the content part. Possible values: image_url	Yes

OpenAI.ChatCompletionRequestMessageContentPartImageImageUrl

Name	Type	Description	Required	Default
detail	enum	Possible values: auto, low, high	No
url	string		Yes

OpenAI.ChatCompletionRequestMessageContentPartRefusal

Name	Type	Description	Required	Default
refusal	string	The refusal message generated by the model.	Yes
type	enum	The type of the content part. Possible values: refusal	Yes

OpenAI.ChatCompletionRequestMessageContentPartText

Name	Type	Description	Required	Default
text	string	The text content.	Yes
type	enum	The type of the content part. Possible values: text	Yes

OpenAI.ChatCompletionRequestMessageType

Property	Value
Type	string
Values	developer system user assistant tool function

OpenAI.ChatCompletionRequestSystemMessage

Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use developer messages for this purpose instead.

Name	Type	Description	Required	Default
content	string or array of OpenAI.ChatCompletionRequestSystemMessageContentPart	The contents of the system message.	Yes
name	string	An optional name for the participant. Provides the model information to differentiate between participants of the same role.	No
role	enum	The role of the messages author, in this case system. Possible values: system	Yes

OpenAI.ChatCompletionRequestSystemMessageContentPart

References: OpenAI.ChatCompletionRequestMessageContentPartText

OpenAI.ChatCompletionRequestToolMessage

Name	Type	Description	Required	Default
content	string or array of OpenAI.ChatCompletionRequestToolMessageContentPart	The contents of the tool message.	Yes
role	enum	The role of the messages author, in this case tool. Possible values: tool	Yes
tool_call_id	string	Tool call that this message is responding to.	Yes

OpenAI.ChatCompletionRequestToolMessageContentPart

References: OpenAI.ChatCompletionRequestMessageContentPartText

OpenAI.ChatCompletionRequestUserMessage

Messages sent by an end user, containing prompts or additional context information.

Name	Type	Description	Required	Default
content	string or array of OpenAI.ChatCompletionRequestUserMessageContentPart	The contents of the user message.	Yes
name	string	An optional name for the participant. Provides the model information to differentiate between participants of the same role.	No
role	enum	The role of the messages author, in this case user. Possible values: user	Yes

OpenAI.ChatCompletionRequestUserMessageContentPart

Discriminator for OpenAI.ChatCompletionRequestUserMessageContentPart

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

Type Value	Schema
image_url	OpenAI.ChatCompletionRequestMessageContentPartImage
input_audio	OpenAI.ChatCompletionRequestMessageContentPartAudio
file	OpenAI.ChatCompletionRequestMessageContentPartFile
text	OpenAI.ChatCompletionRequestUserMessageContentPartChatCompletionRequestMessageContentPartText

Name	Type	Description	Required	Default
type	OpenAI.ChatCompletionRequestUserMessageContentPartType		Yes

OpenAI.ChatCompletionRequestUserMessageContentPartChatCompletionRequestMessageContentPartText

Learn about text inputs.

Name	Type	Description	Required	Default
text	string	The text content.	Yes
type	enum	The type of the content part. Possible values: text	Yes

OpenAI.ChatCompletionRequestUserMessageContentPartType

Property	Value
Type	string
Values	text image_url input_audio file

OpenAI.ChatCompletionResponseMessage

If the audio output modality is requested, this object contains data about the audio response from the model.

Name	Type	Description	Required	Default
annotations	array of OpenAI.ChatCompletionResponseMessageAnnotations	Annotations for the message, when applicable, as when using the web search tool.	No
audio	OpenAI.ChatCompletionResponseMessageAudio or null		No
content	string or null		Yes
function_call	OpenAI.ChatCompletionResponseMessageFunctionCall		No
└─ arguments	string		Yes
└─ name	string		Yes
reasoning_content	string	An Azure-specific extension property containing generated reasoning content from supported models.	No
refusal	string or null		Yes
role	enum	The role of the author of this message. Possible values: assistant	Yes
tool_calls	OpenAI.ChatCompletionMessageToolCallsItem	The tool calls generated by the model, such as function calls.	No

OpenAI.ChatCompletionResponseMessageAnnotations

Name	Type	Description	Required	Default
type	enum	Possible values: url_citation	Yes
url_citation	OpenAI.ChatCompletionResponseMessageAnnotationsUrlCitation		Yes

OpenAI.ChatCompletionResponseMessageAnnotationsUrlCitation

Name	Type	Description	Required	Default
end_index	integer		Yes
start_index	integer		Yes
title	string		Yes
url	string		Yes

OpenAI.ChatCompletionResponseMessageAudio

Name	Type	Description	Required	Default
data	string		Yes
expires_at	integer		Yes
id	string		Yes
transcript	string		Yes

OpenAI.ChatCompletionResponseMessageFunctionCall

Name	Type	Description	Required	Default
arguments	string		Yes
name	string		Yes

OpenAI.ChatCompletionStreamOptions

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

Name	Type	Description	Required	Default
include_obfuscation	boolean	When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.	No
include_usage	boolean	If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array. All other chunks will also include a usage field, but with a null value. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.	No

OpenAI.ChatCompletionStreamResponseDelta

A chat completion delta generated by streamed model responses.

Name	Type	Description	Required	Default
content	string or null		No
function_call	OpenAI.ChatCompletionStreamResponseDeltaFunctionCall		No
└─ arguments	string		No
└─ name	string		No
reasoning_content	string	An Azure-specific extension property containing generated reasoning content from supported models.	No
refusal	string or null		No
role	enum	The role of the author of this message. Possible values: developer, system, user, assistant, tool	No
tool_calls	array of OpenAI.ChatCompletionMessageToolCallChunk		No

OpenAI.ChatCompletionStreamResponseDeltaFunctionCall

Name	Type	Description	Required	Default
arguments	string		No
name	string		No

OpenAI.ChatCompletionTokenLogprob

Name	Type	Description	Required	Default
bytes	array of integer or null		Yes
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.	Yes
token	string	The token.	Yes
top_logprobs	array of OpenAI.ChatCompletionTokenLogprobTopLogprobs	List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.	Yes

OpenAI.ChatCompletionTokenLogprobTopLogprobs

Name	Type	Description	Required	Default
bytes	array of integer or null		Yes
logprob	number		Yes
token	string		Yes

OpenAI.ChatCompletionTool

A function tool that can be used to generate a response.

Name	Type	Description	Required	Default
function	OpenAI.FunctionObject		Yes
type	enum	The type of the tool. Currently, only function is supported. Possible values: function	Yes

OpenAI.ChatCompletionToolChoiceOption

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

Type: string or OpenAI.ChatCompletionAllowedToolsChoice or OpenAI.ChatCompletionNamedToolChoice or OpenAI.ChatCompletionNamedToolChoiceCustom

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

OpenAI.ChunkingStrategyRequestParam

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.

Discriminator for OpenAI.ChunkingStrategyRequestParam

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

Type Value	Schema
auto	OpenAI.AutoChunkingStrategyRequestParam
static	OpenAI.StaticChunkingStrategyRequestParam

Name	Type	Description	Required	Default
type	OpenAI.ChunkingStrategyRequestParamType		Yes

OpenAI.ChunkingStrategyRequestParamType

Property	Value
Type	string
Values	auto static

OpenAI.ChunkingStrategyResponse

The strategy used to chunk the file.

Discriminator for OpenAI.ChunkingStrategyResponse

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

Type Value	Schema
static	OpenAI.StaticChunkingStrategyResponseParam
other	OpenAI.OtherChunkingStrategyResponseParam

Name	Type	Description	Required	Default
type	OpenAI.ChunkingStrategyResponseType		Yes

OpenAI.ChunkingStrategyResponseType

Property	Value
Type	string
Values	static other

OpenAI.ClickButtonType

Property	Value
Type	string
Values	left right wheel back forward

OpenAI.ClickParam

A click action.

Name	Type	Description	Required	Default
button	OpenAI.ClickButtonType		Yes
type	enum	Specifies the event type. For a click action, this property is always click. Possible values: click	Yes
x	integer	The x-coordinate where the click occurred.	Yes
y	integer	The y-coordinate where the click occurred.	Yes

OpenAI.CodeInterpreterContainerAuto

Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

Name	Type	Description	Required	Default
file_ids	array of string	An optional list of uploaded files to make available to your code.	No
memory_limit	OpenAI.ContainerMemoryLimit or null		No
type	enum	Always auto. Possible values: auto	Yes

OpenAI.CodeInterpreterOutputImage

The image output from the code interpreter.

Name	Type	Description	Required	Default
type	enum	The type of the output. Always image. Possible values: image	Yes
url	string	The URL of the image output from the code interpreter.	Yes

OpenAI.CodeInterpreterOutputLogs

The logs output from the code interpreter.

Name	Type	Description	Required	Default
logs	string	The logs output from the code interpreter.	Yes
type	enum	The type of the output. Always logs. Possible values: logs	Yes

OpenAI.CodeInterpreterTool

A tool that runs Python code to help generate a response to a prompt.

Name	Type	Description	Required	Default
container	string or OpenAI.CodeInterpreterContainerAuto	The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.	Yes
type	enum	The type of the code interpreter tool. Always code_interpreter. Possible values: code_interpreter	Yes

OpenAI.ComparisonFilter

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

Name	Type	Description	Required	Default
key	string	The key to compare against the value.	Yes
type	enum	Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin. - eq: equals - ne: not equal - gt: greater than - gte: greater than or equal - lt: less than - lte: less than or equal - in: in - nin: not in Possible values: eq, ne, gt, gte, lt, lte	Yes
value	string or number or boolean or array of OpenAI.ComparisonFilterValueItems	The value to compare against the attribute key; supports string, number, or boolean types.	Yes

OpenAI.ComparisonFilterValueItems

This schema accepts one of the following types:

• string
• number

OpenAI.CompletionUsage

Usage statistics for the completion request.

Name	Type	Description	Required	Default
completion_tokens	integer	Number of tokens in the generated completion.	Yes
completion_tokens_details	OpenAI.CompletionUsageCompletionTokensDetails		No
└─ accepted_prediction_tokens	integer		No
└─ audio_tokens	integer		No
└─ reasoning_tokens	integer		No
└─ rejected_prediction_tokens	integer		No
prompt_tokens	integer	Number of tokens in the prompt.	Yes
prompt_tokens_details	OpenAI.CompletionUsagePromptTokensDetails		No
└─ audio_tokens	integer		No
└─ cached_tokens	integer		No
total_tokens	integer	Total number of tokens used in the request (prompt + completion).	Yes

OpenAI.CompletionUsageCompletionTokensDetails

Name	Type	Description	Required	Default
accepted_prediction_tokens	integer		No
audio_tokens	integer		No
reasoning_tokens	integer		No
rejected_prediction_tokens	integer		No

OpenAI.CompletionUsagePromptTokensDetails

Name	Type	Description	Required	Default
audio_tokens	integer		No
cached_tokens	integer		No

OpenAI.CompoundFilter

Combine multiple filters using and or or.

Name	Type	Description	Required	Default
filters	array of OpenAI.ComparisonFilter or object	Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.	Yes
type	enum	Type of operation: and or or. Possible values: and, or	Yes

OpenAI.ComputerAction

Discriminator for OpenAI.ComputerAction

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

Type Value	Schema
click	OpenAI.ClickParam
double_click	OpenAI.DoubleClickAction
drag	OpenAI.Drag
keypress	OpenAI.KeyPressAction
move	OpenAI.Move
screenshot	OpenAI.Screenshot
scroll	OpenAI.Scroll
type	OpenAI.Type
wait	OpenAI.Wait

Name	Type	Description	Required	Default
type	OpenAI.ComputerActionType		Yes

OpenAI.ComputerActionType

Property	Value
Type	string
Values	click double_click drag keypress move screenshot scroll type wait

OpenAI.ComputerCallSafetyCheckParam

A pending safety check for the computer call.

Name	Type	Description	Required	Default
code	string or null		No
id	string	The ID of the pending safety check.	Yes
message	string or null		No

OpenAI.ComputerEnvironment

Property	Value
Type	string
Values	windows mac linux ubuntu browser

OpenAI.ComputerScreenshotContent

A screenshot of a computer.

Name	Type	Description	Required	Default
file_id	string or null		Yes
image_url	string or null		Yes
type	enum	Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot. Possible values: computer_screenshot	Yes

OpenAI.ComputerScreenshotImage

A computer screenshot image used with the computer use tool.

Name	Type	Description	Required	Default
file_id	string	The identifier of an uploaded file that contains the screenshot.	No
image_url	string	The URL of the screenshot image.	No
type	enum	Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot. Possible values: computer_screenshot	Yes

OpenAI.ComputerUsePreviewTool

A tool that controls a virtual computer.

Name	Type	Description	Required	Default
display_height	integer	The height of the computer display.	Yes
display_width	integer	The width of the computer display.	Yes
environment	OpenAI.ComputerEnvironment		Yes
type	enum	The type of the computer use tool. Always computer_use_preview. Possible values: computer_use_preview	Yes

OpenAI.ContainerFileCitationBody

A citation for a container file used to generate a model response.

Name	Type	Description	Required	Default
container_id	string	The ID of the container file.	Yes
end_index	integer	The index of the last character of the container file citation in the message.	Yes
file_id	string	The ID of the file.	Yes
filename	string	The filename of the container file cited.	Yes
start_index	integer	The index of the first character of the container file citation in the message.	Yes
type	enum	The type of the container file citation. Always container_file_citation. Possible values: container_file_citation	Yes

OpenAI.ContainerFileListResource

Name	Type	Description	Required	Default
data	array of OpenAI.ContainerFileResource	A list of container files.	Yes
first_id	string	The ID of the first file in the list.	Yes
has_more	boolean	Whether there are more files available.	Yes
last_id	string	The ID of the last file in the list.	Yes
object	enum	The type of object returned, must be ‘list’. Possible values: list	Yes

OpenAI.ContainerFileResource

Name	Type	Description	Required	Default
bytes	integer	Size of the file in bytes.	Yes
container_id	string	The container this file belongs to.	Yes
created_at	integer	Unix timestamp (in seconds) when the file was created.	Yes
id	string	Unique identifier for the file.	Yes
object	enum	The type of this object (container.file). Possible values: container.file	Yes
path	string	Path of the file in the container.	Yes
source	string	Source of the file (for example, user, assistant).	Yes

OpenAI.ContainerListResource

Name	Type	Description	Required	Default
data	array of OpenAI.ContainerResource	A list of containers.	Yes
first_id	string	The ID of the first container in the list.	Yes
has_more	boolean	Whether there are more containers available.	Yes
last_id	string	The ID of the last container in the list.	Yes
object	enum	The type of object returned, must be ‘list’. Possible values: list	Yes

OpenAI.ContainerMemoryLimit

Property	Value
Type	string
Values	1g 4g 16g 64g

OpenAI.ContainerResource

Name	Type	Description	Required	Default
created_at	integer	Unix timestamp (in seconds) when the container was created.	Yes
expires_after	OpenAI.ContainerResourceExpiresAfter		No
└─ anchor	enum	Possible values: last_active_at	No
└─ minutes	integer		No
id	string	Unique identifier for the container.	Yes
last_active_at	integer	Unix timestamp (in seconds) when the container was last active.	No
memory_limit	enum	The memory limit configured for the container. Possible values: 1g, 4g, 16g, 64g	No
name	string	Name of the container.	Yes
object	string	The type of this object.	Yes
status	string	Status of the container (for example, active, deleted).	Yes

OpenAI.ContainerResourceExpiresAfter

Name	Type	Description	Required	Default
anchor	enum	Possible values: last_active_at	No
minutes	integer		No

OpenAI.ConversationItem

A single item within a conversation. The set of possible types are the same as the output type of a Response object.

Discriminator for OpenAI.ConversationItem

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

Type Value	Schema
message	OpenAI.ConversationItemMessage
function_call	OpenAI.ConversationItemFunctionToolCallResource
function_call_output	OpenAI.ConversationItemFunctionToolCallOutputResource
file_search_call	OpenAI.ConversationItemFileSearchToolCall
web_search_call	OpenAI.ConversationItemWebSearchToolCall
image_generation_call	OpenAI.ConversationItemImageGenToolCall
computer_call	OpenAI.ConversationItemComputerToolCall
computer_call_output	OpenAI.ConversationItemComputerToolCallOutputResource
reasoning	OpenAI.ConversationItemReasoningItem
code_interpreter_call	OpenAI.ConversationItemCodeInterpreterToolCall
local_shell_call	OpenAI.ConversationItemLocalShellToolCall
local_shell_call_output	OpenAI.ConversationItemLocalShellToolCallOutput
shell_call	OpenAI.ConversationItemFunctionShellCall
shell_call_output	OpenAI.ConversationItemFunctionShellCallOutput
apply_patch_call	OpenAI.ConversationItemApplyPatchToolCall
apply_patch_call_output	OpenAI.ConversationItemApplyPatchToolCallOutput
mcp_list_tools	OpenAI.ConversationItemMcpListTools
mcp_approval_request	OpenAI.ConversationItemMcpApprovalRequest
mcp_approval_response	OpenAI.ConversationItemMcpApprovalResponseResource
mcp_call	OpenAI.ConversationItemMcpToolCall
custom_tool_call	OpenAI.ConversationItemCustomToolCall
custom_tool_call_output	OpenAI.ConversationItemCustomToolCallOutput

Name	Type	Description	Required	Default
type	OpenAI.ConversationItemType		Yes

OpenAI.ConversationItemApplyPatchToolCall

A tool call that applies file diffs by creating, deleting, or updating files.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the apply patch tool call. Populated when this item is returned via API.	Yes
operation	OpenAI.ApplyPatchFileOperation	One of the create_file, delete_file, or update_file operations applied via apply_patch.	Yes
└─ type	OpenAI.ApplyPatchFileOperationType		Yes
status	OpenAI.ApplyPatchCallStatus		Yes
type	enum	The type of the item. Always apply_patch_call. Possible values: apply_patch_call	Yes

OpenAI.ConversationItemApplyPatchToolCallOutput

The output emitted by an apply patch tool call.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call output.	No
id	string	The unique ID of the apply patch tool call output. Populated when this item is returned via API.	Yes
output	string or null		No
status	OpenAI.ApplyPatchCallOutputStatus		Yes
type	enum	The type of the item. Always apply_patch_call_output. Possible values: apply_patch_call_output	Yes

OpenAI.ConversationItemCodeInterpreterToolCall

A tool call to run code.

Name	Type	Description	Required	Default
code	string or null		Yes
container_id	string	The ID of the container used to run the code.	Yes
id	string	The unique ID of the code interpreter tool call.	Yes
outputs	array of OpenAI.CodeInterpreterOutputLogs or OpenAI.CodeInterpreterOutputImage or null		Yes
status	enum	The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed. Possible values: in_progress, completed, incomplete, interpreting, failed	Yes
type	enum	The type of the code interpreter tool call. Always code_interpreter_call. Possible values: code_interpreter_call	Yes

OpenAI.ConversationItemComputerToolCall

A tool call to a computer use tool. See the computer use guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.ComputerAction		Yes
call_id	string	An identifier used when responding to the tool call with output.	Yes
id	string	The unique ID of the computer call.	Yes
pending_safety_checks	array of OpenAI.ComputerCallSafetyCheckParam	The pending safety checks for the computer call.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the computer call. Always computer_call. Possible values: computer_call	Yes

OpenAI.ConversationItemComputerToolCallOutputResource

Name	Type	Description	Required	Default
acknowledged_safety_checks	array of OpenAI.ComputerCallSafetyCheckParam	The safety checks reported by the API that have been acknowledged by the developer.	No
call_id	string	The ID of the computer tool call that produced the output.	Yes
id	string	The ID of the computer tool call output.	No
output	OpenAI.ComputerScreenshotImage	A computer screenshot image used with the computer use tool.	Yes
status	enum	The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the computer tool call output. Always computer_call_output. Possible values: computer_call_output	Yes

OpenAI.ConversationItemCustomToolCall

A call to a custom tool created by the model.

Name	Type	Description	Required	Default
call_id	string	An identifier used to map this custom tool call to a tool call output.	Yes
id	string	The unique ID of the custom tool call in the OpenAI platform.	No
input	string	The input for the custom tool call generated by the model.	Yes
name	string	The name of the custom tool being called.	Yes
type	enum	The type of the custom tool call. Always custom_tool_call. Possible values: custom_tool_call	Yes

OpenAI.ConversationItemCustomToolCallOutput

The output of a custom tool call from your code, being sent back to the model.

Name	Type	Description	Required	Default
call_id	string	The call ID, used to map this custom tool call output to a custom tool call.	Yes
id	string	The unique ID of the custom tool call output in the OpenAI platform.	No
output	string or array of OpenAI.FunctionAndCustomToolCallOutput	The output from the custom tool call generated by your code. Can be a string or a list of output content.	Yes
type	enum	The type of the custom tool call output. Always custom_tool_call_output. Possible values: custom_tool_call_output	Yes

OpenAI.ConversationItemFileSearchToolCall

The results of a file search tool call. See the file search guide for more information.

Name	Type	Description	Required	Default
id	string	The unique ID of the file search tool call.	Yes
queries	array of string	The queries used to search for files.	Yes
results	array of OpenAI.FileSearchToolCallResults or null		No
status	enum	The status of the file search tool call. One of in_progress, searching, incomplete or failed, Possible values: in_progress, searching, completed, incomplete, failed	Yes
type	enum	The type of the file search tool call. Always file_search_call. Possible values: file_search_call	Yes

OpenAI.ConversationItemFunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Name	Type	Description	Required	Default
action	OpenAI.FunctionShellAction	Execute a shell command.	Yes
└─ commands	array of string		Yes
└─ max_output_length	integer or null		Yes
└─ timeout_ms	integer or null		Yes
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the shell tool call. Populated when this item is returned via API.	Yes
status	OpenAI.LocalShellCallStatus		Yes
type	enum	The type of the item. Always shell_call. Possible values: shell_call	Yes

OpenAI.ConversationItemFunctionShellCallOutput

The output of a shell tool call that was emitted.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The identifier of the actor that created the item.	No
id	string	The unique ID of the shell call output. Populated when this item is returned via API.	Yes
max_output_length	integer or null		Yes
output	array of OpenAI.FunctionShellCallOutputContent	An array of shell call output contents	Yes
type	enum	The type of the shell call output. Always shell_call_output. Possible values: shell_call_output	Yes

OpenAI.ConversationItemFunctionToolCallOutputResource

Name	Type	Description	Required	Default
call_id	string	The unique ID of the function tool call generated by the model.	Yes
id	string	The unique ID of the function tool call output. Populated when this item is returned via API.	No
output	string or array of OpenAI.FunctionAndCustomToolCallOutput	The output from the function call generated by your code. Can be a string or a list of output content.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the function tool call output. Always function_call_output. Possible values: function_call_output	Yes

OpenAI.ConversationItemFunctionToolCallResource

Name	Type	Description	Required	Default
arguments	string	A JSON string of the arguments to pass to the function.	Yes
call_id	string	The unique ID of the function tool call generated by the model.	Yes
id	string	The unique ID of the function tool call.	No
name	string	The name of the function to run.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the function tool call. Always function_call. Possible values: function_call	Yes

OpenAI.ConversationItemImageGenToolCall

An image generation request made by the model.

Name	Type	Description	Required	Default
id	string	The unique ID of the image generation call.	Yes
result	string or null		Yes
status	enum	The status of the image generation call. Possible values: in_progress, completed, generating, failed	Yes
type	enum	The type of the image generation call. Always image_generation_call. Possible values: image_generation_call	Yes

OpenAI.ConversationItemList

A list of Conversation items.

Name	Type	Description	Required	Default
data	array of OpenAI.ConversationItem	A list of conversation items.	Yes
first_id	string	The ID of the first item in the list.	Yes
has_more	boolean	Whether there are more items available.	Yes
last_id	string	The ID of the last item in the list.	Yes
object	enum	The type of object returned, must be list. Possible values: list	Yes

OpenAI.ConversationItemLocalShellToolCall

A tool call to run a command on the local shell.

Name	Type	Description	Required	Default
action	OpenAI.LocalShellExecAction	Execute a shell command on the server.	Yes
call_id	string	The unique ID of the local shell tool call generated by the model.	Yes
id	string	The unique ID of the local shell call.	Yes
status	enum	The status of the local shell call. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the local shell call. Always local_shell_call. Possible values: local_shell_call	Yes

OpenAI.ConversationItemLocalShellToolCallOutput

The output of a local shell tool call.

Name	Type	Description	Required	Default
id	string	The unique ID of the local shell tool call generated by the model.	Yes
output	string	A JSON string of the output of the local shell tool call.	Yes
status	string or null		No
type	enum	The type of the local shell tool call output. Always local_shell_call_output. Possible values: local_shell_call_output	Yes

OpenAI.ConversationItemMcpApprovalRequest

A request for human approval of a tool invocation.

Name	Type	Description	Required	Default
arguments	string	A JSON string of arguments for the tool.	Yes
id	string	The unique ID of the approval request.	Yes
name	string	The name of the tool to run.	Yes
server_label	string	The label of the MCP server making the request.	Yes
type	enum	The type of the item. Always mcp_approval_request. Possible values: mcp_approval_request	Yes

OpenAI.ConversationItemMcpApprovalResponseResource

A response to an MCP approval request.

Name	Type	Description	Required	Default
approval_request_id	string	The ID of the approval request being answered.	Yes
approve	boolean	Whether the request was approved.	Yes
id	string	The unique ID of the approval response	Yes
reason	string or null		No
type	enum	The type of the item. Always mcp_approval_response. Possible values: mcp_approval_response	Yes

OpenAI.ConversationItemMcpListTools

A list of tools available on an MCP server.

Name	Type	Description	Required	Default
error	string or null		No
id	string	The unique ID of the list.	Yes
server_label	string	The label of the MCP server.	Yes
tools	array of OpenAI.MCPListToolsTool	The tools available on the server.	Yes
type	enum	The type of the item. Always mcp_list_tools. Possible values: mcp_list_tools	Yes

OpenAI.ConversationItemMcpToolCall

An invocation of a tool on an MCP server.

Name	Type	Description	Required	Default
approval_request_id	string or null		No
arguments	string	A JSON string of the arguments passed to the tool.	Yes
error	string or null		No
id	string	The unique ID of the tool call.	Yes
name	string	The name of the tool that was run.	Yes
output	string or null		No
server_label	string	The label of the MCP server running the tool.	Yes
status	OpenAI.MCPToolCallStatus		No
type	enum	The type of the item. Always mcp_call. Possible values: mcp_call	Yes

OpenAI.ConversationItemMessage

A message to or from the model.

Name	Type	Description	Required	Default
content	array of OpenAI.InputTextContent or OpenAI.OutputTextContent or OpenAI.TextContent or OpenAI.SummaryTextContent or OpenAI.ReasoningTextContent or OpenAI.RefusalContent or OpenAI.InputImageContent or OpenAI.ComputerScreenshotContent or OpenAI.InputFileContent	The content of the message	Yes
id	string	The unique ID of the message.	Yes
role	OpenAI.MessageRole		Yes
status	OpenAI.MessageStatus		Yes
type	enum	The type of the message. Always set to message. Possible values: message	Yes

OpenAI.ConversationItemReasoningItem

A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

Name	Type	Description	Required	Default
content	array of OpenAI.ReasoningTextContent	Reasoning text content.	No
encrypted_content	string or null		No
id	string	The unique identifier of the reasoning content.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
summary	array of OpenAI.Summary	Reasoning summary content.	Yes
type	enum	The type of the object. Always reasoning. Possible values: reasoning	Yes

OpenAI.ConversationItemType

Property	Value
Type	string
Values	message function_call function_call_output file_search_call web_search_call image_generation_call computer_call computer_call_output reasoning code_interpreter_call local_shell_call local_shell_call_output shell_call shell_call_output apply_patch_call apply_patch_call_output mcp_list_tools mcp_approval_request mcp_approval_response mcp_call custom_tool_call custom_tool_call_output

OpenAI.ConversationItemWebSearchToolCall

The results of a web search tool call. See the web search guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.WebSearchActionSearch or OpenAI.WebSearchActionOpenPage or OpenAI.WebSearchActionFind	An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find).	Yes
id	string	The unique ID of the web search tool call.	Yes
status	enum	The status of the web search tool call. Possible values: in_progress, searching, completed, failed	Yes
type	enum	The type of the web search tool call. Always web_search_call. Possible values: web_search_call	Yes

OpenAI.ConversationParam

The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.

Type: string or OpenAI.ConversationParam-2

The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.

OpenAI.ConversationParam-2

The conversation that this response belongs to.

Name	Type	Description	Required	Default
id	string	The unique ID of the conversation.	Yes

OpenAI.ConversationReference

The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.

Name	Type	Description	Required	Default
id	string	The unique ID of the conversation that this response was associated with.	Yes

OpenAI.ConversationResource

Name	Type	Description	Required	Default
created_at	integer	The time at which the conversation was created, measured in seconds since the Unix epoch.	Yes
id	string	The unique ID of the conversation.	Yes
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
object	enum	The object type, which is always conversation. Possible values: conversation	Yes

OpenAI.CreateChatCompletionRequestAudio

Name	Type	Description	Required	Default
format	enum	Possible values: wav, aac, mp3, flac, opus, pcm16	Yes
voice	OpenAI.VoiceIdsShared		Yes

OpenAI.CreateChatCompletionRequestResponseFormat

An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Discriminator for OpenAI.CreateChatCompletionRequestResponseFormat

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

Type Value	Schema
json_schema	OpenAI.ResponseFormatJsonSchema
text	OpenAI.CreateChatCompletionRequestResponseFormatResponseFormatText
json_object	OpenAI.CreateChatCompletionRequestResponseFormatResponseFormatJsonObject

Name	Type	Description	Required	Default
type	OpenAI.CreateChatCompletionRequestResponseFormatType		Yes

OpenAI.CreateChatCompletionRequestResponseFormatResponseFormatJsonObject

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always json_object. Possible values: json_object	Yes

OpenAI.CreateChatCompletionRequestResponseFormatResponseFormatText

Default response format. Used to generate text responses.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always text. Possible values: text	Yes

OpenAI.CreateChatCompletionRequestResponseFormatType

Property	Value
Type	string
Values	text json_schema json_object

OpenAI.CreateChatCompletionResponseChoices

Name	Type	Description	Required	Default
content_filter_results	AzureContentFilterResultForChoice	A content filter result for a single response item produced by a generative AI system.	No
finish_reason	enum	Possible values: stop, length, tool_calls, content_filter, function_call	Yes
index	integer		Yes
logprobs	OpenAI.CreateChatCompletionResponseChoicesLogprobs or null		Yes
message	OpenAI.ChatCompletionResponseMessage	If the audio output modality is requested, this object contains data about the audio response from the model.	Yes

OpenAI.CreateChatCompletionResponseChoicesLogprobs

Name	Type	Description	Required	Default
content	array of OpenAI.ChatCompletionTokenLogprob or null		Yes
refusal	array of OpenAI.ChatCompletionTokenLogprob or null		Yes

OpenAI.CreateChatCompletionStreamResponseChoices

Name	Type	Description	Required	Default
delta	OpenAI.ChatCompletionStreamResponseDelta	A chat completion delta generated by streamed model responses.	Yes
finish_reason	string or null		Yes
index	integer		Yes
logprobs	OpenAI.CreateChatCompletionStreamResponseChoicesLogprobs or null		No

OpenAI.CreateChatCompletionStreamResponseChoicesLogprobs

Name	Type	Description	Required	Default
content	array of OpenAI.ChatCompletionTokenLogprob or null		Yes
refusal	array of OpenAI.ChatCompletionTokenLogprob or null		Yes

OpenAI.CreateCompletionResponseChoices

Name	Type	Description	Required	Default
content_filter_results	AzureContentFilterResultForChoice	A content filter result for a single response item produced by a generative AI system.	No
finish_reason	enum	Possible values: stop, length, content_filter	Yes
index	integer		Yes
logprobs	OpenAI.CreateCompletionResponseChoicesLogprobs or null		Yes
text	string		Yes

OpenAI.CreateCompletionResponseChoicesLogprobs

Name	Type	Description	Required	Default
text_offset	array of integer		No
token_logprobs	array of number		No
tokens	array of string		No
top_logprobs	array of object		No

OpenAI.CreateContainerBody

Name	Type	Description	Required	Default
expires_after	OpenAI.CreateContainerBodyExpiresAfter		No
└─ anchor	enum	Possible values: last_active_at	Yes
└─ minutes	integer		Yes
file_ids	array of string	IDs of files to copy to the container.	No
memory_limit	enum	Optional memory limit for the container. Defaults to “1g”. Possible values: 1g, 4g, 16g, 64g	No
name	string	Name of the container to create.	Yes

OpenAI.CreateContainerBodyExpiresAfter

Name	Type	Description	Required	Default
anchor	enum	Possible values: last_active_at	Yes
minutes	integer		Yes

OpenAI.CreateContainerFileBody

Name	Type	Description	Required	Default
file		The File object (not file name) to be uploaded.	No
file_id	string	Name of the file to create.	No

OpenAI.CreateConversationBody

Name	Type	Description	Required	Default
items	array of OpenAI.InputItem or null		No
metadata	OpenAI.Metadata or null		No

OpenAI.CreateConversationItemsParametersBody

Name	Type	Description	Required	Default
items	array of OpenAI.InputItem		Yes

OpenAI.CreateEmbeddingRequest

Name	Type	Description	Required	Default
dimensions	integer	The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models. Constraints: min: 1	No
encoding_format	enum	The format to return the embeddings in. Can be either float or base64. Possible values: float, base64	No
input	string or array of string or array of integer or array of array	Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8,192 tokens for all embedding models), cannot be an empty string, and any array must be 2,048 dimensions or less. Example Python code for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request.	Yes
model	string	ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.	Yes
user	string	Learn more.	No

OpenAI.CreateEmbeddingResponse

Name	Type	Description	Required	Default
data	array of OpenAI.Embedding	The list of embeddings generated by the model.	Yes
model	string	The name of the model used to generate the embedding.	Yes
object	enum	The object type, which is always “list”. Possible values: list	Yes
usage	OpenAI.CreateEmbeddingResponseUsage		Yes
└─ prompt_tokens	integer		Yes
└─ total_tokens	integer		Yes

OpenAI.CreateEmbeddingResponseUsage

Name	Type	Description	Required	Default
prompt_tokens	integer		Yes
total_tokens	integer		Yes

OpenAI.CreateEvalCompletionsRunDataSource

A CompletionsRunDataSource object describing a model sampling configuration.

Name	Type	Description	Required	Default
input_messages	OpenAI.CreateEvalCompletionsRunDataSourceInputMessagesTemplate or OpenAI.CreateEvalCompletionsRunDataSourceInputMessagesItemReference	Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, item.input_trajectory), or a template with variable references to the item namespace.	No
model	string	The name of the model to use for generating completions (for example “o3-mini”).	No
sampling_params	AzureCompletionsSamplingParams	Sampling parameters for controlling the behavior of completions.	No
source	OpenAI.EvalJsonlFileContentSource or OpenAI.EvalJsonlFileIdSource or OpenAI.EvalStoredCompletionsSource	Determines what populates the item namespace in this run’s data source.	Yes
type	enum	The type of run data source. Always completions. Possible values: completions	Yes

OpenAI.CreateEvalCompletionsRunDataSourceInputMessagesItemReference

Name	Type	Description	Required	Default
item_reference	string		Yes
type	enum	Possible values: item_reference	Yes

OpenAI.CreateEvalCompletionsRunDataSourceInputMessagesTemplate

Name	Type	Description	Required	Default
template	array of OpenAI.EasyInputMessage or OpenAI.EvalItem		Yes
type	enum	Possible values: template	Yes

OpenAI.CreateEvalCompletionsRunDataSourceSamplingParams

Name	Type	Description	Required	Default
max_completion_tokens	integer		No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
response_format	OpenAI.ResponseFormatText or OpenAI.ResponseFormatJsonSchema or OpenAI.ResponseFormatJsonObject		No
seed	integer	A seed value initializes the randomness during sampling.	No	42
temperature	number	A higher temperature increases randomness in the outputs.	No	1
tools	array of OpenAI.ChatCompletionTool		No
top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1

OpenAI.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
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

OpenAI.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	The content of the message.	Yes
role	string	The role of the message (for example “system”, “assistant”, “user”).	Yes

OpenAI.CreateEvalJsonlRunDataSource

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

Name	Type	Description	Required	Default
source	OpenAI.EvalJsonlFileContentSource or OpenAI.EvalJsonlFileIdSource	Determines what populates the item namespace in the data source.	Yes
type	enum	The type of data source. Always jsonl. Possible values: jsonl	Yes

OpenAI.CreateEvalLabelModelGrader

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

Name	Type	Description	Required	Default
input	array of OpenAI.CreateEvalItem	A list of chat messages forming the prompt or context. May include variable references to the item namespace, ie {{item.name}}.	Yes
labels	array of string	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 of string	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

OpenAI.CreateEvalLogsDataSourceConfig

A data source config which specifies the metadata property of your logs 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

OpenAI.CreateEvalResponsesRunDataSource

A ResponsesRunDataSource object describing a model sampling configuration.

Name	Type	Description	Required	Default
input_messages	OpenAI.CreateEvalResponsesRunDataSourceInputMessagesTemplate or OpenAI.CreateEvalResponsesRunDataSourceInputMessagesItemReference	Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, item.input_trajectory), or a template with variable references to the item namespace.	No
model	string	The name of the model to use for generating completions (for example “o3-mini”).	No
sampling_params	AzureResponsesSamplingParams	Sampling parameters for controlling the behavior of responses.	No
source	OpenAI.EvalJsonlFileContentSource or OpenAI.EvalJsonlFileIdSource or OpenAI.EvalResponsesSource	Determines what populates the item namespace in this run’s data source.	Yes
type	enum	The type of run data source. Always responses. Possible values: responses	Yes

OpenAI.CreateEvalResponsesRunDataSourceInputMessagesItemReference

Name	Type	Description	Required	Default
item_reference	string		Yes
type	enum	Possible values: item_reference	Yes

OpenAI.CreateEvalResponsesRunDataSourceInputMessagesTemplate

Name	Type	Description	Required	Default
template	array of object or OpenAI.EvalItem		Yes
type	enum	Possible values: template	Yes

OpenAI.CreateEvalResponsesRunDataSourceSamplingParams

Name	Type	Description	Required	Default
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
seed	integer	A seed value initializes the randomness during sampling.	No	42
temperature	number	A higher temperature increases randomness in the outputs.	No	1
text	OpenAI.CreateEvalResponsesRunDataSourceSamplingParamsText		No
tools	array of OpenAI.Tool		No
top_p	number	An alternative to temperature for nucleus sampling; 1.0 includes all tokens.	No	1

OpenAI.CreateEvalResponsesRunDataSourceSamplingParamsText

Name	Type	Description	Required	Default
format	OpenAI.TextResponseFormatConfiguration	An object specifying the format that the model must output. Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the The default format is { "type": "text" } with no additional options. *Not recommended for gpt-4o and newer models:** Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.	No

OpenAI.CreateEvalRunRequest

Name	Type	Description	Required	Default
data_source	OpenAI.CreateEvalJsonlRunDataSource or OpenAI.CreateEvalCompletionsRunDataSource or OpenAI.CreateEvalResponsesRunDataSource	Details about the run’s data source.	Yes
metadata	OpenAI.Metadata or null		No
name	string	The name of the run.	No

OpenAI.CreateEvalStoredCompletionsDataSourceConfig

Deprecated in favor of LogsDataSourceConfig.

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

OpenAI.CreateFileRequest

Name	Type	Description	Required	Default
expires_after	object		Yes
└─ anchor	AzureFileExpiryAnchor		Yes
└─ seconds	integer		Yes
file		The File object (not file name) to be uploaded.	Yes
purpose	enum	The intended purpose of the uploaded file. One of: - assistants: Used in the Assistants API - batch: Used in the Batch API - fine-tune: Used for fine-tuning - evals: Used for eval data sets Possible values: assistants, batch, fine-tune, evals	Yes

OpenAI.CreateFineTuningCheckpointPermissionRequest

Name	Type	Description	Required	Default
project_ids	array of string	The project identifiers to grant access to.	Yes

OpenAI.CreateFineTuningJobRequest

Valid models:

babbage-002
davinci-002
gpt-3.5-turbo
gpt-4o-mini

Name	Type	Description	Required	Default
hyperparameters	OpenAI.CreateFineTuningJobRequestHyperparameters		No
└─ batch_size	string or integer		No	auto
└─ learning_rate_multiplier	string or number		No
└─ n_epochs	string or integer		No	auto
integrations	array of OpenAI.CreateFineTuningJobRequestIntegrations or null	A list of integrations to enable for your fine-tuning job.	No
metadata	OpenAI.Metadata or null		No
method	OpenAI.FineTuneMethod	The method used for fine-tuning.	No
model	string (see valid models below)	The name of the model to fine-tune. You can select one of the supported models.	Yes
seed	integer or null	The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.	No
suffix	string or null	A string of up to 64 characters that will be added to your fine-tuned model name. For example, a suffix of “custom-model-name” would produce a model name like ft:gpt-4o-mini:openai:custom-model-name:7p4lURel.	No
training_file	string	The ID of an uploaded file that contains training data. See upload file for how to upload a file. Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose fine-tune. The contents of the file should differ depending on if the model uses the chat, completions format, or if the fine-tuning method uses the preference format. See the fine-tuning guide for more details.	Yes
validation_file	string or null	The ID of an uploaded file that contains validation data. If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files. Your dataset must be formatted as a JSONL file. You must upload your file with the purpose fine-tune. See the fine-tuning guide for more details.	No

OpenAI.CreateFineTuningJobRequestHyperparameters

Name	Type	Description	Required	Default
batch_size	string or integer		No
learning_rate_multiplier	string or number		No
n_epochs	string or integer		No

OpenAI.CreateFineTuningJobRequestIntegrations

Name	Type	Description	Required	Default
type	enum	Possible values: wandb	Yes
wandb	OpenAI.CreateFineTuningJobRequestIntegrationsWandb		Yes

OpenAI.CreateFineTuningJobRequestIntegrationsWandb

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

OpenAI.CreateMessageRequest

Name	Type	Description	Required	Default
attachments	array of OpenAI.CreateMessageRequestAttachments or null		No
content	string or array of OpenAI.MessageContentImageFileObject or OpenAI.MessageContentImageUrlObject or OpenAI.MessageRequestContentTextObject		Yes
metadata	OpenAI.Metadata or null		No
role	enum	The role of the entity that is creating the message. Allowed values include: - user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. - assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. Possible values: user, assistant	Yes

OpenAI.CreateMessageRequestAttachments

Name	Type	Description	Required	Default
file_id	string		No
tools	array of OpenAI.AssistantToolsCode or OpenAI.AssistantToolsFileSearchTypeOnly		No

OpenAI.CreateResponse

Name	Type	Description	Required	Default
background	boolean or null		No
conversation	OpenAI.ConversationParam or null		No
include	array of OpenAI.IncludeEnum or null		No
input	OpenAI.InputParam	Text, image, or file inputs to the model, used to generate a response. Learn more: - Text inputs and outputs - Image inputs - File inputs - Conversation state - Function calling	No
instructions	string or null		No
max_output_tokens	integer or null		No
max_tool_calls	integer or null		No
metadata	OpenAI.Metadata or null		No
model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
parallel_tool_calls	boolean or null		No
previous_response_id	string or null		No
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
prompt_cache_retention	string or null		No
reasoning	OpenAI.Reasoning or null		No
safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
store	boolean or null		No
stream	boolean or null		No
stream_options	OpenAI.ResponseStreamOptions or null		No
temperature	number or null		No
text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
top_logprobs	integer or null		No
top_p	number or null		No
truncation	string or null		No
user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No

OpenAI.CreateRunRequest

Name	Type	Description	Required	Default
additional_instructions	string or null	Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.	No
additional_messages	array of OpenAI.CreateMessageRequest or null	Adds additional messages to the thread before creating the run.	No
assistant_id	string	The ID of the assistant to use to execute this run.	Yes
instructions	string or null	Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.	No
max_completion_tokens	integer or null	The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
max_prompt_tokens	integer or null	The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
metadata	OpenAI.Metadata or null		No
model	string	The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.	No
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
response_format	OpenAI.AssistantsApiResponseFormatOption	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.	No
stream	boolean or null	If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.	No
temperature	number or null	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.	No
tool_choice	OpenAI.AssistantsApiToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.	No
tools	array of OpenAI.AssistantTool	Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.	No
top_p	number or null	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
truncation_strategy	OpenAI.TruncationObject	Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.	No

OpenAI.CreateThreadAndRunRequest

Name	Type	Description	Required	Default
assistant_id	string	The ID of the assistant to use to execute this run.	Yes
instructions	string or null	Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.	No
max_completion_tokens	integer or null	The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
max_prompt_tokens	integer or null	The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.	No
metadata	OpenAI.Metadata or null		No
model	string	The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.	No
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	No
response_format	OpenAI.AssistantsApiResponseFormatOption	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.	No
stream	boolean or null	If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.	No
temperature	number or null	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.	No
thread	OpenAI.CreateThreadRequest	Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.	No
tool_choice	OpenAI.AssistantsApiToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.	No
tool_resources	OpenAI.CreateThreadAndRunRequestToolResources or null	A set of resources that are used by the assistant’s tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.	No
tools	array of OpenAI.AssistantTool	Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.	No
top_p	number or null	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
truncation_strategy	OpenAI.TruncationObject	Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.	No

OpenAI.CreateThreadAndRunRequestToolResources

Name	Type	Description	Required	Default
code_interpreter	OpenAI.CreateThreadAndRunRequestToolResourcesCodeInterpreter		No
file_search	OpenAI.CreateThreadAndRunRequestToolResourcesFileSearch		No

OpenAI.CreateThreadAndRunRequestToolResourcesCodeInterpreter

Name	Type	Description	Required	Default
file_ids	array of string		No	[]

OpenAI.CreateThreadAndRunRequestToolResourcesFileSearch

Name	Type	Description	Required	Default
vector_store_ids	array of string		No

OpenAI.CreateThreadRequest

Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.

Name	Type	Description	Required	Default
messages	array of OpenAI.CreateMessageRequest	A list of messages to start the thread with.	No
metadata	OpenAI.Metadata or null		No
tool_resources	OpenAI.CreateThreadRequestToolResources or null		No

OpenAI.CreateThreadRequestToolResources

Name	Type	Description	Required	Default
code_interpreter	OpenAI.CreateThreadRequestToolResourcesCodeInterpreter		No
file_search	object or object		No

OpenAI.CreateThreadRequestToolResourcesCodeInterpreter

Name	Type	Description	Required	Default
file_ids	array of string		No

OpenAI.CreateVectorStoreFileBatchRequest

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
file_ids	array of string	A list of File IDs that the vector store should use. Useful for tools like file_search that can access files. If attributes or chunking_strategy are provided, they will be applied to all files in the batch. Mutually exclusive with files.	No
files	array of OpenAI.CreateVectorStoreFileRequest	A list of objects that each include a file_id plus optional attributes or chunking_strategy. Use this when you need to override metadata for specific files. The global attributes or chunking_strategy will be ignored and must be specified for each file. Mutually exclusive with file_ids.	No

OpenAI.CreateVectorStoreFileRequest

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
file_id	string	A File ID that the vector store should use. Useful for tools like file_search that can access files.	Yes

OpenAI.CreateVectorStoreRequest

Name	Type	Description	Required	Default
chunking_strategy	OpenAI.ChunkingStrategyRequestParam	The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. Only applicable if file_ids is non-empty.	No
description	string	A description for the vector store. Can be used to describe the vector store’s purpose.	No
expires_after	OpenAI.VectorStoreExpirationAfter	The expiration policy for a vector store.	No
file_ids	array of string	A list of File IDs that the vector store should use. Useful for tools like file_search that can access files.	No
metadata	OpenAI.Metadata or null		No
name	string	The name of the vector store.	No

OpenAI.CustomGrammarFormatParam

A grammar defined by the user.

Name	Type	Description	Required	Default
definition	string	The grammar definition.	Yes
syntax	OpenAI.GrammarSyntax1		Yes
type	enum	Grammar format. Always grammar. Possible values: grammar	Yes

OpenAI.CustomTextFormatParam

Unconstrained free-form text.

Name	Type	Description	Required	Default
type	enum	Unconstrained text format. Always text. Possible values: text	Yes

OpenAI.CustomToolChatCompletions

A custom tool that processes input using a specified format.

Name	Type	Description	Required	Default
custom	OpenAI.CustomToolChatCompletionsCustom		Yes
└─ description	string		No
└─ format	OpenAI.CustomToolChatCompletionsCustomFormatText or OpenAI.CustomToolChatCompletionsCustomFormatGrammar		No
└─ name	string		Yes
type	enum	The type of the custom tool. Always custom. Possible values: custom	Yes

OpenAI.CustomToolChatCompletionsCustom

Name	Type	Description	Required	Default
description	string		No
format	OpenAI.CustomToolChatCompletionsCustomFormatText or OpenAI.CustomToolChatCompletionsCustomFormatGrammar		No
name	string		Yes

OpenAI.CustomToolChatCompletionsCustomFormatGrammar

Name	Type	Description	Required	Default
grammar	OpenAI.CustomToolChatCompletionsCustomFormatGrammarGrammar		Yes
└─ definition	string		Yes
└─ syntax	enum	Possible values: lark, regex	Yes
type	enum	Possible values: grammar	Yes

OpenAI.CustomToolChatCompletionsCustomFormatGrammarGrammar

Name	Type	Description	Required	Default
definition	string		Yes
syntax	enum	Possible values: lark, regex	Yes

OpenAI.CustomToolChatCompletionsCustomFormatText

Name	Type	Description	Required	Default
type	enum	Possible values: text	Yes

OpenAI.CustomToolParam

A custom tool that processes input using a specified format. Learn more about custom tools

Name	Type	Description	Required	Default
description	string	Optional description of the custom tool, used to provide more context.	No
format	OpenAI.CustomToolParamFormat	The input format for the custom tool. Default is unconstrained text.	No
└─ type	OpenAI.CustomToolParamFormatType		Yes
name	string	The name of the custom tool, used to identify it in tool calls.	Yes
type	enum	The type of the custom tool. Always custom. Possible values: custom	Yes

OpenAI.CustomToolParamFormat

The input format for the custom tool. Default is unconstrained text.

Discriminator for OpenAI.CustomToolParamFormat

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

Type Value	Schema
text	OpenAI.CustomTextFormatParam
grammar	OpenAI.CustomGrammarFormatParam

Name	Type	Description	Required	Default
type	OpenAI.CustomToolParamFormatType		Yes

OpenAI.CustomToolParamFormatType

Property	Value
Type	string
Values	text grammar

OpenAI.DeleteFileResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: file	Yes

OpenAI.DeleteFineTuningCheckpointPermissionResponse

Name	Type	Description	Required	Default
deleted	boolean	Whether the fine-tuned model checkpoint permission was successfully deleted.	Yes
id	string	The ID of the fine-tuned model checkpoint permission that was deleted.	Yes
object	enum	The object type, which is always “checkpoint.permission”. Possible values: checkpoint.permission	Yes

OpenAI.DeleteMessageResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: thread.message.deleted	Yes

OpenAI.DeleteModelResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	string		Yes

OpenAI.DeleteThreadResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: thread.deleted	Yes

OpenAI.DeleteVectorStoreFileResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: vector_store.file.deleted	Yes

OpenAI.DeleteVectorStoreResponse

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: vector_store.deleted	Yes

OpenAI.DeletedConversationResource

Name	Type	Description	Required	Default
deleted	boolean		Yes
id	string		Yes
object	enum	Possible values: conversation.deleted	Yes

OpenAI.DoubleClickAction

A double click action.

Name	Type	Description	Required	Default
type	enum	Specifies the event type. For a double click action, this property is always set to double_click. Possible values: double_click	Yes
x	integer	The x-coordinate where the double click occurred.	Yes
y	integer	The y-coordinate where the double click occurred.	Yes

OpenAI.Drag

A drag action.

Name	Type	Description	Required	Default
path	array of OpenAI.DragPoint	An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg <br /> [<br /> { x: 100, y: 200 },<br /> { x: 200, y: 300 }<br /> ]<br />	Yes
type	enum	Specifies the event type. For a drag action, this property is always set to drag. Possible values: drag	Yes

OpenAI.DragPoint

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

Name	Type	Description	Required	Default
x	integer	The x-coordinate.	Yes
y	integer	The y-coordinate.	Yes

OpenAI.EasyInputMessage

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	string or OpenAI.InputMessageContentList	Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.	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	Yes

OpenAI.Embedding

Represents an embedding vector returned by embedding endpoint.

Name	Type	Description	Required	Default
embedding	array of number	The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the embedding guide.	Yes
index	integer	The index of the embedding in the list of embeddings.	Yes
object	enum	The object type, which is always “embedding”. Possible values: embedding	Yes

OpenAI.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 o4-mini is better at my usecase 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	OpenAI.EvalCustomDataSourceConfig or OpenAI.EvalLogsDataSourceConfig or OpenAI.EvalStoredCompletionsDataSourceConfig	Configuration of data sources used in runs of the evaluation.	Yes
id	string	Unique identifier for the evaluation.	Yes
metadata	OpenAI.Metadata or null		Yes
name	string	The name of the evaluation.	Yes
object	enum	The object type. Possible values: eval	Yes
testing_criteria	array of OpenAI.CreateEvalLabelModelGrader or OpenAI.EvalGraderStringCheck or OpenAI.EvalGraderTextSimilarity or OpenAI.EvalGraderPython or OpenAI.EvalGraderScoreModel or EvalGraderEndpoint	A list of testing criteria.	Yes

OpenAI.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

OpenAI.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

OpenAI.EvalGraderPython

Name	Type	Description	Required	Default
image_tag	string	The image tag to use for the python script.	No
name	string	The name of the grader.	Yes
pass_threshold	number	The threshold for the score.	No
source	string	The source code of the python script.	Yes
type	enum	The object type, which is always python. Possible values: python	Yes

OpenAI.EvalGraderScoreModel

Name	Type	Description	Required	Default
input	array of OpenAI.EvalItem	The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and 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 of number	The range of the score. Defaults to [0, 1].	No
sampling_params	OpenAI.EvalGraderScoreModelSamplingParams		No
└─ max_completions_tokens	integer or null		No
└─ reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
└─ seed	integer or null		No
└─ temperature	number or null		No
└─ top_p	number or null		No	1
type	enum	The object type, which is always score_model. Possible values: score_model	Yes

OpenAI.EvalGraderScoreModelSamplingParams

Name	Type	Description	Required	Default
max_completions_tokens	integer or null		No
reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
seed	integer or null		No
temperature	number or null		No
top_p	number or null		No

OpenAI.EvalGraderStringCheck

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

OpenAI.EvalGraderTextSimilarity

Name	Type	Description	Required	Default
evaluation_metric	enum	The evaluation metric to use. One of cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l. Possible values: cosine, 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.	Yes
pass_threshold	number	The threshold for the score.	Yes
reference	string	The text being graded against.	Yes
type	enum	The type of grader. Possible values: text_similarity	Yes

OpenAI.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	OpenAI.EvalItemContent	Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.	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

OpenAI.EvalItemContent

Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

Type: OpenAI.EvalItemContentItem or OpenAI.EvalItemContentArray

Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.

OpenAI.EvalItemContentArray

A list of inputs, each of which may be either an input text, output text, input image, or input audio object.

Array of: OpenAI.EvalItemContentItem

OpenAI.EvalItemContentItem

A single content item: input text, output text, input image, or input audio.

Type: OpenAI.EvalItemContentText or OpenAI.EvalItemContentItemObject

A single content item: input text, output text, input image, or input audio.

OpenAI.EvalItemContentItemObject

A single content item: input text, output text, input image, or input audio.

Discriminator for OpenAI.EvalItemContentItemObject

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

Type Value	Schema
output_text	OpenAI.EvalItemContentOutputText
input_image	OpenAI.EvalItemInputImage
input_audio	OpenAI.InputAudio
input_text	OpenAI.EvalItemContentItemObjectInputTextContent

Name	Type	Description	Required	Default
type	OpenAI.EvalItemContentItemObjectType		Yes

OpenAI.EvalItemContentItemObjectInputTextContent

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

OpenAI.EvalItemContentItemObjectType

Property	Value
Type	string
Values	input_text output_text input_image input_audio

OpenAI.EvalItemContentOutputText

A text output from the model.

Name	Type	Description	Required	Default
text	string	The text output from the model.	Yes
type	enum	The type of the output text. Always output_text. Possible values: output_text	Yes

OpenAI.EvalItemContentText

A text input to the model.

Type: string

OpenAI.EvalItemInputImage

An image input block used within EvalItem content arrays.

Name	Type	Description	Required	Default
detail	string	The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.	No
image_url	string	The URL of the image input.	Yes
type	enum	The type of the image input. Always input_image. Possible values: input_image	Yes

OpenAI.EvalJsonlFileContentSource

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

OpenAI.EvalJsonlFileContentSourceContent

Name	Type	Description	Required	Default
item	object		Yes
sample	object		No

OpenAI.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

OpenAI.EvalList

An object representing a list of evals.

Name	Type	Description	Required	Default
data	array of OpenAI.Eval	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 is always set to “list”. Possible values: list	Yes

OpenAI.EvalLogsDataSourceConfig

A LogsDataSourceConfig which specifies the metadata property of your logs 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	OpenAI.Metadata or null		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 logs. Possible values: logs	Yes

OpenAI.EvalResponsesSource

A EvalResponsesSource object describing a run data source configuration.

Name	Type	Description	Required	Default
created_after	integer or null		No
created_before	integer or null		No
instructions_search	string or null		No
metadata	object or null		No
model	string or null		No
reasoning_effort	OpenAI.ReasoningEffort or null		No
temperature	number or null		No
tools	array of string or null		No
top_p	number or null		No
type	enum	The type of run data source. Always responses. Possible values: responses	Yes
users	array of string or null		No

OpenAI.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	OpenAI.CreateEvalJsonlRunDataSource or OpenAI.CreateEvalCompletionsRunDataSource or OpenAI.CreateEvalResponsesRunDataSource	Information about the run’s data source.	Yes
error	OpenAI.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	OpenAI.Metadata or null		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 of OpenAI.EvalRunPerModelUsage	Usage statistics for each model during the evaluation run.	Yes
per_testing_criteria_results	array of OpenAI.EvalRunPerTestingCriteriaResults	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	OpenAI.EvalRunResultCounts		Yes
└─ errored	integer		Yes
└─ failed	integer		Yes
└─ passed	integer		Yes
└─ total	integer		Yes
status	string	The status of the evaluation run.	Yes

OpenAI.EvalRunList

An object representing a list of runs for an evaluation.

Name	Type	Description	Required	Default
data	array of OpenAI.EvalRun	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 is always set to “list”. Possible values: list	Yes

OpenAI.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 of OpenAI.EvalRunOutputItemResult	A list of grader results for this output item.	Yes
run_id	string	The identifier of the evaluation run associated with this output item.	Yes
sample	OpenAI.EvalRunOutputItemSample		Yes
└─ error	OpenAI.EvalApiError	An object representing an error response from the Eval API.	Yes
└─ finish_reason	string		Yes
└─ input	array of OpenAI.EvalRunOutputItemSampleInput		Yes
└─ max_completion_tokens	integer		Yes
└─ model	string		Yes
└─ output	array of OpenAI.EvalRunOutputItemSampleOutput		Yes
└─ seed	integer		Yes
└─ temperature	number		Yes
└─ top_p	number		Yes
└─ usage	OpenAI.EvalRunOutputItemSampleUsage		Yes
status	string	The status of the evaluation run.	Yes

OpenAI.EvalRunOutputItemList

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

Name	Type	Description	Required	Default
data	array of OpenAI.EvalRunOutputItem	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 is always set to “list”. Possible values: list	Yes

OpenAI.EvalRunOutputItemResult

A single grader result for an evaluation run output item.

Name	Type	Description	Required	Default
name	string	The name of the grader.	Yes
passed	boolean	Whether the grader considered the output a pass.	Yes
sample	object or null	Optional sample or intermediate data produced by the grader.	No
score	number	The numeric score produced by the grader.	Yes
type	string	The grader type (for example, “string-check-grader”).	No

OpenAI.EvalRunOutputItemSample

Name	Type	Description	Required	Default
error	OpenAI.EvalApiError	An object representing an error response from the Eval API.	Yes
finish_reason	string		Yes
input	array of OpenAI.EvalRunOutputItemSampleInput		Yes
max_completion_tokens	integer		Yes
model	string		Yes
output	array of OpenAI.EvalRunOutputItemSampleOutput		Yes
seed	integer		Yes
temperature	number		Yes
top_p	number		Yes
usage	OpenAI.EvalRunOutputItemSampleUsage		Yes

OpenAI.EvalRunOutputItemSampleInput

Name	Type	Description	Required	Default
content	string		Yes
role	string		Yes

OpenAI.EvalRunOutputItemSampleOutput

Name	Type	Description	Required	Default
content	string		No
role	string		No

OpenAI.EvalRunOutputItemSampleUsage

Name	Type	Description	Required	Default
cached_tokens	integer		Yes
completion_tokens	integer		Yes
prompt_tokens	integer		Yes
total_tokens	integer		Yes

OpenAI.EvalRunPerModelUsage

Name	Type	Description	Required	Default
cached_tokens	integer		Yes
completion_tokens	integer		Yes
invocation_count	integer		Yes
model_name	string		Yes
prompt_tokens	integer		Yes
total_tokens	integer		Yes

OpenAI.EvalRunPerTestingCriteriaResults

Name	Type	Description	Required	Default
failed	integer		Yes
passed	integer		Yes
testing_criteria	string		Yes

OpenAI.EvalRunResultCounts

Name	Type	Description	Required	Default
errored	integer		Yes
failed	integer		Yes
passed	integer		Yes
total	integer		Yes

OpenAI.EvalStoredCompletionsDataSourceConfig

Deprecated in favor of LogsDataSourceConfig.

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		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

OpenAI.EvalStoredCompletionsSource

A StoredCompletionsRunDataSource configuration describing a set of filters

Name	Type	Description	Required	Default
created_after	integer or null		No
created_before	integer or null		No
limit	integer or null		No
metadata	OpenAI.Metadata or null		No
model	string or null		No
type	enum	The type of source. Always stored_completions. Possible values: stored_completions	Yes

OpenAI.FileCitationBody

A citation to a file.

Name	Type	Description	Required	Default
file_id	string	The ID of the file.	Yes
filename	string	The filename of the file cited.	Yes
index	integer	The index of the file in the list of files.	Yes
type	enum	The type of the file citation. Always file_citation. Possible values: file_citation	Yes

OpenAI.FilePath

A path to a file.

Name	Type	Description	Required	Default
file_id	string	The ID of the file.	Yes
index	integer	The index of the file in the list of files.	Yes
type	enum	The type of the file path. Always file_path. Possible values: file_path	Yes

OpenAI.FileSearchRanker

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

Property	Value
Type	string
Values	auto default_2024_08_21

OpenAI.FileSearchRankingOptions

The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0. See the file search tool documentation for more information.

Name	Type	Description	Required	Default
ranker	OpenAI.FileSearchRanker	The ranker to use for the file search. If not specified will use the auto ranker.	No
score_threshold	number	The score threshold for the file search. All values must be a floating point number between 0 and 1. Constraints: min: 0, max: 1	Yes

OpenAI.FileSearchTool

A tool that searches for relevant content from uploaded files.

Name	Type	Description	Required	Default
filters	OpenAI.Filters or null		No
max_num_results	integer	The maximum number of results to return. This number should be between 1 and 50 inclusive.	No
ranking_options	OpenAI.RankingOptions		No
└─ hybrid_search	OpenAI.HybridSearchOptions	Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.	No
└─ ranker	OpenAI.RankerVersionType	The ranker to use for the file search.	No
└─ score_threshold	number	The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.	No
type	enum	The type of the file search tool. Always file_search. Possible values: file_search	Yes
vector_store_ids	array of string	The IDs of the vector stores to search.	Yes

OpenAI.FileSearchToolCallResults

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
file_id	string		No
filename	string		No
score	number		No
text	string		No

OpenAI.Filters

Type: OpenAI.ComparisonFilter or OpenAI.CompoundFilter

OpenAI.FineTuneDPOHyperparameters

The hyperparameters used for the DPO fine-tuning job.

Name	Type	Description	Required	Default
batch_size	string or integer	Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.	No
beta	string or number	The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.	No
learning_rate_multiplier	string or number	Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.	No
n_epochs	string or integer	The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.	No

OpenAI.FineTuneDPOMethod

Configuration for the DPO fine-tuning method.

Name	Type	Description	Required	Default
hyperparameters	OpenAI.FineTuneDPOHyperparameters	The hyperparameters used for the DPO fine-tuning job.	No

OpenAI.FineTuneMethod

The method used for fine-tuning.

Name	Type	Description	Required	Default
dpo	OpenAI.FineTuneDPOMethod	Configuration for the DPO fine-tuning method.	No
reinforcement	AzureFineTuneReinforcementMethod		No
supervised	OpenAI.FineTuneSupervisedMethod	Configuration for the supervised fine-tuning method.	No
type	enum	The type of method. Is either supervised, dpo, or reinforcement. Possible values: supervised, dpo, reinforcement	Yes

OpenAI.FineTuneReinforcementHyperparameters

The hyperparameters used for the reinforcement fine-tuning job.

Name	Type	Description	Required	Default
batch_size	string or integer	Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.	No
compute_multiplier	string or number	Multiplier on amount of compute used for exploring search space during training.	No
eval_interval	string or integer	The number of training steps between evaluation runs.	No
eval_samples	string or integer	Number of evaluation samples to generate per training step.	No
learning_rate_multiplier	string or number	Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.	No
n_epochs	string or integer	The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.	No
reasoning_effort	enum	Level of reasoning effort. Possible values: default, low, medium, high	No

OpenAI.FineTuneSupervisedHyperparameters

The hyperparameters used for the fine-tuning job.

Name	Type	Description	Required	Default
batch_size	string or integer	Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.	No
learning_rate_multiplier	string or number	Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.	No
n_epochs	string or integer	The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.	No

OpenAI.FineTuneSupervisedMethod

Configuration for the supervised fine-tuning method.

Name	Type	Description	Required	Default
hyperparameters	OpenAI.FineTuneSupervisedHyperparameters	The hyperparameters used for the fine-tuning job.	No

OpenAI.FineTuningCheckpointPermission

The checkpoint.permission object represents a permission for a fine-tuned model checkpoint.

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the permission was created.	Yes
id	string	The permission identifier, which can be referenced in the API endpoints.	Yes
object	enum	The object type, which is always “checkpoint.permission”. Possible values: checkpoint.permission	Yes
project_id	string	The project identifier that the permission is for.	Yes

OpenAI.FineTuningIntegration

Name	Type	Description	Required	Default
type	enum	The type of the integration being enabled for the fine-tuning job Possible values: wandb	Yes
wandb	OpenAI.FineTuningIntegrationWandb		Yes
└─ entity	string or null		No
└─ name	string or null		No
└─ project	string		Yes
└─ tags	array of string		No

OpenAI.FineTuningIntegrationWandb

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

OpenAI.FineTuningJob

The fine_tuning.job object represents a fine-tuning job that has been created through the API.

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the fine-tuning job was created.	Yes
error	OpenAI.FineTuningJobError or null		Yes
estimated_finish	string or null		No
fine_tuned_model	string or null		Yes
finished_at	string or null		Yes
hyperparameters	OpenAI.FineTuningJobHyperparameters		Yes
└─ batch_size	string or integer or null		No	auto
└─ learning_rate_multiplier	string or number		No
└─ n_epochs	string or integer		No	auto
id	string	The object identifier, which can be referenced in the API endpoints.	Yes
integrations	array of OpenAI.FineTuningIntegration or null		No
metadata	OpenAI.Metadata or null		No
method	OpenAI.FineTuneMethod	The method used for fine-tuning.	No
model	string	The base model that is being fine-tuned.	Yes
object	enum	The object type, which is always “fine_tuning.job”. Possible values: fine_tuning.job	Yes
organization_id	string	The organization that owns the fine-tuning job.	Yes
result_files	array of string	The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the Files API.	Yes
seed	integer	The seed used for the fine-tuning job.	Yes
status	enum	The current status of the fine-tuning job, which can be either validating_files, queued, running, succeeded, failed, or cancelled. Possible values: validating_files, queued, running, succeeded, failed, cancelled	Yes
trained_tokens	integer or null		Yes
training_file	string	The file ID used for training. You can retrieve the training data with the Files API.	Yes
validation_file	string or null		Yes

OpenAI.FineTuningJobCheckpoint

The fine_tuning.job.checkpoint object represents a model checkpoint for a fine-tuning job that is ready to use.

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 checkpoint identifier, which can be referenced in the API endpoints.	Yes
metrics	OpenAI.FineTuningJobCheckpointMetrics		Yes
└─ full_valid_loss	number		No
└─ full_valid_mean_token_accuracy	number		No
└─ step	number		No
└─ train_loss	number		No
└─ train_mean_token_accuracy	number		No
└─ valid_loss	number		No
└─ valid_mean_token_accuracy	number		No
object	enum	The object type, which is always “fine_tuning.job.checkpoint”. Possible values: fine_tuning.job.checkpoint	Yes
step_number	integer	The step number that the checkpoint was created at.	Yes

OpenAI.FineTuningJobCheckpointMetrics

Name	Type	Description	Required	Default
full_valid_loss	number		No
full_valid_mean_token_accuracy	number		No
step	number		No
train_loss	number		No
train_mean_token_accuracy	number		No
valid_loss	number		No
valid_mean_token_accuracy	number		No

OpenAI.FineTuningJobError

Name	Type	Description	Required	Default
code	string		Yes
message	string		Yes
param	string or null		Yes

OpenAI.FineTuningJobEvent

Fine-tuning job event object

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the fine-tuning job was created.	Yes
data	OpenAI.FineTuningJobEventData		No
id	string	The object identifier.	Yes
level	enum	The log level of the event. Possible values: info, warn, error	Yes
message	string	The message of the event.	Yes
object	enum	The object type, which is always “fine_tuning.job.event”. Possible values: fine_tuning.job.event	Yes
type	enum	The type of event. Possible values: message, metrics	No

OpenAI.FineTuningJobEventData

Type: object

OpenAI.FineTuningJobHyperparameters

Name	Type	Description	Required	Default
batch_size	string or integer or null		No
learning_rate_multiplier	string or number		No
n_epochs	string or integer		No

OpenAI.FunctionAndCustomToolCallOutput

Discriminator for OpenAI.FunctionAndCustomToolCallOutput

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

Type Value	Schema
input_text	OpenAI.FunctionAndCustomToolCallOutputInputTextContent
input_image	OpenAI.FunctionAndCustomToolCallOutputInputImageContent
input_file	OpenAI.FunctionAndCustomToolCallOutputInputFileContent

Name	Type	Description	Required	Default
type	OpenAI.FunctionAndCustomToolCallOutputType		Yes

OpenAI.FunctionAndCustomToolCallOutputInputFileContent

A file input to the model.

Name	Type	Description	Required	Default
file_data	string	The content of the file to be sent to the model.	No
file_id	string or null		No
file_url	string	The URL of the file to be sent to the model.	No
filename	string	The name of the file to be sent to the model.	No
type	enum	The type of the input item. Always input_file. Possible values: input_file	Yes

OpenAI.FunctionAndCustomToolCallOutputInputImageContent

An image input to the model. Learn about image inputs.

Name	Type	Description	Required	Default
detail	OpenAI.ImageDetail		Yes
file_id	string or null		No
image_url	string or null		No
type	enum	The type of the input item. Always input_image. Possible values: input_image	Yes

OpenAI.FunctionAndCustomToolCallOutputInputTextContent

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

OpenAI.FunctionAndCustomToolCallOutputType

Property	Value
Type	string
Values	input_text input_image input_file

OpenAI.FunctionObject

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. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.	Yes
parameters	OpenAI.FunctionParameters	The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.	No
strict	boolean or null		No

OpenAI.FunctionParameters

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

Type: object

OpenAI.FunctionShellAction

Execute a shell command.

Name	Type	Description	Required	Default
commands	array of string		Yes
max_output_length	integer or null		Yes
timeout_ms	integer or null		Yes

OpenAI.FunctionShellCallOutputContent

The content of a shell tool call output that was emitted.

Name	Type	Description	Required	Default
created_by	string	The identifier of the actor that created the item.	No
outcome	OpenAI.FunctionShellCallOutputOutcome	Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.	Yes
└─ type	OpenAI.FunctionShellCallOutputOutcomeType		Yes
stderr	string	The standard error output that was captured.	Yes
stdout	string	The standard output that was captured.	Yes

OpenAI.FunctionShellCallOutputExitOutcome

Indicates that the shell commands finished and returned an exit code.

Name	Type	Description	Required	Default
exit_code	integer	Exit code from the shell process.	Yes
type	enum	The outcome type. Always exit. Possible values: exit	Yes

OpenAI.FunctionShellCallOutputOutcome

Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.

Discriminator for OpenAI.FunctionShellCallOutputOutcome

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

Type Value	Schema
timeout	OpenAI.FunctionShellCallOutputTimeoutOutcome
exit	OpenAI.FunctionShellCallOutputExitOutcome

Name	Type	Description	Required	Default
type	OpenAI.FunctionShellCallOutputOutcomeType		Yes

OpenAI.FunctionShellCallOutputOutcomeType

Property	Value
Type	string
Values	timeout exit

OpenAI.FunctionShellCallOutputTimeoutOutcome

Indicates that the shell call exceeded its configured time limit.

Name	Type	Description	Required	Default
type	enum	The outcome type. Always timeout. Possible values: timeout	Yes

OpenAI.FunctionShellToolParam

A tool that allows the model to execute shell commands.

Name	Type	Description	Required	Default
type	enum	The type of the shell tool. Always shell. Possible values: shell	Yes

OpenAI.FunctionTool

Defines a function in your own code the model can choose to call.

Name	Type	Description	Required	Default
description	string or null		No
name	string	The name of the function to call.	Yes
parameters	object or null		Yes
strict	boolean or null		Yes
type	enum	The type of the function tool. Always function. Possible values: function	Yes

OpenAI.GraderMulti

A MultiGrader object combines the output of multiple graders to produce a single score.

Name	Type	Description	Required	Default
calculate_output	string	A formula to calculate the output based on grader results.	Yes
graders	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderScoreModel or GraderEndpoint		Yes
name	string	The name of the grader.	Yes
type	enum	The object type, which is always multi. Possible values: multi	Yes

OpenAI.GraderPython

A PythonGrader object that runs a python script on the input.

Name	Type	Description	Required	Default
image_tag	string	The image tag to use for the python script.	No
name	string	The name of the grader.	Yes
source	string	The source code of the python script.	Yes
type	enum	The object type, which is always python. Possible values: python	Yes

OpenAI.GraderScoreModel

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

Name	Type	Description	Required	Default
input	array of OpenAI.EvalItem	The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.	Yes
model	string	The model to use for the evaluation.	Yes
name	string	The name of the grader.	Yes
range	array of number	The range of the score. Defaults to [0, 1].	No
sampling_params	OpenAI.EvalGraderScoreModelSamplingParams		No
└─ max_completions_tokens	integer or null		No
└─ reasoning_effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
└─ seed	integer or null		No
└─ temperature	number or null		No
└─ top_p	number or null		No	1
type	enum	The object type, which is always score_model. Possible values: score_model	Yes

OpenAI.GraderStringCheck

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

OpenAI.GraderTextSimilarity

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 cosine, fuzzy_match, bleu, gleu, meteor, rouge_1, rouge_2, rouge_3, rouge_4, rouge_5, or rouge_l. Possible values: cosine, 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.	Yes
reference	string	The text being graded against.	Yes
type	enum	The type of grader. Possible values: text_similarity	Yes

OpenAI.GrammarSyntax1

Property	Value
Type	string
Values	lark regex

OpenAI.HybridSearchOptions

Name	Type	Description	Required	Default
embedding_weight	number	The weight of the embedding in the reciprocal ranking fusion.	Yes
text_weight	number	The weight of the text in the reciprocal ranking fusion.	Yes

OpenAI.ImageDetail

Property	Value
Type	string
Values	low high auto

OpenAI.ImageGenTool

A tool that generates images using the GPT image models.

Valid models:

gpt-image-1
gpt-image-1-mini
gpt-image-2

Name	Type	Description	Required	Default
background	enum	Background type for the generated image. One of transparent, opaque, or auto. Default: auto. Possible values: transparent, opaque, auto	No
input_fidelity	OpenAI.InputFidelity or null		No
input_image_mask	OpenAI.ImageGenToolInputImageMask		No
└─ file_id	string		No
└─ image_url	string		No
model	string (see valid models below)		No
moderation	enum	Moderation level for the generated image. Default: auto. Possible values: auto, low	No
output_compression	integer	Compression level for the output image. Default: 100. Constraints: min: 0, max: 100	No	100
output_format	enum	The output format of the generated image. One of png, webp, or jpeg. Default: png. Possible values: png, webp, jpeg	No
partial_images	integer	Number of partial images to generate in streaming mode, from 0 (default value) to 3. Constraints: min: 0, max: 3	No
quality	enum	The quality of the generated image. One of low, medium, high, or auto. Default: auto. Possible values: low, medium, high, auto	No
size	enum	The size of the generated image. One of 1024x1024, 1024x1536, 1536x1024, or auto. Default: auto. Possible values: 1024x1024, 1024x1536, 1536x1024, auto	No
type	enum	The type of the image generation tool. Always image_generation. Possible values: image_generation	Yes

OpenAI.ImageGenToolInputImageMask

Name	Type	Description	Required	Default
file_id	string		No
image_url	string		No

OpenAI.IncludeEnum

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

• web_search_call.action.sources: Include the sources of the web search tool call.
• code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
• computer_call_output.output.image_url: Include image urls from the computer call output.
• file_search_call.results: Include the search results of the file search tool call.
• message.input_image.image_url: Include image urls from the input message.
• message.output_text.logprobs: Include logprobs with assistant messages.
• reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).

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

• web_search_call.action.sources: Include the sources of the web search tool call.
• code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
• computer_call_output.output.image_url: Include image urls from the computer call output.
• file_search_call.results: Include the search results of the file search tool call.
• message.input_image.image_url: Include image urls from the input message.
• message.output_text.logprobs: Include logprobs with assistant messages.
• reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program). | | Type | string | | Values | file_search_call.results
web_search_call.results
web_search_call.action.sources
message.input_image.image_url
computer_call_output.output.image_url
code_interpreter_call.outputs
reasoning.encrypted_content
message.output_text.logprobs |

OpenAI.InputAudio

An audio input to the model.

Name	Type	Description	Required	Default
input_audio	OpenAI.InputAudioInputAudio		Yes
type	enum	The type of the input item. Always input_audio. Possible values: input_audio	Yes

OpenAI.InputAudioInputAudio

Name	Type	Description	Required	Default
data	string		Yes
format	enum	Possible values: mp3, wav	Yes

OpenAI.InputContent

Discriminator for OpenAI.InputContent

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

Type Value	Schema
input_text	OpenAI.InputContentInputTextContent
input_image	OpenAI.InputContentInputImageContent
input_file	OpenAI.InputContentInputFileContent

Name	Type	Description	Required	Default
type	OpenAI.InputContentType		Yes

OpenAI.InputContentInputFileContent

A file input to the model.

Name	Type	Description	Required	Default
file_data	string	The content of the file to be sent to the model.	No
file_id	string or null		No
file_url	string	The URL of the file to be sent to the model.	No
filename	string	The name of the file to be sent to the model.	No
type	enum	The type of the input item. Always input_file. Possible values: input_file	Yes

OpenAI.InputContentInputImageContent

An image input to the model. Learn about image inputs.

Name	Type	Description	Required	Default
detail	OpenAI.ImageDetail		Yes
file_id	string or null		No
image_url	string or null		No
type	enum	The type of the input item. Always input_image. Possible values: input_image	Yes

OpenAI.InputContentInputTextContent

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

OpenAI.InputContentType

Property	Value
Type	string
Values	input_text input_image input_file

OpenAI.InputFidelity

Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-2. Unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.

Property	Value
Type	string
Values	high low

OpenAI.InputFileContent

A file input to the model.

Name	Type	Description	Required	Default
file_data	string	The content of the file to be sent to the model.	No
file_id	string or null		No
file_url	string	The URL of the file to be sent to the model.	No
filename	string	The name of the file to be sent to the model.	No
type	enum	The type of the input item. Always input_file. Possible values: input_file	Yes

OpenAI.InputImageContent

An image input to the model. Learn about image inputs.

Name	Type	Description	Required	Default
detail	OpenAI.ImageDetail		Yes
file_id	string or null		No
image_url	string or null		No
type	enum	The type of the input item. Always input_image. Possible values: input_image	Yes

OpenAI.InputItem

Discriminator for OpenAI.InputItem

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

Type Value	Schema
message	OpenAI.EasyInputMessage
item_reference	OpenAI.ItemReferenceParam

Name	Type	Description	Required	Default
type	OpenAI.InputItemType		Yes

OpenAI.InputItemType

Property	Value
Type	string
Values	message item_reference

OpenAI.InputMessageContentList

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

Array of: OpenAI.InputContent

OpenAI.InputMessageResource

Name	Type	Description	Required	Default
content	OpenAI.InputMessageContentList	A list of one or many input items to the model, containing different content types.	Yes
id	string	The unique ID of the message input.	Yes
role	enum	The role of the message input. One of user, system, or developer. Possible values: user, system, developer	Yes
status	enum	The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the message input. Always set to message. Possible values: message	Yes

OpenAI.InputParam

Text, image, or file inputs to the model, used to generate a response. Learn more:

• Text inputs and outputs
• Image inputs
• File inputs
• Conversation state
• Function calling

Type: string or array of OpenAI.InputItem

Text, image, or file inputs to the model, used to generate a response. Learn more:

• Text inputs and outputs
• Image inputs
• File inputs
• Conversation state
• Function calling

OpenAI.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

OpenAI.ItemReferenceParam

An internal identifier for an item to reference.

Name	Type	Description	Required	Default
id	string	The ID of the item to reference.	Yes
type	enum	The type of item to reference. Always item_reference. Possible values: item_reference	Yes

OpenAI.ItemResource

Content item used to generate a response.

Discriminator for OpenAI.ItemResource

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

Type Value	Schema
message	OpenAI.InputMessageResource
output_message	OpenAI.ItemResourceOutputMessage
file_search_call	OpenAI.ItemResourceFileSearchToolCall
computer_call	OpenAI.ItemResourceComputerToolCall
computer_call_output	OpenAI.ItemResourceComputerToolCallOutputResource
web_search_call	OpenAI.ItemResourceWebSearchToolCall
function_call	OpenAI.ItemResourceFunctionToolCallResource
function_call_output	OpenAI.ItemResourceFunctionToolCallOutputResource
image_generation_call	OpenAI.ItemResourceImageGenToolCall
code_interpreter_call	OpenAI.ItemResourceCodeInterpreterToolCall
local_shell_call	OpenAI.ItemResourceLocalShellToolCall
local_shell_call_output	OpenAI.ItemResourceLocalShellToolCallOutput
shell_call	OpenAI.ItemResourceFunctionShellCall
shell_call_output	OpenAI.ItemResourceFunctionShellCallOutput
apply_patch_call	OpenAI.ItemResourceApplyPatchToolCall
apply_patch_call_output	OpenAI.ItemResourceApplyPatchToolCallOutput
mcp_list_tools	OpenAI.ItemResourceMcpListTools
mcp_approval_request	OpenAI.ItemResourceMcpApprovalRequest
mcp_approval_response	OpenAI.ItemResourceMcpApprovalResponseResource
mcp_call	OpenAI.ItemResourceMcpToolCall

Name	Type	Description	Required	Default
type	OpenAI.ItemResourceType		Yes

OpenAI.ItemResourceApplyPatchToolCall

A tool call that applies file diffs by creating, deleting, or updating files.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the apply patch tool call. Populated when this item is returned via API.	Yes
operation	OpenAI.ApplyPatchFileOperation	One of the create_file, delete_file, or update_file operations applied via apply_patch.	Yes
└─ type	OpenAI.ApplyPatchFileOperationType		Yes
status	OpenAI.ApplyPatchCallStatus		Yes
type	enum	The type of the item. Always apply_patch_call. Possible values: apply_patch_call	Yes

OpenAI.ItemResourceApplyPatchToolCallOutput

The output emitted by an apply patch tool call.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call output.	No
id	string	The unique ID of the apply patch tool call output. Populated when this item is returned via API.	Yes
output	string or null		No
status	OpenAI.ApplyPatchCallOutputStatus		Yes
type	enum	The type of the item. Always apply_patch_call_output. Possible values: apply_patch_call_output	Yes

OpenAI.ItemResourceCodeInterpreterToolCall

A tool call to run code.

Name	Type	Description	Required	Default
code	string or null		Yes
container_id	string	The ID of the container used to run the code.	Yes
id	string	The unique ID of the code interpreter tool call.	Yes
outputs	array of OpenAI.CodeInterpreterOutputLogs or OpenAI.CodeInterpreterOutputImage or null		Yes
status	enum	The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed. Possible values: in_progress, completed, incomplete, interpreting, failed	Yes
type	enum	The type of the code interpreter tool call. Always code_interpreter_call. Possible values: code_interpreter_call	Yes

OpenAI.ItemResourceComputerToolCall

A tool call to a computer use tool. See the computer use guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.ComputerAction		Yes
call_id	string	An identifier used when responding to the tool call with output.	Yes
id	string	The unique ID of the computer call.	Yes
pending_safety_checks	array of OpenAI.ComputerCallSafetyCheckParam	The pending safety checks for the computer call.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the computer call. Always computer_call. Possible values: computer_call	Yes

OpenAI.ItemResourceComputerToolCallOutputResource

Name	Type	Description	Required	Default
acknowledged_safety_checks	array of OpenAI.ComputerCallSafetyCheckParam	The safety checks reported by the API that have been acknowledged by the developer.	No
call_id	string	The ID of the computer tool call that produced the output.	Yes
id	string	The ID of the computer tool call output.	No
output	OpenAI.ComputerScreenshotImage	A computer screenshot image used with the computer use tool.	Yes
status	enum	The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the computer tool call output. Always computer_call_output. Possible values: computer_call_output	Yes

OpenAI.ItemResourceFileSearchToolCall

The results of a file search tool call. See the file search guide for more information.

Name	Type	Description	Required	Default
id	string	The unique ID of the file search tool call.	Yes
queries	array of string	The queries used to search for files.	Yes
results	array of OpenAI.FileSearchToolCallResults or null		No
status	enum	The status of the file search tool call. One of in_progress, searching, incomplete or failed, Possible values: in_progress, searching, completed, incomplete, failed	Yes
type	enum	The type of the file search tool call. Always file_search_call. Possible values: file_search_call	Yes

OpenAI.ItemResourceFunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Name	Type	Description	Required	Default
action	OpenAI.FunctionShellAction	Execute a shell command.	Yes
└─ commands	array of string		Yes
└─ max_output_length	integer or null		Yes
└─ timeout_ms	integer or null		Yes
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the shell tool call. Populated when this item is returned via API.	Yes
status	OpenAI.LocalShellCallStatus		Yes
type	enum	The type of the item. Always shell_call. Possible values: shell_call	Yes

OpenAI.ItemResourceFunctionShellCallOutput

The output of a shell tool call that was emitted.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The identifier of the actor that created the item.	No
id	string	The unique ID of the shell call output. Populated when this item is returned via API.	Yes
max_output_length	integer or null		Yes
output	array of OpenAI.FunctionShellCallOutputContent	An array of shell call output contents	Yes
type	enum	The type of the shell call output. Always shell_call_output. Possible values: shell_call_output	Yes

OpenAI.ItemResourceFunctionToolCallOutputResource

Name	Type	Description	Required	Default
call_id	string	The unique ID of the function tool call generated by the model.	Yes
id	string	The unique ID of the function tool call output. Populated when this item is returned via API.	No
output	string or array of OpenAI.FunctionAndCustomToolCallOutput	The output from the function call generated by your code. Can be a string or a list of output content.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the function tool call output. Always function_call_output. Possible values: function_call_output	Yes

OpenAI.ItemResourceFunctionToolCallResource

Name	Type	Description	Required	Default
arguments	string	A JSON string of the arguments to pass to the function.	Yes
call_id	string	The unique ID of the function tool call generated by the model.	Yes
id	string	The unique ID of the function tool call.	No
name	string	The name of the function to run.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the function tool call. Always function_call. Possible values: function_call	Yes

OpenAI.ItemResourceImageGenToolCall

An image generation request made by the model.

Name	Type	Description	Required	Default
id	string	The unique ID of the image generation call.	Yes
result	string or null		Yes
status	enum	The status of the image generation call. Possible values: in_progress, completed, generating, failed	Yes
type	enum	The type of the image generation call. Always image_generation_call. Possible values: image_generation_call	Yes

OpenAI.ItemResourceLocalShellToolCall

A tool call to run a command on the local shell.

Name	Type	Description	Required	Default
action	OpenAI.LocalShellExecAction	Execute a shell command on the server.	Yes
call_id	string	The unique ID of the local shell tool call generated by the model.	Yes
id	string	The unique ID of the local shell call.	Yes
status	enum	The status of the local shell call. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the local shell call. Always local_shell_call. Possible values: local_shell_call	Yes

OpenAI.ItemResourceLocalShellToolCallOutput

The output of a local shell tool call.

Name	Type	Description	Required	Default
id	string	The unique ID of the local shell tool call generated by the model.	Yes
output	string	A JSON string of the output of the local shell tool call.	Yes
status	string or null		No
type	enum	The type of the local shell tool call output. Always local_shell_call_output. Possible values: local_shell_call_output	Yes

OpenAI.ItemResourceMcpApprovalRequest

A request for human approval of a tool invocation.

Name	Type	Description	Required	Default
arguments	string	A JSON string of arguments for the tool.	Yes
id	string	The unique ID of the approval request.	Yes
name	string	The name of the tool to run.	Yes
server_label	string	The label of the MCP server making the request.	Yes
type	enum	The type of the item. Always mcp_approval_request. Possible values: mcp_approval_request	Yes

OpenAI.ItemResourceMcpApprovalResponseResource

A response to an MCP approval request.

Name	Type	Description	Required	Default
approval_request_id	string	The ID of the approval request being answered.	Yes
approve	boolean	Whether the request was approved.	Yes
id	string	The unique ID of the approval response	Yes
reason	string or null		No
type	enum	The type of the item. Always mcp_approval_response. Possible values: mcp_approval_response	Yes

OpenAI.ItemResourceMcpListTools

A list of tools available on an MCP server.

Name	Type	Description	Required	Default
error	string or null		No
id	string	The unique ID of the list.	Yes
server_label	string	The label of the MCP server.	Yes
tools	array of OpenAI.MCPListToolsTool	The tools available on the server.	Yes
type	enum	The type of the item. Always mcp_list_tools. Possible values: mcp_list_tools	Yes

OpenAI.ItemResourceMcpToolCall

An invocation of a tool on an MCP server.

Name	Type	Description	Required	Default
approval_request_id	string or null		No
arguments	string	A JSON string of the arguments passed to the tool.	Yes
error	string or null		No
id	string	The unique ID of the tool call.	Yes
name	string	The name of the tool that was run.	Yes
output	string or null		No
server_label	string	The label of the MCP server running the tool.	Yes
status	OpenAI.MCPToolCallStatus		No
type	enum	The type of the item. Always mcp_call. Possible values: mcp_call	Yes

OpenAI.ItemResourceOutputMessage

An output message from the model.

Name	Type	Description	Required	Default
content	array of OpenAI.OutputMessageContent	The content of the output message.	Yes
id	string	The unique ID of the output message.	Yes
role	enum	The role of the output message. Always assistant. Possible values: assistant	Yes
status	enum	The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the output message. Always message. Possible values: output_message	Yes

OpenAI.ItemResourceType

Property	Value
Type	string
Values	message output_message file_search_call computer_call computer_call_output web_search_call function_call function_call_output image_generation_call code_interpreter_call local_shell_call local_shell_call_output shell_call shell_call_output apply_patch_call apply_patch_call_output mcp_list_tools mcp_approval_request mcp_approval_response mcp_call

OpenAI.ItemResourceWebSearchToolCall

The results of a web search tool call. See the web search guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.WebSearchActionSearch or OpenAI.WebSearchActionOpenPage or OpenAI.WebSearchActionFind	An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find).	Yes
id	string	The unique ID of the web search tool call.	Yes
status	enum	The status of the web search tool call. Possible values: in_progress, searching, completed, failed	Yes
type	enum	The type of the web search tool call. Always web_search_call. Possible values: web_search_call	Yes

OpenAI.KeyPressAction

A collection of keypresses the model would like to perform.

Name	Type	Description	Required	Default
keys	array of string	The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.	Yes
type	enum	Specifies the event type. For a keypress action, this property is always set to keypress. Possible values: keypress	Yes

OpenAI.ListBatchesResponse

Name	Type	Description	Required	Default
data	array of OpenAI.Batch		Yes
first_id	string		No
has_more	boolean		Yes
last_id	string		No
object	enum	Possible values: list	Yes

OpenAI.ListFilesResponse

Name	Type	Description	Required	Default
data	array of OpenAI.OpenAIFile		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.ListFineTuningCheckpointPermissionResponse

Name	Type	Description	Required	Default
data	array of OpenAI.FineTuningCheckpointPermission		Yes
first_id	string or null		No
has_more	boolean		Yes
last_id	string or null		No
object	enum	Possible values: list	Yes

OpenAI.ListFineTuningJobCheckpointsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.FineTuningJobCheckpoint		Yes
first_id	string or null		No
has_more	boolean		Yes
last_id	string or null		No
object	enum	Possible values: list	Yes

OpenAI.ListFineTuningJobEventsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.FineTuningJobEvent		Yes
has_more	boolean		Yes
object	enum	Possible values: list	Yes

OpenAI.ListMessagesResponse

Name	Type	Description	Required	Default
data	array of OpenAI.MessageObject		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.ListModelsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.Model		Yes
object	enum	Possible values: list	Yes

OpenAI.ListPaginatedFineTuningJobsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.FineTuningJob		Yes
has_more	boolean		Yes
object	enum	Possible values: list	Yes

OpenAI.ListRunStepsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.RunStepObject		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.ListRunsResponse

Name	Type	Description	Required	Default
data	array of OpenAI.RunObject		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.ListVectorStoreFilesResponse

Name	Type	Description	Required	Default
data	array of OpenAI.VectorStoreFileObject		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.ListVectorStoresResponse

Name	Type	Description	Required	Default
data	array of OpenAI.VectorStoreObject		Yes
first_id	string		Yes
has_more	boolean		Yes
last_id	string		Yes
object	string		Yes

OpenAI.LocalShellCallStatus

Property	Value
Type	string
Values	in_progress completed incomplete

OpenAI.LocalShellExecAction

Execute a shell command on the server.

Name	Type	Description	Required	Default
command	array of string	The command to run.	Yes
env	object	Environment variables to set for the command.	Yes
timeout_ms	integer or null		No
type	enum	The type of the local shell action. Always exec. Possible values: exec	Yes
user	string or null		No
working_directory	string or null		No

OpenAI.LocalShellToolParam

A tool that allows the model to execute shell commands in a local environment.

Name	Type	Description	Required	Default
type	enum	The type of the local shell tool. Always local_shell. Possible values: local_shell	Yes

OpenAI.LogProb

The log probability of a token.

Name	Type	Description	Required	Default
bytes	array of integer		Yes
logprob	number		Yes
token	string		Yes
top_logprobs	array of OpenAI.TopLogProb		Yes

OpenAI.MCPListToolsTool

A tool available on an MCP server.

Name	Type	Description	Required	Default
annotations	OpenAI.MCPListToolsToolAnnotations or null		No
description	string or null		No
input_schema	OpenAI.MCPListToolsToolInputSchema		Yes
name	string	The name of the tool.	Yes

OpenAI.MCPListToolsToolAnnotations

Type: object

OpenAI.MCPListToolsToolInputSchema

Type: object

OpenAI.MCPTool

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

Name	Type	Description	Required	Default
allowed_tools	array of string or OpenAI.MCPToolFilter or null		No
authorization	string	An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.	No
connector_id	enum	Identifier for service connectors, like those available in ChatGPT. One of server_url or connector_id must be provided. Learn more about service connectors here. Currently supported connector_id values are: - Dropbox: connector_dropbox - Gmail: connector_gmail - Google Calendar: connector_googlecalendar - Google Drive: connector_googledrive - Microsoft Teams: connector_microsoftteams - Outlook Calendar: connector_outlookcalendar - Outlook Email: connector_outlookemail - SharePoint: connector_sharepoint Possible values: connector_dropbox, connector_gmail, connector_googlecalendar, connector_googledrive, connector_microsoftteams, connector_outlookcalendar, connector_outlookemail, connector_sharepoint	No
headers	object or null		No
require_approval	OpenAI.MCPToolRequireApproval or string or null		No
server_description	string	Optional description of the MCP server, used to provide more context.	No
server_label	string	A label for this MCP server, used to identify it in tool calls.	Yes
server_url	string	The URL for the MCP server. One of server_url or connector_id must be provided.	No
type	enum	The type of the MCP tool. Always mcp. Possible values: mcp	Yes

OpenAI.MCPToolCallStatus

Property	Value
Type	string
Values	in_progress completed incomplete calling failed

OpenAI.MCPToolFilter

A filter object to specify which tools are allowed.

Name	Type	Description	Required	Default
read_only	boolean	Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.	No
tool_names	array of string	List of allowed tool names.	No

OpenAI.MCPToolRequireApproval

Name	Type	Description	Required	Default
always	OpenAI.MCPToolFilter	A filter object to specify which tools are allowed.	No
never	OpenAI.MCPToolFilter	A filter object to specify which tools are allowed.	No

OpenAI.MessageContent

Discriminator for OpenAI.MessageContent

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

Type Value	Schema
image_url	OpenAI.MessageContentImageUrlObject
text	OpenAI.MessageContentTextObject
refusal	OpenAI.MessageContentRefusalObject

Name	Type	Description	Required	Default
type	OpenAI.MessageContentType		Yes

OpenAI.MessageContentImageFileObject

References an image File in the content of a message.

Name	Type	Description	Required	Default
image_file	OpenAI.MessageContentImageFileObjectImageFile		Yes
type	enum	Always image_file. Possible values: image_file	Yes

OpenAI.MessageContentImageFileObjectImageFile

Name	Type	Description	Required	Default
detail	enum	Possible values: auto, low, high	No
file_id	string		Yes

OpenAI.MessageContentImageUrlObject

References an image URL in the content of a message.

Name	Type	Description	Required	Default
image_url	OpenAI.MessageContentImageUrlObjectImageUrl		Yes
type	enum	The type of the content part. Possible values: image_url	Yes

OpenAI.MessageContentImageUrlObjectImageUrl

Name	Type	Description	Required	Default
detail	enum	Possible values: auto, low, high	No
url	string		Yes

OpenAI.MessageContentRefusalObject

The refusal content generated by the assistant.

Name	Type	Description	Required	Default
refusal	string		Yes
type	enum	Always refusal. Possible values: refusal	Yes

OpenAI.MessageContentTextAnnotationsFileCitationObject

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

Name	Type	Description	Required	Default
end_index	integer	Constraints: min: 0	Yes
file_citation	OpenAI.MessageContentTextAnnotationsFileCitationObjectFileCitation		Yes
start_index	integer	Constraints: min: 0	Yes
text	string	The text in the message content that needs to be replaced.	Yes
type	enum	Always file_citation. Possible values: file_citation	Yes

OpenAI.MessageContentTextAnnotationsFileCitationObjectFileCitation

Name	Type	Description	Required	Default
file_id	string		Yes

OpenAI.MessageContentTextAnnotationsFilePathObject

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

Name	Type	Description	Required	Default
end_index	integer	Constraints: min: 0	Yes
file_path	OpenAI.MessageContentTextAnnotationsFilePathObjectFilePath		Yes
start_index	integer	Constraints: min: 0	Yes
text	string	The text in the message content that needs to be replaced.	Yes
type	enum	Always file_path. Possible values: file_path	Yes

OpenAI.MessageContentTextAnnotationsFilePathObjectFilePath

Name	Type	Description	Required	Default
file_id	string		Yes

OpenAI.MessageContentTextObject

The text content that is part of a message.

Name	Type	Description	Required	Default
text	OpenAI.MessageContentTextObjectText		Yes
type	enum	Always text. Possible values: text	Yes

OpenAI.MessageContentTextObjectText

Name	Type	Description	Required	Default
annotations	array of OpenAI.TextAnnotation		Yes
value	string		Yes

OpenAI.MessageContentType

Property	Value
Type	string
Values	image_file image_url text refusal

OpenAI.MessageObject

Represents a message within a thread.

Name	Type	Description	Required	Default
assistant_id	string or null		Yes
attachments	array of OpenAI.MessageObjectAttachments or null		Yes
completed_at	string or null		Yes
content	array of OpenAI.MessageContent	The content of the message in array of text and/or images.	Yes
created_at	integer	The Unix timestamp (in seconds) for when the message was created.	Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
incomplete_at	string or null		Yes
incomplete_details	OpenAI.MessageObjectIncompleteDetails or null		Yes
metadata	OpenAI.Metadata or null		Yes
object	enum	The object type, which is always thread.message. Possible values: thread.message	Yes
role	enum	The entity that produced the message. One of user or assistant. Possible values: user, assistant	Yes
run_id	string or null		Yes
status	enum	The status of the message, which can be either in_progress, incomplete, or completed. Possible values: in_progress, incomplete, completed	Yes
thread_id	string	The thread ID that this message belongs to.	Yes

OpenAI.MessageObjectAttachments

Name	Type	Description	Required	Default
file_id	string		No
tools	array of OpenAI.AssistantToolsCode or OpenAI.AssistantToolsFileSearchTypeOnly		No

OpenAI.MessageObjectIncompleteDetails

Name	Type	Description	Required	Default
reason	enum	Possible values: content_filter, max_tokens, run_cancelled, run_expired, run_failed	Yes

OpenAI.MessageRequestContentTextObject

The text content that is part of a message.

Name	Type	Description	Required	Default
text	string	Text content to be sent to the model	Yes
type	enum	Always text. Possible values: text	Yes

OpenAI.MessageRole

Property	Value
Type	string
Values	unknown user assistant system critic discriminator developer tool

OpenAI.MessageStatus

Property	Value
Type	string
Values	in_progress completed incomplete

OpenAI.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.

Type: object

OpenAI.Model

Describes an OpenAI model offering that can be used with the API.

Name	Type	Description	Required	Default
created	integer	The Unix timestamp (in seconds) when the model was created.	Yes
id	string	The model identifier, which can be referenced in the API endpoints.	Yes
object	enum	The object type, which is always “model”. Possible values: model	Yes
owned_by	string	The organization that owns the model.	Yes

OpenAI.ModifyMessageRequest

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No

OpenAI.ModifyRunRequest

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No

OpenAI.ModifyThreadRequest

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null		No
tool_resources	OpenAI.ModifyThreadRequestToolResources or null		No

OpenAI.ModifyThreadRequestToolResources

Name	Type	Description	Required	Default
code_interpreter	OpenAI.ModifyThreadRequestToolResourcesCodeInterpreter		No
file_search	OpenAI.ModifyThreadRequestToolResourcesFileSearch		No

OpenAI.ModifyThreadRequestToolResourcesCodeInterpreter

Name	Type	Description	Required	Default
file_ids	array of string		No

OpenAI.ModifyThreadRequestToolResourcesFileSearch

Name	Type	Description	Required	Default
vector_store_ids	array of string		No

OpenAI.Move

A mouse move action.

Name	Type	Description	Required	Default
type	enum	Specifies the event type. For a move action, this property is always set to move. Possible values: move	Yes
x	integer	The x-coordinate to move to.	Yes
y	integer	The y-coordinate to move to.	Yes

OpenAI.NoiseReductionType

Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

Property	Value
Type	string
Values	near_field far_field

OpenAI.OpenAIFile

The File object represents a document that has been uploaded to OpenAI.

Name	Type	Description	Required	Default
bytes	integer	The size of the file, in bytes.	Yes
created_at	integer	The Unix timestamp (in seconds) for when the file was created.	Yes
expires_at	integer	The Unix timestamp (in seconds) for when the file will expire.	No
filename	string	The name of the file.	Yes
id	string	The file identifier, which can be referenced in the API endpoints.	Yes
object	enum	The object type, which is always file. Possible values: file	Yes
purpose	enum	The intended purpose of the file. Supported values are assistants, assistants_output, batch, batch_output, fine-tune and fine-tune-results. Possible values: assistants, assistants_output, batch, batch_output, fine-tune, fine-tune-results, evals	Yes
status	enum	Possible values: uploaded, pending, running, processed, error, deleting, deleted	Yes
status_details	string (deprecated)	Deprecated. For details on why a fine-tuning training file failed validation, see the error field on fine_tuning.job.	No

OpenAI.OtherChunkingStrategyResponseParam

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

Name	Type	Description	Required	Default
type	enum	Always other. Possible values: other	Yes

OpenAI.OutputContent

Discriminator for OpenAI.OutputContent

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

Type Value	Schema
output_text	OpenAI.OutputContentOutputTextContent
refusal	OpenAI.OutputContentRefusalContent

Name	Type	Description	Required	Default
type	OpenAI.OutputContentType		Yes

OpenAI.OutputContentOutputTextContent

A text output from the model.

Name	Type	Description	Required	Default
annotations	array of OpenAI.Annotation	The annotations of the text output.	Yes
logprobs	array of OpenAI.LogProb		No
text	string	The text output from the model.	Yes
type	enum	The type of the output text. Always output_text. Possible values: output_text	Yes

OpenAI.OutputContentRefusalContent

A refusal from the model.

Name	Type	Description	Required	Default
refusal	string	The refusal explanation from the model.	Yes
type	enum	The type of the refusal. Always refusal. Possible values: refusal	Yes

OpenAI.OutputContentType

Property	Value
Type	string
Values	output_text refusal reasoning_text

OpenAI.OutputItem

Discriminator for OpenAI.OutputItem

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

Type Value	Schema
output_message	OpenAI.OutputItemOutputMessage
file_search_call	OpenAI.OutputItemFileSearchToolCall
function_call	OpenAI.OutputItemFunctionToolCall
web_search_call	OpenAI.OutputItemWebSearchToolCall
computer_call	OpenAI.OutputItemComputerToolCall
reasoning	OpenAI.OutputItemReasoningItem
compaction	OpenAI.OutputItemCompactionBody
image_generation_call	OpenAI.OutputItemImageGenToolCall
code_interpreter_call	OpenAI.OutputItemCodeInterpreterToolCall
local_shell_call	OpenAI.OutputItemLocalShellToolCall
shell_call	OpenAI.OutputItemFunctionShellCall
shell_call_output	OpenAI.OutputItemFunctionShellCallOutput
apply_patch_call	OpenAI.OutputItemApplyPatchToolCall
apply_patch_call_output	OpenAI.OutputItemApplyPatchToolCallOutput
mcp_call	OpenAI.OutputItemMcpToolCall
mcp_list_tools	OpenAI.OutputItemMcpListTools
mcp_approval_request	OpenAI.OutputItemMcpApprovalRequest
custom_tool_call	OpenAI.OutputItemCustomToolCall

Name	Type	Description	Required	Default
type	OpenAI.OutputItemType		Yes

OpenAI.OutputItemApplyPatchToolCall

A tool call that applies file diffs by creating, deleting, or updating files.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the apply patch tool call. Populated when this item is returned via API.	Yes
operation	OpenAI.ApplyPatchFileOperation	One of the create_file, delete_file, or update_file operations applied via apply_patch.	Yes
└─ type	OpenAI.ApplyPatchFileOperationType		Yes
status	OpenAI.ApplyPatchCallStatus		Yes
type	enum	The type of the item. Always apply_patch_call. Possible values: apply_patch_call	Yes

OpenAI.OutputItemApplyPatchToolCallOutput

The output emitted by an apply patch tool call.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the apply patch tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call output.	No
id	string	The unique ID of the apply patch tool call output. Populated when this item is returned via API.	Yes
output	string or null		No
status	OpenAI.ApplyPatchCallOutputStatus		Yes
type	enum	The type of the item. Always apply_patch_call_output. Possible values: apply_patch_call_output	Yes

OpenAI.OutputItemCodeInterpreterToolCall

A tool call to run code.

Name	Type	Description	Required	Default
code	string or null		Yes
container_id	string	The ID of the container used to run the code.	Yes
id	string	The unique ID of the code interpreter tool call.	Yes
outputs	array of OpenAI.CodeInterpreterOutputLogs or OpenAI.CodeInterpreterOutputImage or null		Yes
status	enum	The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed. Possible values: in_progress, completed, incomplete, interpreting, failed	Yes
type	enum	The type of the code interpreter tool call. Always code_interpreter_call. Possible values: code_interpreter_call	Yes

OpenAI.OutputItemCompactionBody

A compaction item generated by the v1/responses/compact API.

Name	Type	Description	Required	Default
created_by	string	The identifier of the actor that created the item.	No
encrypted_content	string	The encrypted content that was produced by compaction.	Yes
id	string	The unique ID of the compaction item.	Yes
type	enum	The type of the item. Always compaction. Possible values: compaction	Yes

OpenAI.OutputItemComputerToolCall

A tool call to a computer use tool. See the computer use guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.ComputerAction		Yes
call_id	string	An identifier used when responding to the tool call with output.	Yes
id	string	The unique ID of the computer call.	Yes
pending_safety_checks	array of OpenAI.ComputerCallSafetyCheckParam	The pending safety checks for the computer call.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the computer call. Always computer_call. Possible values: computer_call	Yes

OpenAI.OutputItemCustomToolCall

A call to a custom tool created by the model.

Name	Type	Description	Required	Default
call_id	string	An identifier used to map this custom tool call to a tool call output.	Yes
id	string	The unique ID of the custom tool call in the OpenAI platform.	No
input	string	The input for the custom tool call generated by the model.	Yes
name	string	The name of the custom tool being called.	Yes
type	enum	The type of the custom tool call. Always custom_tool_call. Possible values: custom_tool_call	Yes

OpenAI.OutputItemFileSearchToolCall

The results of a file search tool call. See the file search guide for more information.

Name	Type	Description	Required	Default
id	string	The unique ID of the file search tool call.	Yes
queries	array of string	The queries used to search for files.	Yes
results	array of OpenAI.FileSearchToolCallResults or null		No
status	enum	The status of the file search tool call. One of in_progress, searching, incomplete or failed, Possible values: in_progress, searching, completed, incomplete, failed	Yes
type	enum	The type of the file search tool call. Always file_search_call. Possible values: file_search_call	Yes

OpenAI.OutputItemFunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Name	Type	Description	Required	Default
action	OpenAI.FunctionShellAction	Execute a shell command.	Yes
└─ commands	array of string		Yes
└─ max_output_length	integer or null		Yes
└─ timeout_ms	integer or null		Yes
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The ID of the entity that created this tool call.	No
id	string	The unique ID of the shell tool call. Populated when this item is returned via API.	Yes
status	OpenAI.LocalShellCallStatus		Yes
type	enum	The type of the item. Always shell_call. Possible values: shell_call	Yes

OpenAI.OutputItemFunctionShellCallOutput

The output of a shell tool call that was emitted.

Name	Type	Description	Required	Default
call_id	string	The unique ID of the shell tool call generated by the model.	Yes
created_by	string	The identifier of the actor that created the item.	No
id	string	The unique ID of the shell call output. Populated when this item is returned via API.	Yes
max_output_length	integer or null		Yes
output	array of OpenAI.FunctionShellCallOutputContent	An array of shell call output contents	Yes
type	enum	The type of the shell call output. Always shell_call_output. Possible values: shell_call_output	Yes

OpenAI.OutputItemFunctionToolCall

A tool call to run a function. See the function calling guide for more information.

Name	Type	Description	Required	Default
arguments	string	A JSON string of the arguments to pass to the function.	Yes
call_id	string	The unique ID of the function tool call generated by the model.	Yes
id	string	The unique ID of the function tool call.	No
name	string	The name of the function to run.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
type	enum	The type of the function tool call. Always function_call. Possible values: function_call	Yes

OpenAI.OutputItemImageGenToolCall

An image generation request made by the model.

Name	Type	Description	Required	Default
id	string	The unique ID of the image generation call.	Yes
result	string or null		Yes
status	enum	The status of the image generation call. Possible values: in_progress, completed, generating, failed	Yes
type	enum	The type of the image generation call. Always image_generation_call. Possible values: image_generation_call	Yes

OpenAI.OutputItemLocalShellToolCall

A tool call to run a command on the local shell.

Name	Type	Description	Required	Default
action	OpenAI.LocalShellExecAction	Execute a shell command on the server.	Yes
call_id	string	The unique ID of the local shell tool call generated by the model.	Yes
id	string	The unique ID of the local shell call.	Yes
status	enum	The status of the local shell call. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the local shell call. Always local_shell_call. Possible values: local_shell_call	Yes

OpenAI.OutputItemMcpApprovalRequest

A request for human approval of a tool invocation.

Name	Type	Description	Required	Default
arguments	string	A JSON string of arguments for the tool.	Yes
id	string	The unique ID of the approval request.	Yes
name	string	The name of the tool to run.	Yes
server_label	string	The label of the MCP server making the request.	Yes
type	enum	The type of the item. Always mcp_approval_request. Possible values: mcp_approval_request	Yes

OpenAI.OutputItemMcpListTools

A list of tools available on an MCP server.

Name	Type	Description	Required	Default
error	string or null		No
id	string	The unique ID of the list.	Yes
server_label	string	The label of the MCP server.	Yes
tools	array of OpenAI.MCPListToolsTool	The tools available on the server.	Yes
type	enum	The type of the item. Always mcp_list_tools. Possible values: mcp_list_tools	Yes

OpenAI.OutputItemMcpToolCall

An invocation of a tool on an MCP server.

Name	Type	Description	Required	Default
approval_request_id	string or null		No
arguments	string	A JSON string of the arguments passed to the tool.	Yes
error	string or null		No
id	string	The unique ID of the tool call.	Yes
name	string	The name of the tool that was run.	Yes
output	string or null		No
server_label	string	The label of the MCP server running the tool.	Yes
status	OpenAI.MCPToolCallStatus		No
type	enum	The type of the item. Always mcp_call. Possible values: mcp_call	Yes

OpenAI.OutputItemOutputMessage

An output message from the model.

Name	Type	Description	Required	Default
content	array of OpenAI.OutputMessageContent	The content of the output message.	Yes
id	string	The unique ID of the output message.	Yes
role	enum	The role of the output message. Always assistant. Possible values: assistant	Yes
status	enum	The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API. Possible values: in_progress, completed, incomplete	Yes
type	enum	The type of the output message. Always message. Possible values: output_message	Yes

OpenAI.OutputItemReasoningItem

A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

Name	Type	Description	Required	Default
content	array of OpenAI.ReasoningTextContent	Reasoning text content.	No
encrypted_content	string or null		No
id	string	The unique identifier of the reasoning content.	Yes
status	enum	The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API. Possible values: in_progress, completed, incomplete	No
summary	array of OpenAI.Summary	Reasoning summary content.	Yes
type	enum	The type of the object. Always reasoning. Possible values: reasoning	Yes

OpenAI.OutputItemType

Property	Value
Type	string
Values	output_message file_search_call function_call web_search_call computer_call reasoning compaction image_generation_call code_interpreter_call local_shell_call shell_call shell_call_output apply_patch_call apply_patch_call_output mcp_call mcp_list_tools mcp_approval_request custom_tool_call

OpenAI.OutputItemWebSearchToolCall

The results of a web search tool call. See the web search guide for more information.

Name	Type	Description	Required	Default
action	OpenAI.WebSearchActionSearch or OpenAI.WebSearchActionOpenPage or OpenAI.WebSearchActionFind	An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find).	Yes
id	string	The unique ID of the web search tool call.	Yes
status	enum	The status of the web search tool call. Possible values: in_progress, searching, completed, failed	Yes
type	enum	The type of the web search tool call. Always web_search_call. Possible values: web_search_call	Yes

OpenAI.OutputMessageContent

Discriminator for OpenAI.OutputMessageContent

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

Type Value	Schema
output_text	OpenAI.OutputMessageContentOutputTextContent
refusal	OpenAI.OutputMessageContentRefusalContent

Name	Type	Description	Required	Default
type	OpenAI.OutputMessageContentType		Yes

OpenAI.OutputMessageContentOutputTextContent

A text output from the model.

Name	Type	Description	Required	Default
annotations	array of OpenAI.Annotation	The annotations of the text output.	Yes
logprobs	array of OpenAI.LogProb		No
text	string	The text output from the model.	Yes
type	enum	The type of the output text. Always output_text. Possible values: output_text	Yes

OpenAI.OutputMessageContentRefusalContent

A refusal from the model.

Name	Type	Description	Required	Default
refusal	string	The refusal explanation from the model.	Yes
type	enum	The type of the refusal. Always refusal. Possible values: refusal	Yes

OpenAI.OutputMessageContentType

Property	Value
Type	string
Values	output_text refusal

OpenAI.OutputTextContent

A text output from the model.

Name	Type	Description	Required	Default
annotations	array of OpenAI.Annotation	The annotations of the text output.	Yes
logprobs	array of OpenAI.LogProb		No
text	string	The text output from the model.	Yes
type	enum	The type of the output text. Always output_text. Possible values: output_text	Yes

OpenAI.ParallelToolCalls

Whether to enable parallel function calling during tool use.

Type: boolean

OpenAI.PredictionContent

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

Name	Type	Description	Required	Default
content	string or array of OpenAI.ChatCompletionRequestMessageContentPartText	The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly.	Yes
type	enum	The type of the predicted content you want to provide. This type is currently always content. Possible values: content	Yes

OpenAI.Prompt

Reference to a prompt template and its variables. Learn more.

Name	Type	Description	Required	Default
id	string	The unique identifier of the prompt template to use.	Yes
variables	OpenAI.ResponsePromptVariables or null		No
version	string or null		No

OpenAI.RankerVersionType

Property	Value
Type	string
Values	auto default-2024-11-15

OpenAI.RankingOptions

Name	Type	Description	Required	Default
hybrid_search	OpenAI.HybridSearchOptions		No
└─ embedding_weight	number	The weight of the embedding in the reciprocal ranking fusion.	Yes
└─ text_weight	number	The weight of the text in the reciprocal ranking fusion.	Yes
ranker	OpenAI.RankerVersionType		No
score_threshold	number	The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.	No

OpenAI.RealtimeAudioFormats

Discriminator for OpenAI.RealtimeAudioFormats

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

Type Value	Schema
audio/pcm	OpenAI.RealtimeAudioFormatsAudioPcm
audio/pcmu	OpenAI.RealtimeAudioFormatsAudioPcmu
audio/pcma	OpenAI.RealtimeAudioFormatsAudioPcma

Name	Type	Description	Required	Default
type	OpenAI.RealtimeAudioFormatsType		Yes

OpenAI.RealtimeAudioFormatsAudioPcm

Name	Type	Description	Required	Default
rate	enum	Possible values: 24000	No
type	enum	Possible values: audio/pcm	Yes

OpenAI.RealtimeAudioFormatsAudioPcma

Name	Type	Description	Required	Default
type	enum	Possible values: audio/pcma	Yes

OpenAI.RealtimeAudioFormatsAudioPcmu

Name	Type	Description	Required	Default
type	enum	Possible values: audio/pcmu	Yes

OpenAI.RealtimeAudioFormatsType

Property	Value
Type	string
Values	audio/pcm audio/pcmu audio/pcma

OpenAI.RealtimeCallCreateRequest

Name	Type	Description	Required	Default
sdp	string	WebRTC Session Description Protocol (SDP) offer generated by the caller.	Yes
session	OpenAI.RealtimeSessionCreateRequestGA	Realtime session object configuration.	No
└─ audio	OpenAI.RealtimeSessionCreateRequestGAAudio	Configuration for input and output audio.	No
└─ include	array of string	Additional fields to include in server outputs. item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.	No
└─ instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
└─ max_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
└─ model	string	The Realtime model used for this session.	No
└─ output_modalities	array of string	The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.	No	[‘audio’]
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ tool_choice	OpenAI.ToolChoiceOptions or OpenAI.ToolChoiceFunction or OpenAI.ToolChoiceMCP	How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.	No	auto
└─ tools	array of OpenAI.RealtimeFunctionTool or OpenAI.MCPTool	Tools available to the model.	No
└─ tracing	string or OpenAI.RealtimeSessionCreateRequestGATracing or null	"" Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No	auto
└─ truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
└─ type	enum	The type of session to create. Always realtime for the Realtime API. Possible values: realtime	Yes

OpenAI.RealtimeCallReferRequest

Parameters required to transfer a SIP call to a new destination using the Realtime API.

Name	Type	Description	Required	Default
target_uri	string	URI that should appear in the SIP Refer-To header. Supports values like tel:[phone] or sip:agent\@example.com.	Yes

OpenAI.RealtimeCallRejectRequest

Parameters used to decline an incoming SIP call handled by the Realtime API.

Name	Type	Description	Required	Default
status_code	integer	SIP response code to send back to the caller. Defaults to 603 (Decline) when omitted.	No

OpenAI.RealtimeCreateClientSecretRequest

Create a session and client secret for the Realtime API. The request can specify either a realtime or a transcription session configuration. Learn more about the Realtime API.

Name	Type	Description	Required	Default
expires_after	OpenAI.RealtimeCreateClientSecretRequestExpiresAfter		No
└─ anchor	enum	Possible values: created_at	No
└─ seconds	integer	Constraints: min: 10, max: 7200	No	600
session	OpenAI.RealtimeSessionCreateRequestUnion		No
└─ type	OpenAI.RealtimeSessionCreateRequestUnionType		Yes

OpenAI.RealtimeCreateClientSecretRequestExpiresAfter

Name	Type	Description	Required	Default
anchor	enum	Possible values: created_at	No
seconds	integer	Constraints: min: 10, max: 7200	No	600

OpenAI.RealtimeCreateClientSecretResponse

Response from creating a session and client secret for the Realtime API.

Name	Type	Description	Required	Default
expires_at	integer	Expiration timestamp for the client secret, in seconds since epoch.	Yes
session	OpenAI.RealtimeSessionCreateResponseUnion		Yes
└─ type	OpenAI.RealtimeSessionCreateResponseUnionType		Yes
value	string	The generated client secret value.	Yes

OpenAI.RealtimeFunctionTool

Name	Type	Description	Required	Default
description	string	The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).	No
name	string	The name of the function.	No
parameters	OpenAI.RealtimeFunctionToolParameters		No
type	enum	The type of the tool, i.e. function. Possible values: function	No

OpenAI.RealtimeFunctionToolParameters

Type: object

OpenAI.RealtimeSessionCreateRequest

A new Realtime session configuration, with an ephemeral key. Default TTL for keys is one minute.

Name	Type	Description	Required	Default
client_secret	OpenAI.RealtimeSessionCreateRequestClientSecret		Yes
└─ expires_at	integer		Yes
└─ value	string		Yes
input_audio_format	string	The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.	No
input_audio_transcription	OpenAI.RealtimeSessionCreateRequestInputAudioTranscription		No
└─ model	string		No
instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
max_response_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
modalities	array of string	The set of modalities the model can respond with. To disable audio, set this to [“text”].	No	[‘text’, ‘audio’]
output_audio_format	string	The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.	No
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
speed	number	The speed of the model’s spoken response. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. Constraints: min: 0.25, max: 1.5	No	1
temperature	number	Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.	No
tool_choice	string	How the model chooses tools. Options are auto, none, required, or specify a function.	No
tools	array of OpenAI.RealtimeSessionCreateRequestTools	Tools (functions) available to the model.	No
tracing	string or object	Configuration options for tracing. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No
truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
turn_detection	OpenAI.RealtimeSessionCreateRequestTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	string		No
type	enum	Possible values: realtime	Yes
voice	OpenAI.VoiceIdsShared		No

OpenAI.RealtimeSessionCreateRequestClientSecret

Name	Type	Description	Required	Default
expires_at	integer		Yes
value	string		Yes

OpenAI.RealtimeSessionCreateRequestGA

Realtime session object configuration.

Name	Type	Description	Required	Default
audio	OpenAI.RealtimeSessionCreateRequestGAAudio		No
└─ input	OpenAI.RealtimeSessionCreateRequestGAAudioInput		No
└─ output	OpenAI.RealtimeSessionCreateRequestGAAudioOutput		No
include	array of string	Additional fields to include in server outputs. item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.	No
instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
max_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
model	string	The Realtime model used for this session.	No
output_modalities	array of string	The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.	No	[‘audio’]
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
tool_choice	OpenAI.ToolChoiceOptions or OpenAI.ToolChoiceFunction or OpenAI.ToolChoiceMCP	How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.	No
tools	array of OpenAI.RealtimeFunctionTool or OpenAI.MCPTool	Tools available to the model.	No
tracing	string or OpenAI.RealtimeSessionCreateRequestGATracing or null	"" Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No
truncation	OpenAI.RealtimeTruncation	When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.	No
type	enum	The type of session to create. Always realtime for the Realtime API. Possible values: realtime	Yes

OpenAI.RealtimeSessionCreateRequestGAAudio

Name	Type	Description	Required	Default
input	OpenAI.RealtimeSessionCreateRequestGAAudioInput		No
output	OpenAI.RealtimeSessionCreateRequestGAAudioOutput		No

OpenAI.RealtimeSessionCreateRequestGAAudioInput

Name	Type	Description	Required	Default
format	OpenAI.RealtimeAudioFormats		No
noise_reduction	OpenAI.RealtimeSessionCreateRequestGAAudioInputNoiseReduction		No
transcription	OpenAI.AudioTranscription		No
turn_detection	OpenAI.RealtimeTurnDetection		No

OpenAI.RealtimeSessionCreateRequestGAAudioInputNoiseReduction

Name	Type	Description	Required	Default
type	OpenAI.NoiseReductionType	Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.	No

OpenAI.RealtimeSessionCreateRequestGAAudioOutput

Name	Type	Description	Required	Default
format	OpenAI.RealtimeAudioFormats		No
speed	number	Constraints: min: 0.25, max: 1.5	No	1
voice	OpenAI.VoiceIdsShared		No

OpenAI.RealtimeSessionCreateRequestGATracing

Name	Type	Description	Required	Default
group_id	string		No
metadata	object		No
workflow_name	string		No

OpenAI.RealtimeSessionCreateRequestInputAudioTranscription

Name	Type	Description	Required	Default
model	string		No

OpenAI.RealtimeSessionCreateRequestTools

Name	Type	Description	Required	Default
description	string		No
name	string		No
parameters	OpenAI.RealtimeSessionCreateRequestToolsParameters		No
type	enum	Possible values: function	No

OpenAI.RealtimeSessionCreateRequestToolsParameters

Type: object

OpenAI.RealtimeSessionCreateRequestTurnDetection

Name	Type	Description	Required	Default
prefix_padding_ms	integer		No
silence_duration_ms	integer		No
threshold	number		No
type	string		No

OpenAI.RealtimeSessionCreateRequestUnion

Discriminator for OpenAI.RealtimeSessionCreateRequestUnion

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

Type Value	Schema
realtime	OpenAI.RealtimeSessionCreateRequest
transcription	OpenAI.RealtimeTranscriptionSessionCreateRequest

Name	Type	Description	Required	Default
type	OpenAI.RealtimeSessionCreateRequestUnionType		Yes

OpenAI.RealtimeSessionCreateRequestUnionType

Property	Value
Type	string
Values	realtime transcription

OpenAI.RealtimeSessionCreateResponse

A Realtime session configuration object.

Name	Type	Description	Required	Default
audio	OpenAI.RealtimeSessionCreateResponseAudio		No
└─ input	OpenAI.RealtimeSessionCreateResponseAudioInput		No
└─ output	OpenAI.RealtimeSessionCreateResponseAudioOutput		No
expires_at	integer	Expiration timestamp for the session, in seconds since epoch.	No
id	string	Unique identifier for the session that looks like sess_1234567890abcdef.	No
include	array of string	Additional fields to include in server outputs. - item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.	No
instructions	string	The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (for example “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (for example “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.	No
max_output_tokens	integer (see valid models below)	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or inf for the maximum available tokens for a given model. Defaults to inf.	No
model	string	The Realtime model used for this session.	No
object	string	The object type. Always realtime.session.	No
output_modalities	array of string	The set of modalities the model can respond with. To disable audio, set this to [“text”].	No
tool_choice	string	How the model chooses tools. Options are auto, none, required, or specify a function.	No
tools	array of OpenAI.RealtimeFunctionTool	Tools (functions) available to the model.	No
tracing	string or object	Configuration options for tracing. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. auto will create a trace for the session with default values for the workflow name, group id, and metadata.	No
turn_detection	OpenAI.RealtimeSessionCreateResponseTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	string		No
type	enum	Possible values: realtime	Yes

OpenAI.RealtimeSessionCreateResponseAudio

Name	Type	Description	Required	Default
input	OpenAI.RealtimeSessionCreateResponseAudioInput		No
output	OpenAI.RealtimeSessionCreateResponseAudioOutput		No

OpenAI.RealtimeSessionCreateResponseAudioInput

Name	Type	Description	Required	Default
format	OpenAI.RealtimeAudioFormats		No
noise_reduction	OpenAI.RealtimeSessionCreateResponseAudioInputNoiseReduction		No
transcription	OpenAI.AudioTranscription		No
turn_detection	OpenAI.RealtimeSessionCreateResponseAudioInputTurnDetection		No

OpenAI.RealtimeSessionCreateResponseAudioInputNoiseReduction

Name	Type	Description	Required	Default
type	OpenAI.NoiseReductionType	Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.	No

OpenAI.RealtimeSessionCreateResponseAudioInputTurnDetection

Name	Type	Description	Required	Default
prefix_padding_ms	integer		No
silence_duration_ms	integer		No
threshold	number		No
type	string		No

OpenAI.RealtimeSessionCreateResponseAudioOutput

Name	Type	Description	Required	Default
format	OpenAI.RealtimeAudioFormats		No
speed	number		No
voice	OpenAI.VoiceIdsShared		No

OpenAI.RealtimeSessionCreateResponseTurnDetection

Name	Type	Description	Required	Default
prefix_padding_ms	integer		No
silence_duration_ms	integer		No
threshold	number		No
type	string		No

OpenAI.RealtimeSessionCreateResponseUnion

Discriminator for OpenAI.RealtimeSessionCreateResponseUnion

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

Type Value	Schema
realtime	OpenAI.RealtimeSessionCreateResponse
transcription	OpenAI.RealtimeTranscriptionSessionCreateResponse

Name	Type	Description	Required	Default
type	OpenAI.RealtimeSessionCreateResponseUnionType		Yes

OpenAI.RealtimeSessionCreateResponseUnionType

Property	Value
Type	string
Values	realtime transcription

OpenAI.RealtimeTranscriptionSessionCreateRequest

Realtime transcription session object configuration.

Name	Type	Description	Required	Default
include	array of string	The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs	No
input_audio_format	enum	The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24-kHz sample rate, single channel (mono), and little-endian byte order. Possible values: pcm16, g711_ulaw, g711_alaw	No
input_audio_noise_reduction	OpenAI.RealtimeTranscriptionSessionCreateRequestInputAudioNoiseReduction		No
└─ type	OpenAI.NoiseReductionType	Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.	No
input_audio_transcription	OpenAI.AudioTranscription		No
└─ language	string	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.	No
└─ model	string	The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.	No
└─ prompt	string	An optional text to guide the model’s style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example “expect words related to technology”.	No
turn_detection	OpenAI.RealtimeTranscriptionSessionCreateRequestTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	enum	Possible values: server_vad	No
type	enum	Possible values: transcription	Yes

OpenAI.RealtimeTranscriptionSessionCreateRequestInputAudioNoiseReduction

Name	Type	Description	Required	Default
type	OpenAI.NoiseReductionType	Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.	No

OpenAI.RealtimeTranscriptionSessionCreateRequestTurnDetection

Name	Type	Description	Required	Default
prefix_padding_ms	integer		No
silence_duration_ms	integer		No
threshold	number		No
type	enum	Possible values: server_vad	No

OpenAI.RealtimeTranscriptionSessionCreateResponse

A new Realtime transcription session configuration. When a session is created on the server via REST API, the session object also contains an ephemeral key. Default TTL for keys is 10 minutes. This property is not present when a session is updated via the WebSocket API.

Name	Type	Description	Required	Default
client_secret	OpenAI.RealtimeTranscriptionSessionCreateResponseClientSecret		Yes
└─ expires_at	integer		Yes
└─ value	string		Yes
input_audio_format	string	The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.	No
input_audio_transcription	OpenAI.AudioTranscription		No
└─ language	string	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.	No
└─ model	string	The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, and gpt-4o-transcribe-diarize. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.	No
└─ prompt	string	An optional text to guide the model’s style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example “expect words related to technology”.	No
modalities	array of string	The set of modalities the model can respond with. To disable audio, set this to [“text”].	No
turn_detection	OpenAI.RealtimeTranscriptionSessionCreateResponseTurnDetection		No
└─ prefix_padding_ms	integer		No
└─ silence_duration_ms	integer		No
└─ threshold	number		No
└─ type	string		No
type	enum	Possible values: transcription	Yes

OpenAI.RealtimeTranscriptionSessionCreateResponseClientSecret

Name	Type	Description	Required	Default
expires_at	integer		Yes
value	string		Yes

OpenAI.RealtimeTranscriptionSessionCreateResponseTurnDetection

Name	Type	Description	Required	Default
prefix_padding_ms	integer		No
silence_duration_ms	integer		No
threshold	number		No
type	string		No

OpenAI.RealtimeTruncation

When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.

Property	Value
Type	string
Values	auto disabled

OpenAI.RealtimeTurnDetection

Discriminator for OpenAI.RealtimeTurnDetection

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

Type Value	Schema

Name	Type	Description	Required	Default
type	OpenAI.RealtimeTurnDetectionType		Yes

OpenAI.RealtimeTurnDetectionType

Type: string

OpenAI.Reasoning

gpt-5 and o-series models only Configuration options for reasoning models.

Name	Type	Description	Required	Default
effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1. - All models before gpt-5.1 default to medium reasoning effort, and do not support none. - The gpt-5-pro model defaults to (and only supports) high reasoning effort. - xhigh is supported for all models after gpt-5.1-codex-max.	No
generate_summary	string or null		No
summary	string or null		No

OpenAI.ReasoningEffort

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

• gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
• All models before gpt-5.1 default to medium reasoning effort, and do not support none.
• The gpt-5-pro model defaults to (and only supports) high reasoning effort.
• xhigh is supported for all models after gpt-5.1-codex-max.

Property	Value
Type	string
Values	none minimal low medium high xhigh

OpenAI.ReasoningTextContent

Reasoning text from the model.

Name	Type	Description	Required	Default
text	string	The reasoning text from the model.	Yes
type	enum	The type of the reasoning text. Always reasoning_text. Possible values: reasoning_text	Yes

OpenAI.RefusalContent

A refusal from the model.

Name	Type	Description	Required	Default
refusal	string	The refusal explanation from the model.	Yes
type	enum	The type of the refusal. Always refusal. Possible values: refusal	Yes

OpenAI.Response

Name	Type	Description	Required	Default
background	boolean or null		No
completed_at	string or null		No
content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
conversation	OpenAI.ConversationReference or null		No
created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
error	OpenAI.ResponseError or null		Yes
id	string	Unique identifier for this Response.	Yes
incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
instructions	string or array of OpenAI.InputItem or null		Yes
max_output_tokens	integer or null		No
max_tool_calls	integer or null		No
metadata	OpenAI.Metadata or null		No
model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
object	enum	The object type of this resource - always set to response. Possible values: response	Yes
output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
output_text	string or null		No
parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
previous_response_id	string or null		No
prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
prompt_cache_retention	string or null		No
reasoning	OpenAI.Reasoning or null		No
safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
temperature	number or null		No
text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
top_logprobs	integer or null		No
top_p	number or null		No
truncation	string or null		No
usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No

OpenAI.ResponseAudioDeltaEvent

Emitted when there is a partial audio response.

Name	Type	Description	Required	Default
delta	string	A chunk of Base64 encoded response audio bytes.	Yes
sequence_number	integer	A sequence number for this chunk of the stream response.	Yes
type	enum	The type of the event. Always response.audio.delta. Possible values: response.audio.delta	Yes

OpenAI.ResponseAudioTranscriptDeltaEvent

Emitted when there is a partial transcript of audio.

Name	Type	Description	Required	Default
delta	string	The partial transcript of the audio response.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.audio.transcript.delta. Possible values: response.audio.transcript.delta	Yes

OpenAI.ResponseCodeInterpreterCallCodeDeltaEvent

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

Name	Type	Description	Required	Default
delta	string	The partial code snippet being streamed by the code interpreter.	Yes
item_id	string	The unique identifier of the code interpreter tool call item.	Yes
output_index	integer	The index of the output item in the response for which the code is being streamed.	Yes
sequence_number	integer	The sequence number of this event, used to order streaming events.	Yes
type	enum	The type of the event. Always response.code_interpreter_call_code.delta. Possible values: response.code_interpreter_call_code.delta	Yes

OpenAI.ResponseCodeInterpreterCallInProgressEvent

Emitted when a code interpreter call is in progress.

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the code interpreter tool call item.	Yes
output_index	integer	The index of the output item in the response for which the code interpreter call is in progress.	Yes
sequence_number	integer	The sequence number of this event, used to order streaming events.	Yes
type	enum	The type of the event. Always response.code_interpreter_call.in_progress. Possible values: response.code_interpreter_call.in_progress	Yes

OpenAI.ResponseCodeInterpreterCallInterpretingEvent

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

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the code interpreter tool call item.	Yes
output_index	integer	The index of the output item in the response for which the code interpreter is interpreting code.	Yes
sequence_number	integer	The sequence number of this event, used to order streaming events.	Yes
type	enum	The type of the event. Always response.code_interpreter_call.interpreting. Possible values: response.code_interpreter_call.interpreting	Yes

OpenAI.ResponseContentPartAddedEvent

Emitted when a new content part is added.

Name	Type	Description	Required	Default
content_index	integer	The index of the content part that was added.	Yes
item_id	string	The ID of the output item that the content part was added to.	Yes
output_index	integer	The index of the output item that the content part was added to.	Yes
part	OpenAI.OutputContent		Yes
└─ type	OpenAI.OutputContentType		Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.content_part.added. Possible values: response.content_part.added	Yes

OpenAI.ResponseCreatedEvent

An event that is emitted when a response is created.

Name	Type	Description	Required	Default
response	OpenAI.Response		Yes
└─ background	boolean or null		No
└─ completed_at	string or null		No
└─ content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
└─ conversation	OpenAI.ConversationReference or null		No
└─ created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
└─ error	OpenAI.ResponseError or null		Yes
└─ id	string	Unique identifier for this Response.	Yes
└─ incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
└─ instructions	string or array of OpenAI.InputItem or null		Yes
└─ max_output_tokens	integer or null		No
└─ max_tool_calls	integer or null		No
└─ metadata	OpenAI.Metadata or null		No
└─ model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
└─ object	enum	The object type of this resource - always set to response. Possible values: response	Yes
└─ output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
└─ output_text	string or null		No
└─ parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
└─ previous_response_id	string or null		No
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
└─ prompt_cache_retention	string or null		No
└─ reasoning	OpenAI.Reasoning or null		No
└─ safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
└─ status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
└─ temperature	number or null		No	1
└─ text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
└─ tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
└─ tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
└─ top_logprobs	integer or null		No
└─ top_p	number or null		No	1
└─ truncation	string or null		No	disabled
└─ usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
└─ user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No
sequence_number	integer	The sequence number for this event.	Yes
type	enum	The type of the event. Always response.created. Possible values: response.created	Yes

OpenAI.ResponseCustomToolCallInputDeltaEvent

Event representing a delta (partial update) to the input of a custom tool call.

Name	Type	Description	Required	Default
delta	string	The incremental input data (delta) for the custom tool call.	Yes
item_id	string	Unique identifier for the API item associated with this event.	Yes
output_index	integer	The index of the output this delta applies to.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The event type identifier. Possible values: response.custom_tool_call_input.delta	Yes

OpenAI.ResponseError

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

Name	Type	Description	Required	Default
code	OpenAI.ResponseErrorCode	The error code for the response.	Yes
message	string	A human-readable description of the error.	Yes

OpenAI.ResponseErrorCode

The error code for the response.

Property	Value
Type	string
Values	server_error rate_limit_exceeded invalid_prompt vector_store_timeout invalid_image invalid_image_format invalid_base64_image invalid_image_url image_too_large image_too_small image_parse_error image_content_policy_violation invalid_image_mode image_file_too_large unsupported_image_media_type empty_image_file failed_to_download_image image_file_not_found

OpenAI.ResponseErrorEvent

Emitted when an error occurs.

Name	Type	Description	Required	Default
code	string or null		Yes
message	string	The error message.	Yes
param	string or null		Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always error. Possible values: error	Yes

OpenAI.ResponseFailedEvent

An event that is emitted when a response fails.

Name	Type	Description	Required	Default
response	OpenAI.Response		Yes
└─ background	boolean or null		No
└─ completed_at	string or null		No
└─ content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
└─ conversation	OpenAI.ConversationReference or null		No
└─ created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
└─ error	OpenAI.ResponseError or null		Yes
└─ id	string	Unique identifier for this Response.	Yes
└─ incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
└─ instructions	string or array of OpenAI.InputItem or null		Yes
└─ max_output_tokens	integer or null		No
└─ max_tool_calls	integer or null		No
└─ metadata	OpenAI.Metadata or null		No
└─ model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
└─ object	enum	The object type of this resource - always set to response. Possible values: response	Yes
└─ output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
└─ output_text	string or null		No
└─ parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
└─ previous_response_id	string or null		No
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
└─ prompt_cache_retention	string or null		No
└─ reasoning	OpenAI.Reasoning or null		No
└─ safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
└─ status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
└─ temperature	number or null		No	1
└─ text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
└─ tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
└─ tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
└─ top_logprobs	integer or null		No
└─ top_p	number or null		No	1
└─ truncation	string or null		No	disabled
└─ usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
└─ user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.failed. Possible values: response.failed	Yes

OpenAI.ResponseFileSearchCallInProgressEvent

Emitted when a file search call is initiated.

Name	Type	Description	Required	Default
item_id	string	The ID of the output item that the file search call is initiated.	Yes
output_index	integer	The index of the output item that the file search call is initiated.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.file_search_call.in_progress. Possible values: response.file_search_call.in_progress	Yes

OpenAI.ResponseFileSearchCallSearchingEvent

Emitted when a file search is currently searching.

Name	Type	Description	Required	Default
item_id	string	The ID of the output item that the file search call is initiated.	Yes
output_index	integer	The index of the output item that the file search call is searching.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.file_search_call.searching. Possible values: response.file_search_call.searching	Yes

OpenAI.ResponseFormatJsonObject

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always json_object. Possible values: json_object	Yes

OpenAI.ResponseFormatJsonSchema

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

Name	Type	Description	Required	Default
json_schema	OpenAI.ResponseFormatJsonSchemaJsonSchema		Yes
└─ description	string		No
└─ name	string		Yes
└─ schema	OpenAI.ResponseFormatJsonSchemaSchema	The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.	No
└─ strict	boolean or null		No
type	enum	The type of response format being defined. Always json_schema. Possible values: json_schema	Yes

OpenAI.ResponseFormatJsonSchemaJsonSchema

Name	Type	Description	Required	Default
description	string		No
name	string		Yes
schema	OpenAI.ResponseFormatJsonSchemaSchema	The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.	No
strict	boolean or null		No

OpenAI.ResponseFormatJsonSchemaSchema

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

Type: object

OpenAI.ResponseFormatText

Default response format. Used to generate text responses.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always text. Possible values: text	Yes

OpenAI.ResponseFunctionCallArgumentsDeltaEvent

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

Name	Type	Description	Required	Default
delta	string	The function-call arguments delta that is added.	Yes
item_id	string	The ID of the output item that the function-call arguments delta is added to.	Yes
output_index	integer	The index of the output item that the function-call arguments delta is added to.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.function_call_arguments.delta. Possible values: response.function_call_arguments.delta	Yes

OpenAI.ResponseImageGenCallGeneratingEvent

Emitted when an image generation tool call is actively generating an image (intermediate state).

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the image generation item being processed.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
sequence_number	integer	The sequence number of the image generation item being processed.	Yes
type	enum	The type of the event. Always ‘response.image_generation_call.generating’. Possible values: response.image_generation_call.generating	Yes

OpenAI.ResponseImageGenCallInProgressEvent

Emitted when an image generation tool call is in progress.

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the image generation item being processed.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
sequence_number	integer	The sequence number of the image generation item being processed.	Yes
type	enum	The type of the event. Always ‘response.image_generation_call.in_progress’. Possible values: response.image_generation_call.in_progress	Yes

OpenAI.ResponseImageGenCallPartialImageEvent

Emitted when a partial image is available during image generation streaming.

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the image generation item being processed.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
partial_image_b64	string	Base64-encoded partial image data, suitable for rendering as an image.	Yes
partial_image_index	integer	0-based index for the partial image (backend is 1-based, but this is 0-based for the user).	Yes
sequence_number	integer	The sequence number of the image generation item being processed.	Yes
type	enum	The type of the event. Always ‘response.image_generation_call.partial_image’. Possible values: response.image_generation_call.partial_image	Yes

OpenAI.ResponseInProgressEvent

Emitted when the response is in progress.

Name	Type	Description	Required	Default
response	OpenAI.Response		Yes
└─ background	boolean or null		No
└─ completed_at	string or null		No
└─ content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
└─ conversation	OpenAI.ConversationReference or null		No
└─ created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
└─ error	OpenAI.ResponseError or null		Yes
└─ id	string	Unique identifier for this Response.	Yes
└─ incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
└─ instructions	string or array of OpenAI.InputItem or null		Yes
└─ max_output_tokens	integer or null		No
└─ max_tool_calls	integer or null		No
└─ metadata	OpenAI.Metadata or null		No
└─ model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
└─ object	enum	The object type of this resource - always set to response. Possible values: response	Yes
└─ output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
└─ output_text	string or null		No
└─ parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
└─ previous_response_id	string or null		No
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
└─ prompt_cache_retention	string or null		No
└─ reasoning	OpenAI.Reasoning or null		No
└─ safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
└─ status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
└─ temperature	number or null		No	1
└─ text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
└─ tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
└─ tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
└─ top_logprobs	integer or null		No
└─ top_p	number or null		No	1
└─ truncation	string or null		No	disabled
└─ usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
└─ user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.in_progress. Possible values: response.in_progress	Yes

OpenAI.ResponseIncompleteDetails

Name	Type	Description	Required	Default
reason	enum	Possible values: max_output_tokens, content_filter	No

OpenAI.ResponseIncompleteEvent

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

Name	Type	Description	Required	Default
response	OpenAI.Response		Yes
└─ background	boolean or null		No
└─ completed_at	string or null		No
└─ content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
└─ conversation	OpenAI.ConversationReference or null		No
└─ created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
└─ error	OpenAI.ResponseError or null		Yes
└─ id	string	Unique identifier for this Response.	Yes
└─ incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
└─ instructions	string or array of OpenAI.InputItem or null		Yes
└─ max_output_tokens	integer or null		No
└─ max_tool_calls	integer or null		No
└─ metadata	OpenAI.Metadata or null		No
└─ model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
└─ object	enum	The object type of this resource - always set to response. Possible values: response	Yes
└─ output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
└─ output_text	string or null		No
└─ parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
└─ previous_response_id	string or null		No
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
└─ prompt_cache_retention	string or null		No
└─ reasoning	OpenAI.Reasoning or null		No
└─ safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
└─ status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
└─ temperature	number or null		No	1
└─ text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
└─ tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
└─ tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
└─ top_logprobs	integer or null		No
└─ top_p	number or null		No	1
└─ truncation	string or null		No	disabled
└─ usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
└─ user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.incomplete. Possible values: response.incomplete	Yes

OpenAI.ResponseItemList

A list of Response items.

Name	Type	Description	Required	Default
data	array of OpenAI.ItemResource	A list of items used to generate this response.	Yes
first_id	string	The ID of the first item in the list.	Yes
has_more	boolean	Whether there are more items available.	Yes
last_id	string	The ID of the last item in the list.	Yes
object	enum	The type of object returned, must be list. Possible values: list	Yes

OpenAI.ResponseLogProb

A logprob is the logarithmic probability that the model assigns to producing a particular token at a given position in the sequence. Less-negative (higher) logprob values indicate greater model confidence in that token choice.

Name	Type	Description	Required	Default
logprob	number	The log probability of this token.	Yes
token	string	A possible text token.	Yes
top_logprobs	array of OpenAI.ResponseLogProbTopLogprobs	The log probability of the top 20 most likely tokens.	No

OpenAI.ResponseLogProbTopLogprobs

Name	Type	Description	Required	Default
logprob	number		No
token	string		No

OpenAI.ResponseMCPCallArgumentsDeltaEvent

Emitted when there is a delta (partial update) to the arguments of an MCP tool call.

Name	Type	Description	Required	Default
delta	string	A JSON string containing the partial update to the arguments for the MCP tool call.	Yes
item_id	string	The unique identifier of the MCP tool call item being processed.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.mcp_call_arguments.delta’. Possible values: response.mcp_call_arguments.delta	Yes

OpenAI.ResponseMCPCallFailedEvent

Emitted when an MCP tool call has failed.

Name	Type	Description	Required	Default
item_id	string	The ID of the MCP tool call item that failed.	Yes
output_index	integer	The index of the output item that failed.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.mcp_call.failed’. Possible values: response.mcp_call.failed	Yes

OpenAI.ResponseMCPCallInProgressEvent

Emitted when an MCP tool call is in progress.

Name	Type	Description	Required	Default
item_id	string	The unique identifier of the MCP tool call item being processed.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.mcp_call.in_progress’. Possible values: response.mcp_call.in_progress	Yes

OpenAI.ResponseMCPListToolsFailedEvent

Emitted when the attempt to list available MCP tools has failed.

Name	Type	Description	Required	Default
item_id	string	The ID of the MCP tool call item that failed.	Yes
output_index	integer	The index of the output item that failed.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.mcp_list_tools.failed’. Possible values: response.mcp_list_tools.failed	Yes

OpenAI.ResponseMCPListToolsInProgressEvent

Emitted when the system is in the process of retrieving the list of available MCP tools.

Name	Type	Description	Required	Default
item_id	string	The ID of the MCP tool call item that is being processed.	Yes
output_index	integer	The index of the output item that is being processed.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.mcp_list_tools.in_progress’. Possible values: response.mcp_list_tools.in_progress	Yes

OpenAI.ResponseModalities

Output types that you would like the model to generate. Most models are capable of generating text, which is the default: ["text"] The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: ["text", "audio"]

This schema accepts one of the following types:

• array
• null

OpenAI.ResponseOutputItemAddedEvent

Emitted when a new output item is added.

Name	Type	Description	Required	Default
item	OpenAI.OutputItem		Yes
└─ type	OpenAI.OutputItemType		Yes
output_index	integer	The index of the output item that was added.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.output_item.added. Possible values: response.output_item.added	Yes

OpenAI.ResponseOutputTextAnnotationAddedEvent

Emitted when an annotation is added to output text content.

Name	Type	Description	Required	Default
annotation	OpenAI.Annotation	An annotation that applies to a span of output text.	Yes
└─ type	OpenAI.AnnotationType		Yes
annotation_index	integer	The index of the annotation within the content part.	Yes
content_index	integer	The index of the content part within the output item.	Yes
item_id	string	The unique identifier of the item to which the annotation is being added.	Yes
output_index	integer	The index of the output item in the response’s output array.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always ‘response.output_text.annotation.added’. Possible values: response.output_text.annotation.added	Yes

OpenAI.ResponsePromptVariables

Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.

Type: object

OpenAI.ResponseQueuedEvent

Emitted when a response is queued and waiting to be processed.

Name	Type	Description	Required	Default
response	OpenAI.Response		Yes
└─ background	boolean or null		No
└─ completed_at	string or null		No
└─ content_filters	array of AzureContentFilterForResponsesAPI	The content filter results from RAI.	Yes
└─ conversation	OpenAI.ConversationReference or null		No
└─ created_at	integer	Unix timestamp (in seconds) of when this Response was created.	Yes
└─ error	OpenAI.ResponseError or null		Yes
└─ id	string	Unique identifier for this Response.	Yes
└─ incomplete_details	OpenAI.ResponseIncompleteDetails or null		Yes
└─ instructions	string or array of OpenAI.InputItem or null		Yes
└─ max_output_tokens	integer or null		No
└─ max_tool_calls	integer or null		No
└─ metadata	OpenAI.Metadata or null		No
└─ model	string	Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.	No
└─ object	enum	The object type of this resource - always set to response. Possible values: response	Yes
└─ output	array of OpenAI.OutputItem	An array of content items generated by the model. - The length and order of items in the output array is dependent on the model’s response. - Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.	Yes
└─ output_text	string or null		No
└─ parallel_tool_calls	boolean	Whether to allow the model to run tool calls in parallel.	Yes	True
└─ previous_response_id	string or null		No
└─ prompt	OpenAI.Prompt	Reference to a prompt template and its variables. Learn more.	No
└─ prompt_cache_key	string	Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.	No
└─ prompt_cache_retention	string or null		No
└─ reasoning	OpenAI.Reasoning or null		No
└─ safety_identifier	string	A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.	No
└─ status	enum	The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete. Possible values: completed, failed, in_progress, cancelled, queued, incomplete	No
└─ temperature	number or null		No	1
└─ text	OpenAI.ResponseTextParam	Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - Text inputs and outputs - Structured Outputs	No
└─ tool_choice	OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.	No
└─ tools	OpenAI.ToolsArray	An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools: - Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools. - MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools. - Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.	No
└─ top_logprobs	integer or null		No
└─ top_p	number or null		No	1
└─ truncation	string or null		No	disabled
└─ usage	OpenAI.ResponseUsage	Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.	No
└─ user	string (deprecated)	This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.	No
sequence_number	integer	The sequence number for this event.	Yes
type	enum	The type of the event. Always ‘response.queued’. Possible values: response.queued	Yes

OpenAI.ResponseReasoningSummaryPartAddedEvent

Emitted when a new reasoning summary part is added.

Name	Type	Description	Required	Default
item_id	string	The ID of the item this summary part is associated with.	Yes
output_index	integer	The index of the output item this summary part is associated with.	Yes
part	OpenAI.ResponseReasoningSummaryPartAddedEventPart		Yes
└─ text	string		Yes
└─ type	enum	Possible values: summary_text	Yes
sequence_number	integer	The sequence number of this event.	Yes
summary_index	integer	The index of the summary part within the reasoning summary.	Yes
type	enum	The type of the event. Always response.reasoning_summary_part.added. Possible values: response.reasoning_summary_part.added	Yes

OpenAI.ResponseReasoningSummaryPartAddedEventPart

Name	Type	Description	Required	Default
text	string		Yes
type	enum	Possible values: summary_text	Yes

OpenAI.ResponseReasoningSummaryTextDeltaEvent

Emitted when a delta is added to a reasoning summary text.

Name	Type	Description	Required	Default
delta	string	The text delta that was added to the summary.	Yes
item_id	string	The ID of the item this summary text delta is associated with.	Yes
output_index	integer	The index of the output item this summary text delta is associated with.	Yes
sequence_number	integer	The sequence number of this event.	Yes
summary_index	integer	The index of the summary part within the reasoning summary.	Yes
type	enum	The type of the event. Always response.reasoning_summary_text.delta. Possible values: response.reasoning_summary_text.delta	Yes

OpenAI.ResponseReasoningTextDeltaEvent

Emitted when a delta is added to a reasoning text.

Name	Type	Description	Required	Default
content_index	integer	The index of the reasoning content part this delta is associated with.	Yes
delta	string	The text delta that was added to the reasoning content.	Yes
item_id	string	The ID of the item this reasoning text delta is associated with.	Yes
output_index	integer	The index of the output item this reasoning text delta is associated with.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.reasoning_text.delta. Possible values: response.reasoning_text.delta	Yes

OpenAI.ResponseRefusalDeltaEvent

Emitted when there is a partial refusal text.

Name	Type	Description	Required	Default
content_index	integer	The index of the content part that the refusal text is added to.	Yes
delta	string	The refusal text that is added.	Yes
item_id	string	The ID of the output item that the refusal text is added to.	Yes
output_index	integer	The index of the output item that the refusal text is added to.	Yes
sequence_number	integer	The sequence number of this event.	Yes
type	enum	The type of the event. Always response.refusal.delta. Possible values: response.refusal.delta	Yes

OpenAI.ResponseStreamOptions

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

Name	Type	Description	Required	Default
include_obfuscation	boolean	When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.	No

OpenAI.ResponseTextDeltaEvent

Emitted when there is an additional text delta.

Name	Type	Description	Required	Default
content_index	integer	The index of the content part that the text delta was added to.	Yes
delta	string	The text delta that was added.	Yes
item_id	string	The ID of the output item that the text delta was added to.	Yes
logprobs	array of OpenAI.ResponseLogProb	The log probabilities of the tokens in the delta.	Yes
output_index	integer	The index of the output item that the text delta was added to.	Yes
sequence_number	integer	The sequence number for this event.	Yes
type	enum	The type of the event. Always response.output_text.delta. Possible values: response.output_text.delta	Yes

OpenAI.ResponseTextParam

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

• Text inputs and outputs
• Structured Outputs

Name	Type	Description	Required	Default
format	OpenAI.TextResponseFormatConfiguration	An object specifying the format that the model must output. Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the The default format is { "type": "text" } with no additional options. *Not recommended for gpt-4o and newer models: Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.	No
verbosity	OpenAI.Verbosity	Constrains the verbosity of the model’s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.	No

OpenAI.ResponseUsage

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

Name	Type	Description	Required	Default
input_tokens	integer	The number of input tokens.	Yes
input_tokens_details	OpenAI.ResponseUsageInputTokensDetails		Yes
└─ cached_tokens	integer		Yes
output_tokens	integer	The number of output tokens.	Yes
output_tokens_details	OpenAI.ResponseUsageOutputTokensDetails		Yes
└─ reasoning_tokens	integer		Yes
total_tokens	integer	The total number of tokens used.	Yes

OpenAI.ResponseUsageInputTokensDetails

Name	Type	Description	Required	Default
cached_tokens	integer		Yes

OpenAI.ResponseUsageOutputTokensDetails

Name	Type	Description	Required	Default
reasoning_tokens	integer		Yes

OpenAI.ResponseWebSearchCallInProgressEvent

Note: web_search is not yet available via Azure OpenAI.

Name	Type	Description	Required	Default
item_id	string	Unique ID for the output item associated with the web search call.	Yes
output_index	integer	The index of the output item that the web search call is associated with.	Yes
sequence_number	integer	The sequence number of the web search call being processed.	Yes
type	enum	The type of the event. Always response.web_search_call.in_progress. Possible values: response.web_search_call.in_progress	Yes

OpenAI.ResponseWebSearchCallSearchingEvent

Note: web_search is not yet available via Azure OpenAI.

Name	Type	Description	Required	Default
item_id	string	Unique ID for the output item associated with the web search call.	Yes
output_index	integer	The index of the output item that the web search call is associated with.	Yes
sequence_number	integer	The sequence number of the web search call being processed.	Yes
type	enum	The type of the event. Always response.web_search_call.searching. Possible values: response.web_search_call.searching	Yes

OpenAI.RunCompletionUsage

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

Name	Type	Description	Required	Default
completion_tokens	integer	Number of completion tokens used over the course of the run.	Yes
prompt_tokens	integer	Number of prompt tokens used over the course of the run.	Yes
total_tokens	integer	Total number of tokens used (prompt + completion).	Yes

OpenAI.RunGraderRequest

Name	Type	Description	Required	Default
grader	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderPython or OpenAI.GraderScoreModel or OpenAI.GraderMulti or GraderEndpoint	The grader used for the fine-tuning job.	Yes
item	OpenAI.RunGraderRequestItem		No
model_sample	string	The model sample to be evaluated. This value will be used to populate the sample namespace. See the guide for more details. The output_json variable will be populated if the model sample is a valid JSON string.	Yes

OpenAI.RunGraderRequestItem

Type: object

OpenAI.RunGraderResponse

Name	Type	Description	Required	Default
metadata	OpenAI.RunGraderResponseMetadata		Yes
model_grader_token_usage_per_model	object		Yes
reward	number		Yes
sub_rewards	object		Yes

OpenAI.RunGraderResponseMetadata

Name	Type	Description	Required	Default
errors	OpenAI.RunGraderResponseMetadataErrors		Yes
execution_time	number		Yes
name	string		Yes
sampled_model_name	string or null		Yes
scores	object		Yes
token_usage	integer or null		Yes
type	string		Yes

OpenAI.RunGraderResponseMetadataErrors

Name	Type	Description	Required	Default
formula_parse_error	boolean		Yes
invalid_variable_error	boolean		Yes
model_grader_parse_error	boolean		Yes
model_grader_refusal_error	boolean		Yes
model_grader_server_error	boolean		Yes
model_grader_server_error_details	string or null		Yes
other_error	boolean		Yes
python_grader_runtime_error	boolean		Yes
python_grader_runtime_error_details	string or null		Yes
python_grader_server_error	boolean		Yes
python_grader_server_error_type	string or null		Yes
sample_parse_error	boolean		Yes
truncated_observation_error	boolean		Yes
unresponsive_reward_error	boolean		Yes

OpenAI.RunObject

Represents an execution run on a thread.

Name	Type	Description	Required	Default
assistant_id	string	The ID of the assistant used for execution of this run.	Yes
cancelled_at	string or null	The Unix timestamp (in seconds) for when the run was cancelled.	Yes
completed_at	string or null	The Unix timestamp (in seconds) for when the run was completed.	Yes
created_at	integer	The Unix timestamp (in seconds) for when the run was created.	Yes
expires_at	string or null	The Unix timestamp (in seconds) for when the run will expire.	Yes
failed_at	string or null	The Unix timestamp (in seconds) for when the run failed.	Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
incomplete_details	OpenAI.RunObjectIncompleteDetails or null	Details on why the run is incomplete. Will be null if the run is not incomplete.	Yes
instructions	string	The instructions that the assistant used for this run.	Yes
last_error	OpenAI.RunObjectLastError or null	The last error associated with this run. Will be null if there are no errors.	Yes
max_completion_tokens	integer or null	The maximum number of completion tokens specified to have been used over the course of the run.	Yes
max_prompt_tokens	integer or null	The maximum number of prompt tokens specified to have been used over the course of the run.	Yes
metadata	OpenAI.Metadata or null		Yes
model	string	The model that the assistant used for this run.	Yes
object	enum	The object type, which is always thread.run. Possible values: thread.run	Yes
parallel_tool_calls	OpenAI.ParallelToolCalls	Whether to enable parallel function calling during tool use.	Yes
required_action	OpenAI.RunObjectRequiredAction or null	Details on the action required to continue the run. Will be null if no action is required.	Yes
response_format	OpenAI.AssistantsApiResponseFormatOption	Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensure the model will match your supplied JSON schema. Learn more in the Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important:* when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.	Yes
started_at	string or null	The Unix timestamp (in seconds) for when the run was started.	Yes
status	OpenAI.RunStatus	The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.	Yes
temperature	number or null	The sampling temperature used for this run. If not set, defaults to 1.	No
thread_id	string	The ID of the thread that was executed on as a part of this run.	Yes
tool_choice	OpenAI.AssistantsApiToolChoiceOption	Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.	Yes
tools	array of OpenAI.AssistantTool	The list of tools that the assistant used for this run.	Yes	[]
top_p	number or null	The nucleus sampling value used for this run. If not set, defaults to 1.	No
truncation_strategy	OpenAI.TruncationObject	Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.	Yes
usage	OpenAI.RunCompletionUsage or null		Yes

OpenAI.RunObjectIncompleteDetails

Name	Type	Description	Required	Default
reason	enum	Possible values: max_completion_tokens, max_prompt_tokens	No

OpenAI.RunObjectLastError

Name	Type	Description	Required	Default
code	enum	Possible values: server_error, rate_limit_exceeded, invalid_prompt	Yes
message	string		Yes

OpenAI.RunObjectRequiredAction

Name	Type	Description	Required	Default
submit_tool_outputs	OpenAI.RunObjectRequiredActionSubmitToolOutputs		Yes
type	enum	Possible values: submit_tool_outputs	Yes

OpenAI.RunObjectRequiredActionSubmitToolOutputs

Name	Type	Description	Required	Default
tool_calls	array of OpenAI.RunToolCallObject		Yes

OpenAI.RunStatus

The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

Property	Value
Type	string
Values	queued in_progress requires_action cancelling cancelled failed completed incomplete expired

OpenAI.RunStepCompletionUsage

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

Name	Type	Description	Required	Default
completion_tokens	integer	Number of completion tokens used over the course of the run step.	Yes
prompt_tokens	integer	Number of prompt tokens used over the course of the run step.	Yes
total_tokens	integer	Total number of tokens used (prompt + completion).	Yes

OpenAI.RunStepDetailsMessageCreationObject

Details of the message creation by the run step.

Name	Type	Description	Required	Default
message_creation	OpenAI.RunStepDetailsMessageCreationObjectMessageCreation		Yes
type	enum	Always message_creation. Possible values: message_creation	Yes

OpenAI.RunStepDetailsMessageCreationObjectMessageCreation

Name	Type	Description	Required	Default
message_id	string		Yes

OpenAI.RunStepDetailsToolCall

Discriminator for OpenAI.RunStepDetailsToolCall

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

Type Value	Schema
code_interpreter	OpenAI.RunStepDetailsToolCallsCodeObject
file_search	OpenAI.RunStepDetailsToolCallsFileSearchObject
function	OpenAI.RunStepDetailsToolCallsFunctionObject

Name	Type	Description	Required	Default
type	OpenAI.RunStepDetailsToolCallType		Yes

OpenAI.RunStepDetailsToolCallType

Property	Value
Type	string
Values	code_interpreter file_search function

OpenAI.RunStepDetailsToolCallsCodeObject

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

Name	Type	Description	Required	Default
code_interpreter	OpenAI.RunStepDetailsToolCallsCodeObjectCodeInterpreter		Yes
└─ input	string		Yes
└─ outputs	array of OpenAI.RunStepDetailsToolCallsCodeOutputLogsObject or OpenAI.RunStepDetailsToolCallsCodeOutputImageObject		Yes
id	string	The ID of the tool call.	Yes
type	enum	The type of tool call. This is always going to be code_interpreter for this type of tool call. Possible values: code_interpreter	Yes

OpenAI.RunStepDetailsToolCallsCodeObjectCodeInterpreter

Name	Type	Description	Required	Default
input	string		Yes
outputs	array of OpenAI.RunStepDetailsToolCallsCodeOutputLogsObject or OpenAI.RunStepDetailsToolCallsCodeOutputImageObject		Yes

OpenAI.RunStepDetailsToolCallsCodeOutputImageObject

Name	Type	Description	Required	Default
image	OpenAI.RunStepDetailsToolCallsCodeOutputImageObjectImage		Yes
type	enum	Always image. Possible values: image	Yes

OpenAI.RunStepDetailsToolCallsCodeOutputImageObjectImage

Name	Type	Description	Required	Default
file_id	string		Yes

OpenAI.RunStepDetailsToolCallsCodeOutputLogsObject

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

Name	Type	Description	Required	Default
logs	string	The text output from the Code Interpreter tool call.	Yes
type	enum	Always logs. Possible values: logs	Yes

OpenAI.RunStepDetailsToolCallsFileSearchObject

Name	Type	Description	Required	Default
file_search	OpenAI.RunStepDetailsToolCallsFileSearchObjectFileSearch		Yes
└─ ranking_options	OpenAI.RunStepDetailsToolCallsFileSearchRankingOptionsObject	The ranking options for the file search.	No
└─ results	array of OpenAI.RunStepDetailsToolCallsFileSearchResultObject		No
id	string	The ID of the tool call object.	Yes
type	enum	The type of tool call. This is always going to be file_search for this type of tool call. Possible values: file_search	Yes

OpenAI.RunStepDetailsToolCallsFileSearchObjectFileSearch

Name	Type	Description	Required	Default
ranking_options	OpenAI.RunStepDetailsToolCallsFileSearchRankingOptionsObject	The ranking options for the file search.	No
results	array of OpenAI.RunStepDetailsToolCallsFileSearchResultObject		No

OpenAI.RunStepDetailsToolCallsFileSearchRankingOptionsObject

The ranking options for the file search.

Name	Type	Description	Required	Default
ranker	OpenAI.FileSearchRanker	The ranker to use for the file search. If not specified will use the auto ranker.	Yes
score_threshold	number	The score threshold for the file search. All values must be a floating point number between 0 and 1. Constraints: min: 0, max: 1	Yes

OpenAI.RunStepDetailsToolCallsFileSearchResultObject

A result instance of the file search.

Name	Type	Description	Required	Default
content	array of OpenAI.RunStepDetailsToolCallsFileSearchResultObjectContent	The content of the result that was found. The content is only included if requested via the include query parameter.	No
file_id	string	The ID of the file that result was found in.	Yes
file_name	string	The name of the file that result was found in.	Yes
score	number	The score of the result. All values must be a floating point number between 0 and 1. Constraints: min: 0, max: 1	Yes

OpenAI.RunStepDetailsToolCallsFileSearchResultObjectContent

Name	Type	Description	Required	Default
text	string		No
type	enum	Possible values: text	No

OpenAI.RunStepDetailsToolCallsFunctionObject

Name	Type	Description	Required	Default
function	OpenAI.RunStepDetailsToolCallsFunctionObjectFunction		Yes
└─ arguments	string		Yes
└─ name	string		Yes
└─ output	string or null		Yes
id	string	The ID of the tool call object.	Yes
type	enum	The type of tool call. This is always going to be function for this type of tool call. Possible values: function	Yes

OpenAI.RunStepDetailsToolCallsFunctionObjectFunction

Name	Type	Description	Required	Default
arguments	string		Yes
name	string		Yes
output	string or null		Yes

OpenAI.RunStepDetailsToolCallsObject

Details of the tool call.

Name	Type	Description	Required	Default
tool_calls	array of OpenAI.RunStepDetailsToolCall	An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.	Yes
type	enum	Always tool_calls. Possible values: tool_calls	Yes

OpenAI.RunStepObject

Represents a step in execution of a run.

Name	Type	Description	Required	Default
assistant_id	string	The ID of the assistant associated with the run step.	Yes
cancelled_at	string or null		Yes
completed_at	string or null		Yes
created_at	integer	The Unix timestamp (in seconds) for when the run step was created.	Yes
expired_at	string or null		Yes
failed_at	string or null		Yes
id	string	The identifier of the run step, which can be referenced in API endpoints.	Yes
last_error	OpenAI.RunStepObjectLastError or null		Yes
metadata	OpenAI.Metadata or null		Yes
object	enum	The object type, which is always thread.run.step. Possible values: thread.run.step	Yes
run_id	string	The ID of the run that this run step is a part of.	Yes
status	enum	The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired. Possible values: in_progress, cancelled, failed, completed, expired	Yes
step_details	OpenAI.RunStepDetailsMessageCreationObject or OpenAI.RunStepDetailsToolCallsObject	The details of the run step.	Yes
thread_id	string	The ID of the thread that was run.	Yes
type	enum	The type of run step, which can be either message_creation or tool_calls. Possible values: message_creation, tool_calls	Yes
usage	OpenAI.RunStepCompletionUsage	Usage statistics related to the run step. This value will be null while the run step’s status is in_progress.	Yes

OpenAI.RunStepObjectLastError

Name	Type	Description	Required	Default
code	enum	Possible values: server_error, rate_limit_exceeded	Yes
message	string		Yes

OpenAI.RunToolCallObject

Tool call objects

Name	Type	Description	Required	Default
function	OpenAI.RunToolCallObjectFunction		Yes
└─ arguments	string		Yes
└─ name	string		Yes
id	string	The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.	Yes
type	enum	The type of tool call the output is required for. For now, this is always function. Possible values: function	Yes

OpenAI.RunToolCallObjectFunction

Name	Type	Description	Required	Default
arguments	string		Yes
name	string		Yes

OpenAI.Screenshot

A screenshot action.

Name	Type	Description	Required	Default
type	enum	Specifies the event type. For a screenshot action, this property is always set to screenshot. Possible values: screenshot	Yes

OpenAI.Scroll

A scroll action.

Name	Type	Description	Required	Default
scroll_x	integer	The horizontal scroll distance.	Yes
scroll_y	integer	The vertical scroll distance.	Yes
type	enum	Specifies the event type. For a scroll action, this property is always set to scroll. Possible values: scroll	Yes
x	integer	The x-coordinate where the scroll occurred.	Yes
y	integer	The y-coordinate where the scroll occurred.	Yes

OpenAI.SearchContextSize

Property	Value
Type	string
Values	low medium high

OpenAI.SpecificApplyPatchParam

Forces the model to call the apply_patch tool when executing a tool call.

Name	Type	Description	Required	Default
type	enum	The tool to call. Always apply_patch. Possible values: apply_patch	Yes

OpenAI.SpecificFunctionShellParam

Forces the model to call the shell tool when a tool call is required.

Name	Type	Description	Required	Default
type	enum	The tool to call. Always shell. Possible values: shell	Yes

OpenAI.StaticChunkingStrategy

Name	Type	Description	Required	Default
chunk_overlap_tokens	integer	The number of tokens that overlap between chunks. The default value is 400. Note that the overlap must not exceed half of max_chunk_size_tokens.	Yes
max_chunk_size_tokens	integer	The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096. Constraints: min: 100, max: 4096	Yes

OpenAI.StaticChunkingStrategyRequestParam

Customize your own chunking strategy by setting chunk size and chunk overlap.

Name	Type	Description	Required	Default
static	OpenAI.StaticChunkingStrategy		Yes
type	enum	Always static. Possible values: static	Yes

OpenAI.StaticChunkingStrategyResponseParam

Name	Type	Description	Required	Default
static	OpenAI.StaticChunkingStrategy		Yes
type	enum	Always static. Possible values: static	Yes

OpenAI.StopConfiguration

Not supported with latest reasoning models o3 and o4-mini. Up to four sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

This schema accepts one of the following types:

• array
• null

OpenAI.SubmitToolOutputsRunRequest

Name	Type	Description	Required	Default
stream	boolean or null		No
tool_outputs	array of OpenAI.SubmitToolOutputsRunRequestToolOutputs	A list of tools for which the outputs are being submitted.	Yes

OpenAI.SubmitToolOutputsRunRequestToolOutputs

Name	Type	Description	Required	Default
output	string		No
tool_call_id	string		No

OpenAI.Summary

A summary text from the model.

Name	Type	Description	Required	Default
text	string	A summary of the reasoning output from the model so far.	Yes
type	enum	The type of the object. Always summary_text. Possible values: summary_text	Yes

OpenAI.SummaryTextContent

A summary text from the model.

Name	Type	Description	Required	Default
text	string	A summary of the reasoning output from the model so far.	Yes
type	enum	The type of the object. Always summary_text. Possible values: summary_text	Yes

OpenAI.TextAnnotation

Discriminator for OpenAI.TextAnnotation

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

Type Value	Schema
file_citation	OpenAI.MessageContentTextAnnotationsFileCitationObject
file_path	OpenAI.MessageContentTextAnnotationsFilePathObject

Name	Type	Description	Required	Default
type	OpenAI.TextAnnotationType		Yes

OpenAI.TextAnnotationType

Property	Value
Type	string
Values	file_citation file_path

OpenAI.TextContent

A text content.

Name	Type	Description	Required	Default
text	string		Yes
type	enum	Possible values: text	Yes

OpenAI.TextResponseFormatConfiguration

An object specifying the format that the model must output. Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the

The default format is { "type": "text" } with no additional options. Not recommended for gpt-4o and newer models:* Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Discriminator for OpenAI.TextResponseFormatConfiguration

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

Type Value	Schema
json_schema	OpenAI.TextResponseFormatJsonSchema
text	OpenAI.TextResponseFormatConfigurationResponseFormatText
json_object	OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject

Name	Type	Description	Required	Default
type	OpenAI.TextResponseFormatConfigurationType		Yes

OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always json_object. Possible values: json_object	Yes

OpenAI.TextResponseFormatConfigurationResponseFormatText

Default response format. Used to generate text responses.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always text. Possible values: text	Yes

OpenAI.TextResponseFormatConfigurationType

Property	Value
Type	string
Values	text json_schema json_object

OpenAI.TextResponseFormatJsonSchema

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

Name	Type	Description	Required	Default
description	string	A description of what the response format is for, used by the model to determine how to respond in the format.	No
name	string	The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.	Yes
schema	OpenAI.ResponseFormatJsonSchemaSchema	The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.	Yes
strict	boolean or null		No
type	enum	The type of response format being defined. Always json_schema. Possible values: json_schema	Yes

OpenAI.ThreadObject

Represents a thread that contains messages.

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the thread was created.	Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
metadata	OpenAI.Metadata or null		Yes
object	enum	The object type, which is always thread. Possible values: thread	Yes
tool_resources	OpenAI.ThreadObjectToolResources or null		Yes

OpenAI.ThreadObjectToolResources

Name	Type	Description	Required	Default
code_interpreter	OpenAI.ThreadObjectToolResourcesCodeInterpreter		No
file_search	OpenAI.ThreadObjectToolResourcesFileSearch		No

OpenAI.ThreadObjectToolResourcesCodeInterpreter

Name	Type	Description	Required	Default
file_ids	array of string		No

OpenAI.ThreadObjectToolResourcesFileSearch

Name	Type	Description	Required	Default
vector_store_ids	array of string		No

OpenAI.TokenLimits

Name	Type	Description	Required	Default
post_instructions	integer	Constraints: min: 0	No

OpenAI.Tool

A tool that can be used to generate a response.

Discriminator for OpenAI.Tool

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

Type Value	Schema
code_interpreter	OpenAI.CodeInterpreterTool
function	OpenAI.FunctionTool
file_search	OpenAI.FileSearchTool
computer_use_preview	OpenAI.ComputerUsePreviewTool
web_search	OpenAI.WebSearchTool
mcp	OpenAI.MCPTool
image_generation	OpenAI.ImageGenTool
local_shell	OpenAI.LocalShellToolParam
shell	OpenAI.FunctionShellToolParam
custom	OpenAI.CustomToolParam
web_search_preview	OpenAI.WebSearchPreviewTool
apply_patch	OpenAI.ApplyPatchToolParam

Name	Type	Description	Required	Default
type	OpenAI.ToolType		Yes

OpenAI.ToolChoiceAllowed

Constrains the tools available to the model to a predefined set.

Name	Type	Description	Required	Default
mode	enum	Constrains the tools available to the model to a predefined set. auto allows the model to pick from among the allowed tools and generate a message. required requires the model to call one or more of the allowed tools. Possible values: auto, required	Yes
tools	array of object	A list of tool definitions that the model should be allowed to call. For the Responses API, the list of tool definitions might look like: json<br /> [<br /> { "type": "function", "name": "get_weather" },<br /> { "type": "mcp", "server_label": "deepwiki" },<br /> { "type": "image_generation" }<br /> ]<br />	Yes
type	enum	Allowed tool configuration type. Always allowed_tools. Possible values: allowed_tools	Yes

OpenAI.ToolChoiceCodeInterpreter

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: code_interpreter	Yes

OpenAI.ToolChoiceComputerUsePreview

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: computer_use_preview	Yes

OpenAI.ToolChoiceCustom

Use this option to force the model to call a specific custom tool.

Name	Type	Description	Required	Default
name	string	The name of the custom tool to call.	Yes
type	enum	For custom tool calling, the type is always custom. Possible values: custom	Yes

OpenAI.ToolChoiceFileSearch

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: file_search	Yes

OpenAI.ToolChoiceFunction

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

Name	Type	Description	Required	Default
name	string	The name of the function to call.	Yes
type	enum	For function calling, the type is always function. Possible values: function	Yes

OpenAI.ToolChoiceImageGeneration

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: image_generation	Yes

OpenAI.ToolChoiceMCP

Use this option to force the model to call a specific tool on a remote MCP server.

Name	Type	Description	Required	Default
name	string or null		No
server_label	string	The label of the MCP server to use.	Yes
type	enum	For MCP tools, the type is always mcp. Possible values: mcp	Yes

OpenAI.ToolChoiceOptions

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools.

Property	Value
Type	string
Values	none auto required

OpenAI.ToolChoiceParam

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Discriminator for OpenAI.ToolChoiceParam

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

Type Value	Schema
allowed_tools	OpenAI.ToolChoiceAllowed
mcp	OpenAI.ToolChoiceMCP
custom	OpenAI.ToolChoiceCustom
apply_patch	OpenAI.SpecificApplyPatchParam
shell	OpenAI.SpecificFunctionShellParam
file_search	OpenAI.ToolChoiceFileSearch
web_search_preview	OpenAI.ToolChoiceWebSearchPreview
computer_use_preview	OpenAI.ToolChoiceComputerUsePreview
web_search_preview_2025_03_11	OpenAI.ToolChoiceWebSearchPreview20250311
image_generation	OpenAI.ToolChoiceImageGeneration
code_interpreter	OpenAI.ToolChoiceCodeInterpreter

Name	Type	Description	Required	Default
type	OpenAI.ToolChoiceParamType		Yes

OpenAI.ToolChoiceParamType

Property	Value
Type	string
Values	allowed_tools function mcp custom apply_patch shell file_search web_search_preview computer_use_preview web_search_preview_2025_03_11 image_generation code_interpreter

OpenAI.ToolChoiceWebSearchPreview

Note: web_search is not yet available via Azure OpenAI.

Name	Type	Description	Required	Default
type	enum	Possible values: web_search_preview	Yes

OpenAI.ToolChoiceWebSearchPreview20250311

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: web_search_preview_2025_03_11	Yes

OpenAI.ToolType

Property	Value
Type	string
Values	function file_search computer_use_preview web_search mcp code_interpreter image_generation local_shell shell custom web_search_preview apply_patch

OpenAI.ToolsArray

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter. We support the following categories of tools:

• Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools.
• MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
• Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.

Array of: OpenAI.Tool

OpenAI.TopLogProb

The top log probability of a token.

Name	Type	Description	Required	Default
bytes	array of integer		Yes
logprob	number		Yes
token	string		Yes

OpenAI.TranscriptionSegment

Name	Type	Description	Required	Default
avg_logprob	number	Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.	Yes
compression_ratio	number	Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.	Yes
end	number	End time of the segment in seconds.	Yes
id	integer	Unique identifier of the segment.	Yes
no_speech_prob	number	Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.	Yes
seek	integer	Seek offset of the segment.	Yes
start	number	Start time of the segment in seconds.	Yes
temperature	number	Temperature parameter used for generating the segment.	Yes
text	string	Text content of the segment.	Yes
tokens	array of integer	Array of token IDs for the text content.	Yes

OpenAI.TranscriptionWord

Name	Type	Description	Required	Default
end	number	End time of the word in seconds.	Yes
start	number	Start time of the word in seconds.	Yes
word	string	The text content of the word.	Yes

OpenAI.TruncationObject

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

Name	Type	Description	Required	Default
last_messages	integer or null		No
type	enum	The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens. Possible values: auto, last_messages	Yes

OpenAI.Type

An action to type in text.

Name	Type	Description	Required	Default
text	string	The text to type.	Yes
type	enum	Specifies the event type. For a type action, this property is always set to type. Possible values: type	Yes

OpenAI.UpdateConversationBody

Name	Type	Description	Required	Default
metadata	OpenAI.Metadata or null	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

OpenAI.UpdateVectorStoreFileAttributesRequest

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		Yes

OpenAI.UpdateVectorStoreRequest

Name	Type	Description	Required	Default
expires_after	OpenAI.VectorStoreExpirationAfter	The expiration policy for a vector store.	No
metadata	OpenAI.Metadata or null		No
name	string or null	The name of the vector store.	No

OpenAI.UrlCitationBody

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

Name	Type	Description	Required	Default
end_index	integer	The index of the last character of the URL citation in the message.	Yes
start_index	integer	The index of the first character of the URL citation in the message.	Yes
title	string	The title of the web resource.	Yes
type	enum	The type of the URL citation. Always url_citation. Possible values: url_citation	Yes
url	string	The URL of the web resource.	Yes

OpenAI.ValidateGraderResponse

Name	Type	Description	Required	Default
grader	OpenAI.GraderStringCheck or OpenAI.GraderTextSimilarity or OpenAI.GraderPython or OpenAI.GraderScoreModel or OpenAI.GraderMulti or GraderEndpoint	The grader used for the fine-tuning job.	No

OpenAI.VectorStoreExpirationAfter

The expiration policy for a vector store.

Name	Type	Description	Required	Default
anchor	enum	Anchor timestamp after which the expiration policy applies. Supported anchors: last_active_at. Possible values: last_active_at	Yes
days	integer	The number of days after the anchor time that the vector store will expire. Constraints: min: 1, max: 365	Yes

OpenAI.VectorStoreFileAttributes

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

Type: object

OpenAI.VectorStoreFileBatchObject

A batch of files attached to a vector store.

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the vector store files batch was created.	Yes
file_counts	OpenAI.VectorStoreFileBatchObjectFileCounts		Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
object	enum	The object type, which is always vector_store.file_batch. Possible values: vector_store.files_batch	Yes
status	enum	The status of the vector store files batch, which can be either in_progress, completed, cancelled or failed. Possible values: in_progress, completed, cancelled, failed	Yes
vector_store_id	string	The ID of the vector store that the File is attached to.	Yes

OpenAI.VectorStoreFileBatchObjectFileCounts

Name	Type	Description	Required	Default
cancelled	integer		Yes
completed	integer		Yes
failed	integer		Yes
in_progress	integer		Yes
total	integer		Yes

OpenAI.VectorStoreFileObject

A list of files attached to a vector store.

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		No
chunking_strategy	OpenAI.ChunkingStrategyResponse	The strategy used to chunk the file.	No
created_at	integer	The Unix timestamp (in seconds) for when the vector store file was created.	Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
last_error	OpenAI.VectorStoreFileObjectLastError or null		Yes
object	enum	The object type, which is always vector_store.file. Possible values: vector_store.file	Yes
status	enum	The status of the vector store file, which can be either in_progress, completed, cancelled, or failed. The status completed indicates that the vector store file is ready for use. Possible values: in_progress, completed, cancelled, failed	Yes
usage_bytes	integer	The total vector store usage in bytes. Note that this may be different from the original file size.	Yes
vector_store_id	string	The ID of the vector store that the File is attached to.	Yes

OpenAI.VectorStoreFileObjectLastError

Name	Type	Description	Required	Default
code	enum	Possible values: server_error, unsupported_file, invalid_file	Yes
message	string		Yes

OpenAI.VectorStoreObject

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

Name	Type	Description	Required	Default
created_at	integer	The Unix timestamp (in seconds) for when the vector store was created.	Yes
expires_after	OpenAI.VectorStoreExpirationAfter	The expiration policy for a vector store.	No
expires_at	string or null		No
file_counts	OpenAI.VectorStoreObjectFileCounts		Yes
id	string	The identifier, which can be referenced in API endpoints.	Yes
last_active_at	string or null		Yes
metadata	OpenAI.Metadata or null		Yes
name	string	The name of the vector store.	Yes
object	enum	The object type, which is always vector_store. Possible values: vector_store	Yes
status	enum	The status of the vector store, which can be either expired, in_progress, or completed. A status of completed indicates that the vector store is ready for use. Possible values: expired, in_progress, completed	Yes
usage_bytes	integer	The total number of bytes used by the files in the vector store.	Yes

OpenAI.VectorStoreObjectFileCounts

Name	Type	Description	Required	Default
cancelled	integer		Yes
completed	integer		Yes
failed	integer		Yes
in_progress	integer		Yes
total	integer		Yes

OpenAI.VectorStoreSearchRequest

Name	Type	Description	Required	Default
filters	OpenAI.ComparisonFilter or OpenAI.CompoundFilter	A filter to apply based on file attributes.	No
max_num_results	integer	The maximum number of results to return. This number should be between 1 and 50 inclusive. Constraints: min: 1, max: 50	No	10
query	string or array of string	A query string for a search	Yes
ranking_options	OpenAI.VectorStoreSearchRequestRankingOptions		No
└─ ranker	enum	Possible values: none, auto, default-2024-11-15	No
└─ score_threshold	number	Constraints: min: 0, max: 1	No
rewrite_query	boolean	Whether to rewrite the natural language query for vector search.	No

OpenAI.VectorStoreSearchRequestRankingOptions

Name	Type	Description	Required	Default
ranker	enum	Possible values: none, auto, default-2024-11-15	No
score_threshold	number	Constraints: min: 0, max: 1	No

OpenAI.VectorStoreSearchResultContentObject

Name	Type	Description	Required	Default
text	string	The text content returned from search.	Yes
type	enum	The type of content. Possible values: text	Yes

OpenAI.VectorStoreSearchResultItem

Name	Type	Description	Required	Default
attributes	OpenAI.VectorStoreFileAttributes or null		Yes
content	array of OpenAI.VectorStoreSearchResultContentObject	Content chunks from the file.	Yes
file_id	string	The ID of the vector store file.	Yes
filename	string	The name of the vector store file.	Yes
score	number	The similarity score for the result. Constraints: min: 0, max: 1	Yes

OpenAI.VectorStoreSearchResultsPage

Name	Type	Description	Required	Default
data	array of OpenAI.VectorStoreSearchResultItem	The list of search result items.	Yes
has_more	boolean	Indicates if there are more results to fetch.	Yes
next_page	string or null		Yes
object	enum	The object type, which is always vector_store.search_results.page Possible values: vector_store.search_results.page	Yes
search_query	array of string		Yes

OpenAI.Verbosity

Constrains the verbosity of the model’s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

Property	Value
Type	string
Values	low medium high

OpenAI.VoiceIdsShared

Property	Value
Type	string
Values	alloy ash ballad coral echo sage shimmer verse marin cedar

OpenAI.Wait

A wait action.

Name	Type	Description	Required	Default
type	enum	Specifies the event type. For a wait action, this property is always set to wait. Possible values: wait	Yes

OpenAI.WebSearchActionFind

Action type “find”: Searches for a pattern within a loaded page.

Name	Type	Description	Required	Default
pattern	string	The pattern or text to search for within the page.	Yes
type	enum	The action type. Possible values: find_in_page	Yes
url	string	The URL of the page searched for the pattern.	Yes

OpenAI.WebSearchActionOpenPage

Action type “open_page” - Opens a specific URL from search results.

Name	Type	Description	Required	Default
type	enum	The action type. Possible values: open_page	Yes
url	string	The URL opened by the model.	Yes

OpenAI.WebSearchActionSearch

Action type “search” - Performs a web search query.

Name	Type	Description	Required	Default
queries	array of string	The search queries.	No
query	string (deprecated)	[DEPRECATED] The search query.	Yes
sources	array of OpenAI.WebSearchActionSearchSources	The sources used in the search.	No
type	enum	The action type. Possible values: search	Yes

OpenAI.WebSearchActionSearchSources

Name	Type	Description	Required	Default
type	enum	Possible values: url	Yes
url	string		Yes

OpenAI.WebSearchApproximateLocation

The approximate location of the user.

Name	Type	Description	Required	Default
city	string or null		No
country	string or null		No
region	string or null		No
timezone	string or null		No
type	enum	The type of location approximation. Always approximate. Possible values: approximate	No

OpenAI.WebSearchPreviewTool

Note: web_search is not yet available via Azure OpenAI.

Name	Type	Description	Required	Default
search_context_size	OpenAI.SearchContextSize		No
type	enum	The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11. Possible values: web_search_preview	Yes
user_location	OpenAI.ApproximateLocation or null		No

OpenAI.WebSearchTool

Note: web_search is not yet available via Azure OpenAI.

Name	Type	Description	Required	Default
filters	OpenAI.WebSearchToolFilters or null		No
search_context_size	enum	High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default. Possible values: low, medium, high	No
type	enum	The type of the web search tool. One of web_search or web_search_2025_08_26. Possible values: web_search	Yes
user_location	OpenAI.WebSearchApproximateLocation or null		No

OpenAI.WebSearchToolFilters

Name	Type	Description	Required	Default
allowed_domains	array of string or null		No

Order

Property	Value
Type	string
Values	asc desc

ResponseFormatJSONSchemaRequest

Name	Type	Description	Required	Default
json_schema	object	JSON Schema for the response format	Yes
type	enum	Type of response format Possible values: json_schema	Yes

SpeechGenerationResponse

A representation of a response for a text-to-speech operation.

Name	Type	Description	Required	Default
audio	string	The generated audio, generated in the requested audio output format.	Yes

SpeechGenerationResponseFormat

The supported audio output formats for text-to-speech.

This component can be one of the following:

• string
• string: mp3, opus, aac, flac, wav, pcm

SpeechVoice

The available voices for text-to-speech.

Property	Value
Description	The available voices for text-to-speech.
Type	string
Values	alloy echo fable onyx nova shimmer

VideoContent

Name	Type	Description	Required	Default
content	string		Yes

VideoContentVariant

Selectable asset variants for downloaded content.

Property	Value
Description	Selectable asset variants for downloaded content.
Type	string
Values	video thumbnail spritesheet

VideoIdParameter

Name	Type	Description	Required	Default
video-id	string	The ID of the video to use for the Azure OpenAI request.	Yes

VideoList

A list of video generation jobs.

Name	Type	Description	Required	Default
data	array of VideoResource	The list of video generation jobs.	Yes
first_id	string	The ID of the first video in the current page, if available.	No
has_more	boolean	A flag indicating whether there are more jobs available after the list.	Yes
last_id	string	The ID of the last video in the current page, if available.	No
object	enum	Possible values: list	Yes

VideoResource

Structured information describing a generated video job.

Name	Type	Description	Required	Default
completed_at	integer	Unix timestamp (seconds) for when the job completed, if finished.	No
created_at	integer	Unix timestamp (seconds) for when the job was created.	Yes
error	Error		No
└─ code	string		Yes
└─ message	string		Yes
expires_at	integer	Unix timestamp (seconds) for when the video generation expires (and will be deleted).	No
id	string	Unique identifier for the video job.	Yes
model	string	The video generation model deployment that produced the job.	Yes
object	string	The object type, which is always video.	Yes
progress	integer	Approximate completion percentage for the generation task.	Yes
remixed_from_video_id	string	Identifier of the source video if this video is a remix.	No
seconds	VideoSeconds	Supported clip durations, measured in seconds.	Yes
size	VideoSize	Output dimensions formatted as {width}x{height}.	Yes
status	VideoStatus	Lifecycle state of a generated video.	Yes

VideoSeconds

Supported clip durations, measured in seconds.

Property	Value
Description	Supported clip durations, measured in seconds.
Type	string
Values	4 8 12

VideoSize

Output dimensions formatted as {width}x{height}.

Property	Value
Description	Output dimensions formatted as {width}x{height}.
Type	string
Values	720x1280 1280x720 1024x1792 1792x1024

VideoStatus

Lifecycle state of a generated video.

Property	Value
Description	Lifecycle state of a generated video.
Type	string
Values	queued in_progress completed failed