# Create a model response

`POST /openai/v1/responses`

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

## Parameters

### Header parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `x-ms-user-isolation-key` | `string` | No | Opaque per-user isolation key used to scope endpoint-scoped data (responses, conversations, sessions) to a specific end user. |

## Request Body

Content-Type: `application/json` *(required)*

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `metadata` | `OpenAI.Metadata \| null` | No |  |
| `top_logprobs` | `OpenAI.integer \| null` | No |  |
| `temperature` | `OpenAI.numeric \| null` | No | _Default:_ `1` |
| `top_p` | `OpenAI.numeric \| null` | No | _Default:_ `1` |
| `user` | `string` | No | 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](/docs/guides/safety-best-practices#safety-identifiers). |
| `safety_identifier` | `string` | No | 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, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). |
| `prompt_cache_key` | `string` | No | Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). |
| `service_tier` | `enum` | No | Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. _Enum:_ `auto`, `default`, `flex`, `scale`, `priority` |
| `prompt_cache_retention` | `enum` | No | _Enum:_ `in_memory`, `24h` |
| `previous_response_id` | `string \| null` | No |  |
| `model` | `string` | No | The model deployment to use for the creation of this response. |
| `reasoning` | `OpenAI.Reasoning \| null` | No |  |
| `background` | `boolean \| null` | No |  |
| `max_tool_calls` | `OpenAI.integer \| null` | No |  |
| `text` | `OpenAI.ResponseTextParam` | No | Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](/docs/guides/text) - [Structured Outputs](/docs/guides/structured-outputs) |
| `tools` | `(BingGroundingTool \| MicrosoftFabricPreviewTool \| SharepointPreviewTool \| AzureAISearchTool \| OpenApiTool \| BingCustomSearchPreviewTool \| BrowserAutomationPreviewTool \| AzureFunctionTool \| CaptureStructuredOutputsTool \| A2APreviewTool \| WorkIQPreviewTool \| FabricIQPreviewTool \| MemorySearchPreviewTool \| ToolboxSearchPreviewTool \| OpenAI.CodeInterpreterTool \| OpenAI.FunctionTool \| OpenAI.FileSearchTool \| OpenAI.ComputerUsePreviewTool \| OpenAI.WebSearchTool \| OpenAI.MCPTool \| OpenAI.ImageGenTool \| OpenAI.LocalShellToolParam \| OpenAI.FunctionShellToolParam \| OpenAI.CustomToolParam \| OpenAI.WebSearchPreviewTool \| OpenAI.ApplyPatchToolParam \| OpenAI.ComputerTool \| OpenAI.NamespaceToolParam \| OpenAI.ToolSearchToolParam)[]` | No | 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](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search). Learn more about [built-in tools](/docs/guides/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](/docs/guides/tools-connectors-mcp). - **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](/docs/guides/function-calling). You can also use custom tools to call your own code. |
| `tool_choice` | `OpenAI.ToolChoiceOptions \| OpenAI.ToolChoiceParam` | No | _Enum:_ `none`, `auto`, `required` |
| `prompt` | `OpenAI.Prompt` | No | Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). |
| `truncation` | `enum` | No | _Default:_ `"disabled"` _Enum:_ `auto`, `disabled` |
| `input` | `string \| (OpenAI.EasyInputMessage \| OpenAI.ItemReferenceParam \| OpenAI.InputItemOutputMessage \| OpenAI.InputItemFileSearchToolCall \| OpenAI.InputItemComputerToolCall \| OpenAI.InputItemComputerCallOutputItemParam \| OpenAI.InputItemWebSearchToolCall \| OpenAI.InputItemFunctionToolCall \| OpenAI.InputItemFunctionCallOutputItemParam \| OpenAI.InputItemToolSearchCallItemParam \| OpenAI.InputItemToolSearchOutputItemParam \| OpenAI.InputItemReasoningItem \| OpenAI.InputItemCompactionSummaryItemParam \| OpenAI.InputItemImageGenToolCall \| OpenAI.InputItemCodeInterpreterToolCall \| OpenAI.InputItemLocalShellToolCall \| OpenAI.InputItemLocalShellToolCallOutput \| OpenAI.InputItemFunctionShellCallItemParam \| OpenAI.InputItemFunctionShellCallOutputItemParam \| OpenAI.InputItemApplyPatchToolCallItemParam \| OpenAI.InputItemApplyPatchToolCallOutputItemParam \| OpenAI.InputItemMcpListTools \| OpenAI.InputItemMcpApprovalRequest \| OpenAI.InputItemMcpApprovalResponse \| OpenAI.InputItemMcpToolCall \| OpenAI.InputItemCustomToolCallOutput \| OpenAI.InputItemCustomToolCall)[]` | No | Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](/docs/guides/text) - [Image inputs](/docs/guides/images) - [File inputs](/docs/guides/pdf-files) - [Conversation state](/docs/guides/conversation-state) - [Function calling](/docs/guides/function-calling) |
| `include` | `enum[] \| null` | No | _Enum:_ `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`, `memory_search_call.results` |
| `parallel_tool_calls` | `boolean \| null` | No | _Default:_ `true` |
| `store` | `boolean \| null` | No | _Default:_ `true` |
| `instructions` | `string \| null` | No |  |
| `stream` | `boolean \| null` | No |  |
| `stream_options` | `OpenAI.ResponseStreamOptions \| null` | No |  |
| `conversation` | `string \| OpenAI.ConversationParam-2 \| null` | No |  |
| `context_management` | `OpenAI.ContextManagementParam[] \| null` | No | Context management configuration for this request. |
| `max_output_tokens` | `OpenAI.integer \| null` | No |  |
| `agent_reference` | `AgentReference` | No | The agent to use for generating the response. |
| `structured_inputs` | `object` | No | The structured inputs to the response that can participate in prompt template substitution or tool argument bindings. |

### `reasoning` — `OpenAI.Reasoning | null`

**One of the following:**

#### `OpenAI.Reasoning` — `OpenAI.Reasoning`

**gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `effort` | `enum` | No | Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). 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`. _Enum:_ `none`, `minimal`, `low`, `medium`, `high`, `xhigh` |
| `summary` | `enum` | No | _Enum:_ `auto`, `concise`, `detailed` |
| `generate_summary` | `enum` | No | _Enum:_ `auto`, `concise`, `detailed` |

#### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

### `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](/docs/guides/text) - [Structured Outputs](/docs/guides/structured-outputs)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `format` | `OpenAI.TextResponseFormatJsonSchema \| OpenAI.TextResponseFormatConfigurationResponseFormatText \| OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject` | No | 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 [Structured Outputs guide](/docs/guides/structured-outputs). 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. |
| `verbosity` | `enum` | No | 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`. _Enum:_ `low`, `medium`, `high` |

#### `format` — `OpenAI.TextResponseFormatJsonSchema | OpenAI.TextResponseFormatConfigurationResponseFormatText | OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject`

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 [Structured Outputs guide](/docs/guides/structured-outputs). 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.

**One of the following:**

##### `json_schema` — `json_schema (OpenAI.TextResponseFormatJsonSchema)`

JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](/docs/guides/structured-outputs).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `json_schema`. _Constant:_ `json_schema` |
| `description` | `string` | No | A description of what the response format is for, used by the model to determine how to respond in the format. |
| `name` | `string` | Yes | 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. |
| `schema` | `OpenAI.ResponseFormatJsonSchemaSchema` | Yes | The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). |
| `strict` | `boolean \| null` | No |  |

##### `text` — `text (OpenAI.TextResponseFormatConfigurationResponseFormatText)`

Default response format. Used to generate text responses.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `text`. _Constant:_ `text` |

##### `json_object` — `json_object (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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `json_object`. _Constant:_ `json_object` |

### `tools` — `(BingGroundingTool | MicrosoftFabricPreviewTool | SharepointPreviewTool | AzureAISearchTool | OpenApiTool | BingCustomSearchPreviewTool | BrowserAutomationPreviewTool | AzureFunctionTool | CaptureStructuredOutputsTool | A2APreviewTool | WorkIQPreviewTool | FabricIQPreviewTool | MemorySearchPreviewTool | ToolboxSearchPreviewTool | OpenAI.CodeInterpreterTool | OpenAI.FunctionTool | OpenAI.FileSearchTool | OpenAI.ComputerUsePreviewTool | OpenAI.WebSearchTool | OpenAI.MCPTool | OpenAI.ImageGenTool | OpenAI.LocalShellToolParam | OpenAI.FunctionShellToolParam | OpenAI.CustomToolParam | OpenAI.WebSearchPreviewTool | OpenAI.ApplyPatchToolParam | OpenAI.ComputerTool | OpenAI.NamespaceToolParam | OpenAI.ToolSearchToolParam)[]`

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](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search). Learn more about [built-in tools](/docs/guides/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](/docs/guides/tools-connectors-mcp). - **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](/docs/guides/function-calling). You can also use custom tools to call your own code.

**One of the following:**

#### `bing_grounding` — `bing_grounding (BingGroundingTool)`

The input definition information for a bing grounding search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_grounding'. _Constant:_ `bing_grounding` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_grounding` | `BingGroundingSearchToolParameters` | Yes | The bing grounding search tool parameters. |

##### `bing_grounding` — `BingGroundingSearchToolParameters`

The bing grounding search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingGroundingSearchConfiguration[]` | Yes | The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. |

###### `search_configurations` — `BingGroundingSearchConfiguration[]`

The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool.

**Array of** `BingGroundingSearchConfiguration`**:**

Search configuration for Bing Grounding

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

#### `fabric_dataagent_preview` — `fabric_dataagent_preview (MicrosoftFabricPreviewTool)`

The input definition information for a Microsoft Fabric tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_dataagent_preview'. _Constant:_ `fabric_dataagent_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `fabric_dataagent_preview` | `FabricDataAgentToolParameters` | Yes | The fabric data agent tool parameters. |

##### `fabric_dataagent_preview` — `FabricDataAgentToolParameters`

The fabric data agent tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

###### `project_connections` — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

#### `sharepoint_grounding_preview` — `sharepoint_grounding_preview (SharepointPreviewTool)`

The input definition information for a sharepoint tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'sharepoint_grounding_preview'. _Constant:_ `sharepoint_grounding_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `sharepoint_grounding_preview` | `SharepointGroundingToolParameters` | Yes | The sharepoint grounding tool parameters. |

##### `sharepoint_grounding_preview` — `SharepointGroundingToolParameters`

The sharepoint grounding tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

###### `project_connections` — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

#### `azure_ai_search` — `azure_ai_search (AzureAISearchTool)`

The input definition information for an Azure AI search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'azure_ai_search'. _Constant:_ `azure_ai_search` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `azure_ai_search` | `AzureAISearchToolResource` | Yes | The azure ai search index resource. |

##### `azure_ai_search` — `AzureAISearchToolResource`

The azure ai search index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `indexes` | `AISearchIndexResource[]` | Yes | The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. |

###### `indexes` — `AISearchIndexResource[]`

The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent.

**Array of** `AISearchIndexResource`**:**

A AI Search Index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | No | An index connection ID in an IndexResource attached to this agent. |
| `index_name` | `string` | No | The name of an index in an IndexResource attached to this agent. |
| `query_type` | `enum` | No | Type of query in an AIIndexResource attached to this agent. _Enum:_ `simple`, `semantic`, `vector`, `vector_simple_hybrid`, `vector_semantic_hybrid` |
| `top_k` | `integer` | No | Number of documents to retrieve from search and present to the model. _Format:_ `int32` |
| `filter` | `string` | No | filter string for search resource. [Learn more here](https://learn.microsoft.com/azure/search/search-filters). |
| `index_asset_id` | `string` | No | Index asset id for search resource. |

#### `openapi` — `openapi (OpenApiTool)`

The input definition information for an OpenAPI tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'openapi'. _Constant:_ `openapi` |
| `openapi` | `OpenApiFunctionDefinition` | Yes | The openapi function definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `openapi` — `OpenApiFunctionDefinition`

The openapi function definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the function to be called. |
| `description` | `string` | No | A description of what the function does, used by the model to choose when and how to call the function. |
| `spec` | `object` | Yes | The openapi function shape, described as a JSON Schema object. |
| `auth` | `OpenApiAnonymousAuthDetails \| OpenApiProjectConnectionAuthDetails \| OpenApiManagedAuthDetails` | Yes | Open API authentication details |
| `default_params` | `string[]` | No | List of OpenAPI spec parameters that will use user-provided defaults |
| `functions` | `object[]` | No | List of function definitions used by OpenApi tool |

###### `auth` — `OpenApiAnonymousAuthDetails | OpenApiProjectConnectionAuthDetails | OpenApiManagedAuthDetails`

Open API authentication details

**One of the following:**

- **`anonymous`** — `anonymous (OpenApiAnonymousAuthDetails)`

Security details for OpenApi anonymous authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'anonymous'. _Constant:_ `anonymous` |

- **`project_connection`** — `project_connection (OpenApiProjectConnectionAuthDetails)`

Security details for OpenApi project connection authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'project_connection'. _Constant:_ `project_connection` |
| `security_scheme` | `OpenApiProjectConnectionSecurityScheme` | Yes | Project connection auth security details |

- **`security_scheme`** — `OpenApiProjectConnectionSecurityScheme`

Project connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for Project Connection auth type |

- **`managed_identity`** — `managed_identity (OpenApiManagedAuthDetails)`

Security details for OpenApi managed_identity authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'managed_identity'. _Constant:_ `managed_identity` |
| `security_scheme` | `OpenApiManagedSecurityScheme` | Yes | Connection auth security details |

- **`security_scheme`** — `OpenApiManagedSecurityScheme`

Connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `audience` | `string` | Yes | Authentication scope for managed_identity auth type |

###### `functions` — `object[]`

List of function definitions used by OpenApi tool

**Array of** `object`**:**

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

#### `bing_custom_search_preview` — `bing_custom_search_preview (BingCustomSearchPreviewTool)`

The input definition information for a Bing custom search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_custom_search_preview'. _Constant:_ `bing_custom_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_custom_search_preview` | `BingCustomSearchToolParameters` | Yes | The bing custom search tool parameters. |

##### `bing_custom_search_preview` — `BingCustomSearchToolParameters`

The bing custom search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingCustomSearchConfiguration[]` | Yes | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

###### `search_configurations` — `BingCustomSearchConfiguration[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `BingCustomSearchConfiguration`**:**

A bing custom search configuration.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

#### `browser_automation_preview` — `browser_automation_preview (BrowserAutomationPreviewTool)`

The input definition information for a Browser Automation Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation_preview'. _Constant:_ `browser_automation_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `browser_automation_preview` | `BrowserAutomationToolParameters` | Yes | The Browser Automation Tool parameters. |

##### `browser_automation_preview` — `BrowserAutomationToolParameters`

The Browser Automation Tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `connection` | `BrowserAutomationToolConnectionParameters` | Yes | The project connection parameters associated with the Browser Automation Tool. |

###### `connection` — `BrowserAutomationToolConnectionParameters`

The project connection parameters associated with the Browser Automation Tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | The ID of the project connection to your Azure Playwright resource. |

#### `azure_function` — `azure_function (AzureFunctionTool)`

The input definition information for an Azure Function Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation'. _Constant:_ `azure_function` |
| `azure_function` | `AzureFunctionDefinition` | Yes | The Azure Function Tool definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `azure_function` — `AzureFunctionDefinition`

The Azure Function Tool definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `function` | `object` | Yes | The definition of azure function and its parameters. |
| `input_binding` | `AzureFunctionBinding` | Yes | Input storage queue. The queue storage trigger runs a function as messages are added to it. |
| `output_binding` | `AzureFunctionBinding` | Yes | Output storage queue. The function writes output to this queue when the input items are processed. |

###### `function` — `object`

The definition of azure function and its parameters.

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

###### `input_binding` — `AzureFunctionBinding`

Input storage queue. The queue storage trigger runs a function as messages are added to it.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

###### `output_binding` — `AzureFunctionBinding`

Output storage queue. The function writes output to this queue when the input items are processed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

#### `capture_structured_outputs` — `capture_structured_outputs (CaptureStructuredOutputsTool)`

A tool for capturing structured outputs

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `capture_structured_outputs`. _Constant:_ `capture_structured_outputs` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `outputs` | `StructuredOutputDefinition` | Yes | The structured outputs to capture from the model. |

##### `outputs` — `StructuredOutputDefinition`

The structured outputs to capture from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the structured output. |
| `description` | `string` | Yes | A description of the output to emit. Used by the model to determine when to emit the output. |
| `schema` | `object` | Yes | The JSON schema for the structured output. |
| `strict` | `boolean \| null` | Yes | Whether to enforce strict validation. Default `true`. |

#### `a2a_preview` — `a2a_preview (A2APreviewTool)`

An agent implementing the A2A protocol.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `"a2a_preview`. _Constant:_ `a2a_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `base_url` | `string` | No | Base URL of the agent. _Format:_ `uri` |
| `agent_card_path` | `string` | No | The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json` |
| `project_connection_id` | `string` | No | The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server. |

#### `work_iq_preview` — `work_iq_preview (WorkIQPreviewTool)`

A WorkIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'work_iq_preview'. _Constant:_ `work_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the WorkIQ project connection. |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

#### `fabric_iq_preview` — `fabric_iq_preview (FabricIQPreviewTool)`

A FabricIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_iq_preview'. _Constant:_ `fabric_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the FabricIQ project connection. |
| `server_label` | `string` | No | (Optional) The label of the FabricIQ MCP server to connect to. |
| `server_url` | `string` | No | (Optional) The URL of the FabricIQ MCP server. If not provided, the URL from the project connection will be used. _Format:_ `uri` |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| string \| null` | No | (Optional) Whether the agent requires approval before executing actions. Default is always. _Default:_ `"always"` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `require_approval` — `OpenAI.MCPToolRequireApproval | string | null`

(Optional) Whether the agent requires approval before executing actions. Default is always.

**One of the following:**

###### `OpenAI.MCPToolRequireApproval` — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

###### `string` — `string`

| Type | Description |
|------|-------------|
| `string` | — |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `memory_search_preview` — `memory_search_preview (MemorySearchPreviewTool)`

A tool for integrating memories into the agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `memory_search_preview`. _Constant:_ `memory_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `memory_store_name` | `string` | Yes | The name of the memory store to use. |
| `scope` | `string` | Yes | The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user. |
| `search_options` | `MemorySearchOptions` | No | Options for searching the memory store. |
| `update_delay` | `integer` | No | Time to wait before updating memories after inactivity (seconds). Default 300. _Default:_ `300` _Format:_ `int32` |

##### `search_options` — `MemorySearchOptions`

Options for searching the memory store.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `max_memories` | `integer` | No | Maximum number of memory items to return. _Format:_ `int32` |

#### `toolbox_search_preview` — `toolbox_search_preview (ToolboxSearchPreviewTool)`

A tool for searching over the agent's toolbox. When present, deferred tools are hidden from `tools/list` and only discoverable via `search_tools` queries at runtime.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `toolbox_search_preview`. _Constant:_ `toolbox_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

#### `code_interpreter` — `code_interpreter (OpenAI.CodeInterpreterTool)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool. Always `code_interpreter`. _Constant:_ `code_interpreter` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `container` | `string \| OpenAI.AutoCodeInterpreterToolParam` | No | 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. If not provided, the service assumes auto. |

##### `container` — `string | OpenAI.AutoCodeInterpreterToolParam`

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. If not provided, the service assumes auto.

**One of the following:**

###### `string` — `string`

| Type | Description |
|------|-------------|
| `string` | — |

###### `OpenAI.AutoCodeInterpreterToolParam` — `OpenAI.AutoCodeInterpreterToolParam`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Always `auto`. _Default:_ `"auto"` _Constant:_ `auto` |
| `file_ids` | `string[]` | No | An optional list of uploaded files to make available to your code. |
| `memory_limit` | `enum` | No | _Enum:_ `1g`, `4g`, `16g`, `64g` |
| `network_policy` | `OpenAI.ContainerNetworkPolicyDisabledParam \| OpenAI.ContainerNetworkPolicyAllowlistParam` | No | Network access policy for the container. |

- **`network_policy`** — `OpenAI.ContainerNetworkPolicyDisabledParam | OpenAI.ContainerNetworkPolicyAllowlistParam`

Network access policy for the container.

**One of the following:**

- **`disabled`** — `disabled (OpenAI.ContainerNetworkPolicyDisabledParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Disable outbound network access. Always `disabled`. _Default:_ `"disabled"` _Constant:_ `disabled` |

- **`allowlist`** — `allowlist (OpenAI.ContainerNetworkPolicyAllowlistParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Allow outbound network access only to specified domains. Always `allowlist`. _Default:_ `"allowlist"` _Constant:_ `allowlist` |
| `allowed_domains` | `string[]` | Yes | A list of allowed domains when type is `allowlist`. |

#### `function` — `function (OpenAI.FunctionTool)`

Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool. Always `function`. _Default:_ `"function"` _Constant:_ `function` |
| `name` | `string` | Yes | The name of the function to call. |
| `description` | `string \| null` | No |  |
| `parameters` | `object \| null` | Yes |  |
| `strict` | `boolean \| null` | Yes |  |
| `defer_loading` | `boolean` | No | Whether this function is deferred and loaded via tool search. |

#### `file_search` — `file_search (OpenAI.FileSearchTool)`

A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool. Always `file_search`. _Default:_ `"file_search"` _Constant:_ `file_search` |
| `vector_store_ids` | `string[]` | Yes | The IDs of the vector stores to search. |
| `max_num_results` | `OpenAI.integer` | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. _Format:_ `int64` |
| `ranking_options` | `OpenAI.RankingOptions` | No | Ranking options for search. |
| `filters` | `OpenAI.ComparisonFilter \| OpenAI.CompoundFilter \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `ranking_options` — `OpenAI.RankingOptions`

Ranking options for search.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `ranker` | `OpenAI.RankerVersionType` | No | The ranker to use for the file search. _Enum:_ `auto`, `default-2024-11-15` |
| `score_threshold` | `OpenAI.numeric` | No | 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. _Format:_ `double` |
| `hybrid_search` | `OpenAI.HybridSearchOptions` | No | Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. |

###### `hybrid_search` — `OpenAI.HybridSearchOptions`

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `embedding_weight` | `OpenAI.numeric` | Yes | The weight of the embedding in the reciprocal ranking fusion. _Format:_ `double` |
| `text_weight` | `OpenAI.numeric` | Yes | The weight of the text in the reciprocal ranking fusion. _Format:_ `double` |

##### `filters` — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter | null`

**One of the following:**

###### `OpenAI.Filters` — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter`

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`OpenAI.CompoundFilter`** — `OpenAI.CompoundFilter`

Combine multiple filters using `and` or `or`.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Type of operation: `and` or `or`. _Enum:_ `and`, `or` |
| `filters` | `(OpenAI.ComparisonFilter \| any)[]` | Yes | Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. |

- **`filters`** — `(OpenAI.ComparisonFilter | any)[]`

Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`any`** — `any`

| Type | Description |
|------|-------------|
| `any` | — |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `computer_use_preview` — `computer_use_preview (OpenAI.ComputerUsePreviewTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer use tool. Always `computer_use_preview`. _Default:_ `"computer_use_preview"` _Constant:_ `computer_use_preview` |
| `environment` | `OpenAI.ComputerEnvironment` | Yes | The type of computer environment to control. _Enum:_ `windows`, `mac`, `linux`, `ubuntu`, `browser` |
| `display_width` | `OpenAI.integer` | Yes | The width of the computer display. _Format:_ `int64` |
| `display_height` | `OpenAI.integer` | Yes | The height of the computer display. _Format:_ `int64` |

#### `web_search` — `web_search (OpenAI.WebSearchTool)`

Search the Internet for sources related to the prompt. Learn more about the [web search tool](/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. _Default:_ `"web_search"` _Constant:_ `web_search` |
| `filters` | `OpenAI.WebSearchToolFilters \| null` | No |  |
| `user_location` | `OpenAI.WebSearchApproximateLocation \| null` | No |  |
| `search_context_size` | `enum` | No | 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. _Default:_ `"medium"` _Enum:_ `low`, `medium`, `high` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `custom_search_configuration` | `WebSearchConfiguration` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

##### `filters` — `OpenAI.WebSearchToolFilters | null`

**One of the following:**

###### `OpenAI.WebSearchToolFilters` — `OpenAI.WebSearchToolFilters`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `allowed_domains` | `string[] \| null` | No |  |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `user_location` — `OpenAI.WebSearchApproximateLocation | null`

**One of the following:**

###### `OpenAI.WebSearchApproximateLocation` — `OpenAI.WebSearchApproximateLocation`

The approximate location of the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `custom_search_configuration` — `WebSearchConfiguration`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing custom search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |

#### `mcp` — `mcp (OpenAI.MCPTool)`

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the MCP tool. Always `mcp`. _Constant:_ `mcp` |
| `server_label` | `string` | Yes | A label for this MCP server, used to identify it in tool calls. |
| `server_url` | `string` | No | The URL for the MCP server. One of `server_url` or `connector_id` must be provided. _Format:_ `uri` |
| `connector_id` | `enum` | No | Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors [here](/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` _Enum:_ `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint` |
| `authorization` | `string` | No | An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. |
| `server_description` | `string` | No | Optional description of the MCP server, used to provide more context. |
| `headers` | `object \| null` | No |  |
| `allowed_tools` | `string[] \| OpenAI.MCPToolFilter \| null` | No |  |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| enum \| null` | No | _Default:_ `"always"` _Enum:_ `always`, `never` |
| `defer_loading` | `boolean` | No | Whether this MCP tool is deferred and discovered via tool search. |
| `project_connection_id` | `string` | No | The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `allowed_tools` — `string[] | OpenAI.MCPToolFilter | null`

**One of the following:**

###### `string[]` — `string[]`

Type: `string[]`

###### `OpenAI.MCPToolFilter` — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `require_approval` — `OpenAI.MCPToolRequireApproval | enum | null`

**One of the following:**

###### `OpenAI.MCPToolRequireApproval` — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

###### `enum` — `enum`

| Type | Description |
|------|-------------|
| `enum` | _Enum:_ `always`, `never` |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `image_generation` — `image_generation (OpenAI.ImageGenTool)`

A tool that generates images using the GPT image models.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation tool. Always `image_generation`. _Default:_ `"image_generation"` _Constant:_ `image_generation` |
| `model` | `enum` | No | _Default:_ `"gpt-image-1"` _Enum:_ `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5` |
| `quality` | `enum` | No | The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `low`, `medium`, `high`, `auto` |
| `size` | `enum` | No | The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. _Default:_ `"auto"` _Enum:_ `1024x1024`, `1024x1536`, `1536x1024`, `auto` |
| `output_format` | `enum` | No | The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. _Default:_ `"png"` _Enum:_ `png`, `webp`, `jpeg` |
| `output_compression` | `OpenAI.integer` | No | Compression level for the output image. Default: 100. _Default:_ `100` _Format:_ `int64` |
| `moderation` | `enum` | No | Moderation level for the generated image. Default: `auto`. _Default:_ `"auto"` _Enum:_ `auto`, `low` |
| `background` | `enum` | No | Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `transparent`, `opaque`, `auto` |
| `input_fidelity` | `enum` | No | _Enum:_ `high`, `low` |
| `input_image_mask` | `OpenAI.ImageGenToolInputImageMask` | No | Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). |
| `partial_images` | `OpenAI.integer` | No | Number of partial images to generate in streaming mode, from 0 (default value) to 3. _Format:_ `int64` |
| `action` | `OpenAI.ImageGenActionEnum` | No | Whether to generate a new image or edit an existing image. Default: `auto`. _Enum:_ `generate`, `edit`, `auto` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `input_image_mask` — `OpenAI.ImageGenToolInputImageMask`

Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `image_url` | `string` | No | _Format:_ `uri` |
| `file_id` | `string` | No |  |

#### `local_shell` — `local_shell (OpenAI.LocalShellToolParam)`

A tool that allows the model to execute shell commands in a local environment.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool. Always `local_shell`. _Default:_ `"local_shell"` _Constant:_ `local_shell` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

#### `shell` — `shell (OpenAI.FunctionShellToolParam)`

A tool that allows the model to execute shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell tool. Always `shell`. _Default:_ `"shell"` _Constant:_ `shell` |
| `environment` | `OpenAI.FunctionShellToolParamEnvironment \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `environment` — `OpenAI.FunctionShellToolParamEnvironment | null`

**One of the following:**

###### `OpenAI.FunctionShellToolParamEnvironment` — `OpenAI.FunctionShellToolParamEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `container_auto`, `local`, `container_reference` |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `custom` — `custom (OpenAI.CustomToolParam)`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

##### `format` — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

###### `text` — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

###### `grammar` — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

#### `web_search_preview` — `web_search_preview (OpenAI.WebSearchPreviewTool)`

This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. _Default:_ `"web_search_preview"` _Constant:_ `web_search_preview` |
| `user_location` | `OpenAI.ApproximateLocation \| null` | No |  |
| `search_context_size` | `OpenAI.SearchContextSize` | No | 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. _Enum:_ `low`, `medium`, `high` |
| `search_content_types` | `OpenAI.SearchContentType[]` | No | _Enum:_ `text`, `image` |

##### `user_location` — `OpenAI.ApproximateLocation | null`

**One of the following:**

###### `OpenAI.ApproximateLocation` — `OpenAI.ApproximateLocation`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

###### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `apply_patch` — `apply_patch (OpenAI.ApplyPatchToolParam)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `apply_patch`. _Default:_ `"apply_patch"` _Constant:_ `apply_patch` |

#### `computer` — `computer (OpenAI.ComputerTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool. Always `computer`. _Default:_ `"computer"` _Constant:_ `computer` |

#### `namespace` — `namespace (OpenAI.NamespaceToolParam)`

Groups function/custom tools under a shared namespace.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `namespace`. _Default:_ `"namespace"` _Constant:_ `namespace` |
| `name` | `string` | Yes | The namespace name used in tool calls (for example, `crm`). |
| `description` | `string` | Yes | A description of the namespace shown to the model. |
| `tools` | `(OpenAI.FunctionToolParam \| OpenAI.CustomToolParam)[]` | Yes | The function/custom tools available inside this namespace. |

##### `tools` — `(OpenAI.FunctionToolParam | OpenAI.CustomToolParam)[]`

The function/custom tools available inside this namespace.

**One of the following:**

###### `OpenAI.FunctionToolParam` — `OpenAI.FunctionToolParam`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes |  |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |
| `strict` | `boolean \| null` | No |  |
| `type` | `enum` | Yes | _Default:_ `"function"` _Constant:_ `function` |
| `defer_loading` | `boolean` | No | Whether this function should be deferred and discovered via tool search. |

###### `OpenAI.CustomToolParam` — `OpenAI.CustomToolParam`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

#### `tool_search` — `tool_search (OpenAI.ToolSearchToolParam)`

Hosted or BYOT tool search configuration for deferred tools.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `tool_search`. _Default:_ `"tool_search"` _Constant:_ `tool_search` |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search is executed by the server or by the client. _Enum:_ `server`, `client` |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |

### `tool_choice` — `OpenAI.ToolChoiceOptions | OpenAI.ToolChoiceParam`

**One of the following:**

#### `OpenAI.ToolChoiceOptions` — `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.

| Type | Description |
|------|-------------|
| `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. _Enum:_ `none`, `auto`, `required` |

#### `OpenAI.ToolChoiceParam` — `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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `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`, `computer`, `computer_use` |

### `prompt` — `OpenAI.Prompt`

Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The unique identifier of the prompt template to use. |
| `version` | `string \| null` | No |  |
| `variables` | `OpenAI.ResponsePromptVariables \| null` | No |  |

### `input` — `string | (OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[]`

Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](/docs/guides/text) - [Image inputs](/docs/guides/images) - [File inputs](/docs/guides/pdf-files) - [Conversation state](/docs/guides/conversation-state) - [Function calling](/docs/guides/function-calling)

**One of the following:**

#### `string` — `string`

| Type | Description |
|------|-------------|
| `string` | — |

#### `(OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[]` — `(OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[]`

**One of the following:**

##### `message` — `message (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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the message input. Always `message`. _Constant:_ `message` |
| `role` | `enum` | Yes | The role of the message input. One of `user`, `assistant`, `system`, or `developer`. _Enum:_ `user`, `assistant`, `system`, `developer` |
| `content` | `string \| (OpenAI.InputContentInputTextContent \| OpenAI.InputContentInputImageContent \| OpenAI.InputContentInputFileContent)[]` | Yes | Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. |
| `phase` | `enum` | No | _Enum:_ `commentary`, `final_answer` |
| `status` | `enum` | No | The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `content` — `string | (OpenAI.InputContentInputTextContent | OpenAI.InputContentInputImageContent | OpenAI.InputContentInputFileContent)[]`

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

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.InputMessageContentList`** — `OpenAI.InputMessageContentList ((OpenAI.InputContentInputTextContent | OpenAI.InputContentInputImageContent | OpenAI.InputContentInputFileContent)[])`

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

**One of the following:**

- **`input_text`** — `input_text (OpenAI.InputContentInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.InputContentInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.InputContentInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

##### `item_reference` — `item_reference (OpenAI.ItemReferenceParam)`

An internal identifier for an item to reference.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of item to reference. Always `item_reference`. _Default:_ `"item_reference"` _Constant:_ `item_reference` |
| `id` | `string` | Yes | The ID of the item to reference. |

##### `output_message` — `output_message (OpenAI.InputItemOutputMessage)`

An output message from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output message. Always `message`. _Constant:_ `output_message` |
| `id` | `string` | Yes | The unique ID of the output message. |
| `role` | `enum` | Yes | The role of the output message. Always `assistant`. _Constant:_ `assistant` |
| `content` | `(OpenAI.OutputMessageContentOutputTextContent \| OpenAI.OutputMessageContentRefusalContent)[]` | Yes | The content of the output message. |
| `phase` | `enum` | No | _Enum:_ `commentary`, `final_answer` |
| `status` | `enum` | Yes | The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `content` — `(OpenAI.OutputMessageContentOutputTextContent | OpenAI.OutputMessageContentRefusalContent)[]`

The content of the output message.

**One of the following:**

- **`output_text`** — `output_text (OpenAI.OutputMessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`refusal`** — `refusal (OpenAI.OutputMessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

##### `file_search_call` — `file_search_call (OpenAI.InputItemFileSearchToolCall)`

The results of a file search tool call. See the [file search guide](/docs/guides/tools-file-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool call. Always `file_search_call`. _Constant:_ `file_search_call` |
| `id` | `string` | Yes | The unique ID of the file search tool call. |
| `status` | `enum` | Yes | The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, _Enum:_ `in_progress`, `searching`, `completed`, `incomplete`, `failed` |
| `queries` | `string[]` | Yes | The queries used to search for files. |
| `results` | `OpenAI.FileSearchToolCallResults[] \| null` | No |  |

###### `results` — `OpenAI.FileSearchToolCallResults[] | null`

**One of the following:**

- **`OpenAI.FileSearchToolCallResults[]`** — `OpenAI.FileSearchToolCallResults[]`

**Array of** `OpenAI.FileSearchToolCallResults`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `file_id` | `string` | No |  |
| `text` | `string` | No |  |
| `filename` | `string` | No |  |
| `attributes` | `OpenAI.VectorStoreFileAttributes \| null` | No |  |
| `score` | `number` | No | _Format:_ `float` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `computer_call` — `computer_call (OpenAI.InputItemComputerToolCall)`

A tool call to a computer use tool. See the [computer use guide](/docs/guides/tools-computer-use) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer call. Always `computer_call`. _Default:_ `"computer_call"` _Constant:_ `computer_call` |
| `id` | `string` | Yes | The unique ID of the computer call. |
| `call_id` | `string` | Yes | An identifier used when responding to the tool call with output. |
| `action` | `OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam` | No |  |
| `actions` | `(OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam)[]` | No | Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. |
| `pending_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[]` | Yes | The pending safety checks for the computer call. |
| `status` | `enum` | Yes | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `action` — `OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam`

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

###### `actions` — `(OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam)[]`

Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields.

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

###### `pending_safety_checks` — `OpenAI.ComputerCallSafetyCheckParam[]`

The pending safety checks for the computer call.

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

##### `computer_call_output` — `computer_call_output (OpenAI.InputItemComputerCallOutputItemParam)`

The output of a computer tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool call output. Always `computer_call_output`. _Default:_ `"computer_call_output"` _Constant:_ `computer_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The ID of the computer tool call that produced the output. |
| `output` | `OpenAI.ComputerScreenshotImage` | Yes | A computer screenshot image used with the computer use tool. |
| `acknowledged_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[] \| null` | No |  |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `output` — `OpenAI.ComputerScreenshotImage`

A computer screenshot image used with the computer use tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string` | No | The URL of the screenshot image. _Format:_ `uri` |
| `file_id` | `string` | No | The identifier of an uploaded file that contains the screenshot. |

###### `acknowledged_safety_checks` — `OpenAI.ComputerCallSafetyCheckParam[] | null`

**One of the following:**

- **`OpenAI.ComputerCallSafetyCheckParam[]`** — `OpenAI.ComputerCallSafetyCheckParam[]`

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `web_search_call` — `web_search_call (OpenAI.InputItemWebSearchToolCall)`

The results of a web search tool call. See the [web search guide](/docs/guides/tools-web-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool call. Always `web_search_call`. _Constant:_ `web_search_call` |
| `id` | `string` | Yes | The unique ID of the web search tool call. |
| `status` | `enum` | Yes | The status of the web search tool call. _Enum:_ `in_progress`, `searching`, `completed`, `failed` |
| `action` | `OpenAI.WebSearchActionSearch \| OpenAI.WebSearchActionOpenPage \| OpenAI.WebSearchActionFind` | Yes | 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_in_page). |

###### `action` — `OpenAI.WebSearchActionSearch | OpenAI.WebSearchActionOpenPage | 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_in_page).

**One of the following:**

- **`OpenAI.WebSearchActionSearch`** — `OpenAI.WebSearchActionSearch`

Action type "search" - Performs a web search query.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `search` |
| `query` | `string` | Yes | [DEPRECATED] The search query. |
| `queries` | `string[]` | No | The search queries. |
| `sources` | `OpenAI.WebSearchActionSearchSources[]` | No | The sources used in the search. |

- **`sources`** — `OpenAI.WebSearchActionSearchSources[]`

The sources used in the search.

**Array of** `OpenAI.WebSearchActionSearchSources`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `url` |
| `url` | `string` | Yes | _Format:_ `uri` |

- **`OpenAI.WebSearchActionOpenPage`** — `OpenAI.WebSearchActionOpenPage`

Action type "open_page" - Opens a specific URL from search results.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `open_page` |
| `url` | `string \| null` | No | The URL opened by the model. |

- **`OpenAI.WebSearchActionFind`** — `OpenAI.WebSearchActionFind`

Action type "find_in_page": Searches for a pattern within a loaded page.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `find_in_page` |
| `url` | `string` | Yes | The URL of the page searched for the pattern. _Format:_ `uri` |
| `pattern` | `string` | Yes | The pattern or text to search for within the page. |

##### `function_call` — `function_call (OpenAI.InputItemFunctionToolCall)`

A tool call to run a function. See the [function calling guide](/docs/guides/function-calling) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call. Always `function_call`. _Constant:_ `function_call` |
| `id` | `string` | Yes | The unique ID of the function tool call. |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `namespace` | `string` | No | The namespace of the function to run. |
| `name` | `string` | Yes | The name of the function to run. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the function. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

##### `function_call_output` — `function_call_output (OpenAI.InputItemFunctionCallOutputItemParam)`

The output of a function tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call output. Always `function_call_output`. _Default:_ `"function_call_output"` _Constant:_ `function_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `output` | `string \| (OpenAI.InputTextContentParam \| OpenAI.InputImageContentParamAutoParam \| OpenAI.InputFileContentParam)[]` | Yes | Text, image, or file output of the function tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `output` — `string | (OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`

Text, image, or file output of the function tool call.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`** — `(OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`

**One of the following:**

- **`OpenAI.InputTextContentParam`** — `OpenAI.InputTextContentParam`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`OpenAI.InputImageContentParamAutoParam`** — `OpenAI.InputImageContentParamAutoParam`

An image input to the model. Learn about [image inputs](/docs/guides/vision)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `enum` | No | _Enum:_ `low`, `high`, `auto`, `original` |

- **`OpenAI.InputFileContentParam`** — `OpenAI.InputFileContentParam`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string \| null` | No |  |
| `file_data` | `string \| null` | No |  |
| `file_url` | `string \| null` | No |  |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

##### `tool_search_call` — `tool_search_call (OpenAI.InputItemToolSearchCallItemParam)`

An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The item type. Always `tool_search_call`. _Default:_ `"tool_search_call"` _Constant:_ `tool_search_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string \| null` | No |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `arguments` | `OpenAI.EmptyModelParam` | Yes | The arguments supplied to the tool search call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

##### `tool_search_output` — `tool_search_output (OpenAI.InputItemToolSearchOutputItemParam)`

An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The item type. Always `tool_search_output`. _Default:_ `"tool_search_output"` _Constant:_ `tool_search_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string \| null` | No |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `tools` | `(BingGroundingTool \| MicrosoftFabricPreviewTool \| SharepointPreviewTool \| AzureAISearchTool \| OpenApiTool \| BingCustomSearchPreviewTool \| BrowserAutomationPreviewTool \| AzureFunctionTool \| CaptureStructuredOutputsTool \| A2APreviewTool \| WorkIQPreviewTool \| FabricIQPreviewTool \| MemorySearchPreviewTool \| ToolboxSearchPreviewTool \| OpenAI.CodeInterpreterTool \| OpenAI.FunctionTool \| OpenAI.FileSearchTool \| OpenAI.ComputerUsePreviewTool \| OpenAI.WebSearchTool \| OpenAI.MCPTool \| OpenAI.ImageGenTool \| OpenAI.LocalShellToolParam \| OpenAI.FunctionShellToolParam \| OpenAI.CustomToolParam \| OpenAI.WebSearchPreviewTool \| OpenAI.ApplyPatchToolParam \| OpenAI.ComputerTool \| OpenAI.NamespaceToolParam \| OpenAI.ToolSearchToolParam)[]` | Yes | The loaded tool definitions returned by the tool search output. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `tools` — `(BingGroundingTool | MicrosoftFabricPreviewTool | SharepointPreviewTool | AzureAISearchTool | OpenApiTool | BingCustomSearchPreviewTool | BrowserAutomationPreviewTool | AzureFunctionTool | CaptureStructuredOutputsTool | A2APreviewTool | WorkIQPreviewTool | FabricIQPreviewTool | MemorySearchPreviewTool | ToolboxSearchPreviewTool | OpenAI.CodeInterpreterTool | OpenAI.FunctionTool | OpenAI.FileSearchTool | OpenAI.ComputerUsePreviewTool | OpenAI.WebSearchTool | OpenAI.MCPTool | OpenAI.ImageGenTool | OpenAI.LocalShellToolParam | OpenAI.FunctionShellToolParam | OpenAI.CustomToolParam | OpenAI.WebSearchPreviewTool | OpenAI.ApplyPatchToolParam | OpenAI.ComputerTool | OpenAI.NamespaceToolParam | OpenAI.ToolSearchToolParam)[]`

The loaded tool definitions returned by the tool search output.

**One of the following:**

- **`bing_grounding`** — `bing_grounding (BingGroundingTool)`

The input definition information for a bing grounding search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_grounding'. _Constant:_ `bing_grounding` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_grounding` | `BingGroundingSearchToolParameters` | Yes | The bing grounding search tool parameters. |

- **`bing_grounding`** — `BingGroundingSearchToolParameters`

The bing grounding search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingGroundingSearchConfiguration[]` | Yes | The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. |

- **`search_configurations`** — `BingGroundingSearchConfiguration[]`

The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool.

**Array of** `BingGroundingSearchConfiguration`**:**

Search configuration for Bing Grounding

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`fabric_dataagent_preview`** — `fabric_dataagent_preview (MicrosoftFabricPreviewTool)`

The input definition information for a Microsoft Fabric tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_dataagent_preview'. _Constant:_ `fabric_dataagent_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `fabric_dataagent_preview` | `FabricDataAgentToolParameters` | Yes | The fabric data agent tool parameters. |

- **`fabric_dataagent_preview`** — `FabricDataAgentToolParameters`

The fabric data agent tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`sharepoint_grounding_preview`** — `sharepoint_grounding_preview (SharepointPreviewTool)`

The input definition information for a sharepoint tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'sharepoint_grounding_preview'. _Constant:_ `sharepoint_grounding_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `sharepoint_grounding_preview` | `SharepointGroundingToolParameters` | Yes | The sharepoint grounding tool parameters. |

- **`sharepoint_grounding_preview`** — `SharepointGroundingToolParameters`

The sharepoint grounding tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`azure_ai_search`** — `azure_ai_search (AzureAISearchTool)`

The input definition information for an Azure AI search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'azure_ai_search'. _Constant:_ `azure_ai_search` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `azure_ai_search` | `AzureAISearchToolResource` | Yes | The azure ai search index resource. |

- **`azure_ai_search`** — `AzureAISearchToolResource`

The azure ai search index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `indexes` | `AISearchIndexResource[]` | Yes | The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. |

- **`indexes`** — `AISearchIndexResource[]`

The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent.

**Array of** `AISearchIndexResource`**:**

A AI Search Index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | No | An index connection ID in an IndexResource attached to this agent. |
| `index_name` | `string` | No | The name of an index in an IndexResource attached to this agent. |
| `query_type` | `enum` | No | Type of query in an AIIndexResource attached to this agent. _Enum:_ `simple`, `semantic`, `vector`, `vector_simple_hybrid`, `vector_semantic_hybrid` |
| `top_k` | `integer` | No | Number of documents to retrieve from search and present to the model. _Format:_ `int32` |
| `filter` | `string` | No | filter string for search resource. [Learn more here](https://learn.microsoft.com/azure/search/search-filters). |
| `index_asset_id` | `string` | No | Index asset id for search resource. |

- **`openapi`** — `openapi (OpenApiTool)`

The input definition information for an OpenAPI tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'openapi'. _Constant:_ `openapi` |
| `openapi` | `OpenApiFunctionDefinition` | Yes | The openapi function definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`openapi`** — `OpenApiFunctionDefinition`

The openapi function definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the function to be called. |
| `description` | `string` | No | A description of what the function does, used by the model to choose when and how to call the function. |
| `spec` | `object` | Yes | The openapi function shape, described as a JSON Schema object. |
| `auth` | `OpenApiAnonymousAuthDetails \| OpenApiProjectConnectionAuthDetails \| OpenApiManagedAuthDetails` | Yes | Open API authentication details |
| `default_params` | `string[]` | No | List of OpenAPI spec parameters that will use user-provided defaults |
| `functions` | `object[]` | No | List of function definitions used by OpenApi tool |

- **`auth`** — `OpenApiAnonymousAuthDetails | OpenApiProjectConnectionAuthDetails | OpenApiManagedAuthDetails`

Open API authentication details

**One of the following:**

- **`anonymous`** — `anonymous (OpenApiAnonymousAuthDetails)`

Security details for OpenApi anonymous authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'anonymous'. _Constant:_ `anonymous` |

- **`project_connection`** — `project_connection (OpenApiProjectConnectionAuthDetails)`

Security details for OpenApi project connection authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'project_connection'. _Constant:_ `project_connection` |
| `security_scheme` | `OpenApiProjectConnectionSecurityScheme` | Yes | Project connection auth security details |

- **`security_scheme`** — `OpenApiProjectConnectionSecurityScheme`

Project connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for Project Connection auth type |

- **`managed_identity`** — `managed_identity (OpenApiManagedAuthDetails)`

Security details for OpenApi managed_identity authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'managed_identity'. _Constant:_ `managed_identity` |
| `security_scheme` | `OpenApiManagedSecurityScheme` | Yes | Connection auth security details |

- **`security_scheme`** — `OpenApiManagedSecurityScheme`

Connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `audience` | `string` | Yes | Authentication scope for managed_identity auth type |

- **`functions`** — `object[]`

List of function definitions used by OpenApi tool

**Array of** `object`**:**

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

- **`bing_custom_search_preview`** — `bing_custom_search_preview (BingCustomSearchPreviewTool)`

The input definition information for a Bing custom search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_custom_search_preview'. _Constant:_ `bing_custom_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_custom_search_preview` | `BingCustomSearchToolParameters` | Yes | The bing custom search tool parameters. |

- **`bing_custom_search_preview`** — `BingCustomSearchToolParameters`

The bing custom search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingCustomSearchConfiguration[]` | Yes | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`search_configurations`** — `BingCustomSearchConfiguration[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `BingCustomSearchConfiguration`**:**

A bing custom search configuration.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`browser_automation_preview`** — `browser_automation_preview (BrowserAutomationPreviewTool)`

The input definition information for a Browser Automation Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation_preview'. _Constant:_ `browser_automation_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `browser_automation_preview` | `BrowserAutomationToolParameters` | Yes | The Browser Automation Tool parameters. |

- **`browser_automation_preview`** — `BrowserAutomationToolParameters`

The Browser Automation Tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `connection` | `BrowserAutomationToolConnectionParameters` | Yes | The project connection parameters associated with the Browser Automation Tool. |

- **`connection`** — `BrowserAutomationToolConnectionParameters`

The project connection parameters associated with the Browser Automation Tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | The ID of the project connection to your Azure Playwright resource. |

- **`azure_function`** — `azure_function (AzureFunctionTool)`

The input definition information for an Azure Function Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation'. _Constant:_ `azure_function` |
| `azure_function` | `AzureFunctionDefinition` | Yes | The Azure Function Tool definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`azure_function`** — `AzureFunctionDefinition`

The Azure Function Tool definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `function` | `object` | Yes | The definition of azure function and its parameters. |
| `input_binding` | `AzureFunctionBinding` | Yes | Input storage queue. The queue storage trigger runs a function as messages are added to it. |
| `output_binding` | `AzureFunctionBinding` | Yes | Output storage queue. The function writes output to this queue when the input items are processed. |

- **`function`** — `object`

The definition of azure function and its parameters.

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

- **`input_binding`** — `AzureFunctionBinding`

Input storage queue. The queue storage trigger runs a function as messages are added to it.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`output_binding`** — `AzureFunctionBinding`

Output storage queue. The function writes output to this queue when the input items are processed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`capture_structured_outputs`** — `capture_structured_outputs (CaptureStructuredOutputsTool)`

A tool for capturing structured outputs

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `capture_structured_outputs`. _Constant:_ `capture_structured_outputs` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `outputs` | `StructuredOutputDefinition` | Yes | The structured outputs to capture from the model. |

- **`outputs`** — `StructuredOutputDefinition`

The structured outputs to capture from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the structured output. |
| `description` | `string` | Yes | A description of the output to emit. Used by the model to determine when to emit the output. |
| `schema` | `object` | Yes | The JSON schema for the structured output. |
| `strict` | `boolean \| null` | Yes | Whether to enforce strict validation. Default `true`. |

- **`a2a_preview`** — `a2a_preview (A2APreviewTool)`

An agent implementing the A2A protocol.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `"a2a_preview`. _Constant:_ `a2a_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `base_url` | `string` | No | Base URL of the agent. _Format:_ `uri` |
| `agent_card_path` | `string` | No | The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json` |
| `project_connection_id` | `string` | No | The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server. |

- **`work_iq_preview`** — `work_iq_preview (WorkIQPreviewTool)`

A WorkIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'work_iq_preview'. _Constant:_ `work_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the WorkIQ project connection. |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`fabric_iq_preview`** — `fabric_iq_preview (FabricIQPreviewTool)`

A FabricIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_iq_preview'. _Constant:_ `fabric_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the FabricIQ project connection. |
| `server_label` | `string` | No | (Optional) The label of the FabricIQ MCP server to connect to. |
| `server_url` | `string` | No | (Optional) The URL of the FabricIQ MCP server. If not provided, the URL from the project connection will be used. _Format:_ `uri` |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| string \| null` | No | (Optional) Whether the agent requires approval before executing actions. Default is always. _Default:_ `"always"` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | string | null`

(Optional) Whether the agent requires approval before executing actions. Default is always.

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`memory_search_preview`** — `memory_search_preview (MemorySearchPreviewTool)`

A tool for integrating memories into the agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `memory_search_preview`. _Constant:_ `memory_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `memory_store_name` | `string` | Yes | The name of the memory store to use. |
| `scope` | `string` | Yes | The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user. |
| `search_options` | `MemorySearchOptions` | No | Options for searching the memory store. |
| `update_delay` | `integer` | No | Time to wait before updating memories after inactivity (seconds). Default 300. _Default:_ `300` _Format:_ `int32` |

- **`search_options`** — `MemorySearchOptions`

Options for searching the memory store.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `max_memories` | `integer` | No | Maximum number of memory items to return. _Format:_ `int32` |

- **`toolbox_search_preview`** — `toolbox_search_preview (ToolboxSearchPreviewTool)`

A tool for searching over the agent's toolbox. When present, deferred tools are hidden from `tools/list` and only discoverable via `search_tools` queries at runtime.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `toolbox_search_preview`. _Constant:_ `toolbox_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`code_interpreter`** — `code_interpreter (OpenAI.CodeInterpreterTool)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool. Always `code_interpreter`. _Constant:_ `code_interpreter` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `container` | `string \| OpenAI.AutoCodeInterpreterToolParam` | No | 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. If not provided, the service assumes auto. |

- **`container`** — `string | OpenAI.AutoCodeInterpreterToolParam`

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. If not provided, the service assumes auto.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.AutoCodeInterpreterToolParam`** — `OpenAI.AutoCodeInterpreterToolParam`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Always `auto`. _Default:_ `"auto"` _Constant:_ `auto` |
| `file_ids` | `string[]` | No | An optional list of uploaded files to make available to your code. |
| `memory_limit` | `enum` | No | _Enum:_ `1g`, `4g`, `16g`, `64g` |
| `network_policy` | `OpenAI.ContainerNetworkPolicyDisabledParam \| OpenAI.ContainerNetworkPolicyAllowlistParam` | No | Network access policy for the container. |

- **`network_policy`** — `OpenAI.ContainerNetworkPolicyDisabledParam | OpenAI.ContainerNetworkPolicyAllowlistParam`

Network access policy for the container.

**One of the following:**

- **`disabled`** — `disabled (OpenAI.ContainerNetworkPolicyDisabledParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Disable outbound network access. Always `disabled`. _Default:_ `"disabled"` _Constant:_ `disabled` |

- **`allowlist`** — `allowlist (OpenAI.ContainerNetworkPolicyAllowlistParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Allow outbound network access only to specified domains. Always `allowlist`. _Default:_ `"allowlist"` _Constant:_ `allowlist` |
| `allowed_domains` | `string[]` | Yes | A list of allowed domains when type is `allowlist`. |

- **`function`** — `function (OpenAI.FunctionTool)`

Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool. Always `function`. _Default:_ `"function"` _Constant:_ `function` |
| `name` | `string` | Yes | The name of the function to call. |
| `description` | `string \| null` | No |  |
| `parameters` | `object \| null` | Yes |  |
| `strict` | `boolean \| null` | Yes |  |
| `defer_loading` | `boolean` | No | Whether this function is deferred and loaded via tool search. |

- **`file_search`** — `file_search (OpenAI.FileSearchTool)`

A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool. Always `file_search`. _Default:_ `"file_search"` _Constant:_ `file_search` |
| `vector_store_ids` | `string[]` | Yes | The IDs of the vector stores to search. |
| `max_num_results` | `OpenAI.integer` | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. _Format:_ `int64` |
| `ranking_options` | `OpenAI.RankingOptions` | No | Ranking options for search. |
| `filters` | `OpenAI.ComparisonFilter \| OpenAI.CompoundFilter \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`ranking_options`** — `OpenAI.RankingOptions`

Ranking options for search.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `ranker` | `OpenAI.RankerVersionType` | No | The ranker to use for the file search. _Enum:_ `auto`, `default-2024-11-15` |
| `score_threshold` | `OpenAI.numeric` | No | 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. _Format:_ `double` |
| `hybrid_search` | `OpenAI.HybridSearchOptions` | No | Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. |

- **`hybrid_search`** — `OpenAI.HybridSearchOptions`

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `embedding_weight` | `OpenAI.numeric` | Yes | The weight of the embedding in the reciprocal ranking fusion. _Format:_ `double` |
| `text_weight` | `OpenAI.numeric` | Yes | The weight of the text in the reciprocal ranking fusion. _Format:_ `double` |

- **`filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter | null`

**One of the following:**

- **`OpenAI.Filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter`

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`OpenAI.CompoundFilter`** — `OpenAI.CompoundFilter`

Combine multiple filters using `and` or `or`.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Type of operation: `and` or `or`. _Enum:_ `and`, `or` |
| `filters` | `(OpenAI.ComparisonFilter \| any)[]` | Yes | Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. |

- **`filters`** — `(OpenAI.ComparisonFilter | any)[]`

Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`any`** — `any`

| Type | Description |
|------|-------------|
| `any` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`computer_use_preview`** — `computer_use_preview (OpenAI.ComputerUsePreviewTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer use tool. Always `computer_use_preview`. _Default:_ `"computer_use_preview"` _Constant:_ `computer_use_preview` |
| `environment` | `OpenAI.ComputerEnvironment` | Yes | The type of computer environment to control. _Enum:_ `windows`, `mac`, `linux`, `ubuntu`, `browser` |
| `display_width` | `OpenAI.integer` | Yes | The width of the computer display. _Format:_ `int64` |
| `display_height` | `OpenAI.integer` | Yes | The height of the computer display. _Format:_ `int64` |

- **`web_search`** — `web_search (OpenAI.WebSearchTool)`

Search the Internet for sources related to the prompt. Learn more about the [web search tool](/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. _Default:_ `"web_search"` _Constant:_ `web_search` |
| `filters` | `OpenAI.WebSearchToolFilters \| null` | No |  |
| `user_location` | `OpenAI.WebSearchApproximateLocation \| null` | No |  |
| `search_context_size` | `enum` | No | 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. _Default:_ `"medium"` _Enum:_ `low`, `medium`, `high` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `custom_search_configuration` | `WebSearchConfiguration` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`filters`** — `OpenAI.WebSearchToolFilters | null`

**One of the following:**

- **`OpenAI.WebSearchToolFilters`** — `OpenAI.WebSearchToolFilters`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `allowed_domains` | `string[] \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`user_location`** — `OpenAI.WebSearchApproximateLocation | null`

**One of the following:**

- **`OpenAI.WebSearchApproximateLocation`** — `OpenAI.WebSearchApproximateLocation`

The approximate location of the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom_search_configuration`** — `WebSearchConfiguration`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing custom search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |

- **`mcp`** — `mcp (OpenAI.MCPTool)`

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the MCP tool. Always `mcp`. _Constant:_ `mcp` |
| `server_label` | `string` | Yes | A label for this MCP server, used to identify it in tool calls. |
| `server_url` | `string` | No | The URL for the MCP server. One of `server_url` or `connector_id` must be provided. _Format:_ `uri` |
| `connector_id` | `enum` | No | Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors [here](/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` _Enum:_ `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint` |
| `authorization` | `string` | No | An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. |
| `server_description` | `string` | No | Optional description of the MCP server, used to provide more context. |
| `headers` | `object \| null` | No |  |
| `allowed_tools` | `string[] \| OpenAI.MCPToolFilter \| null` | No |  |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| enum \| null` | No | _Default:_ `"always"` _Enum:_ `always`, `never` |
| `defer_loading` | `boolean` | No | Whether this MCP tool is deferred and discovered via tool search. |
| `project_connection_id` | `string` | No | The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`allowed_tools`** — `string[] | OpenAI.MCPToolFilter | null`

**One of the following:**

- **`string[]`** — `string[]`

Type: `string[]`

- **`OpenAI.MCPToolFilter`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | enum | null`

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`enum`** — `enum`

| Type | Description |
|------|-------------|
| `enum` | _Enum:_ `always`, `never` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`image_generation`** — `image_generation (OpenAI.ImageGenTool)`

A tool that generates images using the GPT image models.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation tool. Always `image_generation`. _Default:_ `"image_generation"` _Constant:_ `image_generation` |
| `model` | `enum` | No | _Default:_ `"gpt-image-1"` _Enum:_ `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5` |
| `quality` | `enum` | No | The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `low`, `medium`, `high`, `auto` |
| `size` | `enum` | No | The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. _Default:_ `"auto"` _Enum:_ `1024x1024`, `1024x1536`, `1536x1024`, `auto` |
| `output_format` | `enum` | No | The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. _Default:_ `"png"` _Enum:_ `png`, `webp`, `jpeg` |
| `output_compression` | `OpenAI.integer` | No | Compression level for the output image. Default: 100. _Default:_ `100` _Format:_ `int64` |
| `moderation` | `enum` | No | Moderation level for the generated image. Default: `auto`. _Default:_ `"auto"` _Enum:_ `auto`, `low` |
| `background` | `enum` | No | Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `transparent`, `opaque`, `auto` |
| `input_fidelity` | `enum` | No | _Enum:_ `high`, `low` |
| `input_image_mask` | `OpenAI.ImageGenToolInputImageMask` | No | Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). |
| `partial_images` | `OpenAI.integer` | No | Number of partial images to generate in streaming mode, from 0 (default value) to 3. _Format:_ `int64` |
| `action` | `OpenAI.ImageGenActionEnum` | No | Whether to generate a new image or edit an existing image. Default: `auto`. _Enum:_ `generate`, `edit`, `auto` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`input_image_mask`** — `OpenAI.ImageGenToolInputImageMask`

Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `image_url` | `string` | No | _Format:_ `uri` |
| `file_id` | `string` | No |  |

- **`local_shell`** — `local_shell (OpenAI.LocalShellToolParam)`

A tool that allows the model to execute shell commands in a local environment.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool. Always `local_shell`. _Default:_ `"local_shell"` _Constant:_ `local_shell` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`shell`** — `shell (OpenAI.FunctionShellToolParam)`

A tool that allows the model to execute shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell tool. Always `shell`. _Default:_ `"shell"` _Constant:_ `shell` |
| `environment` | `OpenAI.FunctionShellToolParamEnvironment \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`environment`** — `OpenAI.FunctionShellToolParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellToolParamEnvironment`** — `OpenAI.FunctionShellToolParamEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `container_auto`, `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom`** — `custom (OpenAI.CustomToolParam)`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`web_search_preview`** — `web_search_preview (OpenAI.WebSearchPreviewTool)`

This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. _Default:_ `"web_search_preview"` _Constant:_ `web_search_preview` |
| `user_location` | `OpenAI.ApproximateLocation \| null` | No |  |
| `search_context_size` | `OpenAI.SearchContextSize` | No | 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. _Enum:_ `low`, `medium`, `high` |
| `search_content_types` | `OpenAI.SearchContentType[]` | No | _Enum:_ `text`, `image` |

- **`user_location`** — `OpenAI.ApproximateLocation | null`

**One of the following:**

- **`OpenAI.ApproximateLocation`** — `OpenAI.ApproximateLocation`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`apply_patch`** — `apply_patch (OpenAI.ApplyPatchToolParam)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `apply_patch`. _Default:_ `"apply_patch"` _Constant:_ `apply_patch` |

- **`computer`** — `computer (OpenAI.ComputerTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool. Always `computer`. _Default:_ `"computer"` _Constant:_ `computer` |

- **`namespace`** — `namespace (OpenAI.NamespaceToolParam)`

Groups function/custom tools under a shared namespace.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `namespace`. _Default:_ `"namespace"` _Constant:_ `namespace` |
| `name` | `string` | Yes | The namespace name used in tool calls (for example, `crm`). |
| `description` | `string` | Yes | A description of the namespace shown to the model. |
| `tools` | `(OpenAI.FunctionToolParam \| OpenAI.CustomToolParam)[]` | Yes | The function/custom tools available inside this namespace. |

- **`tools`** — `(OpenAI.FunctionToolParam | OpenAI.CustomToolParam)[]`

The function/custom tools available inside this namespace.

**One of the following:**

- **`OpenAI.FunctionToolParam`** — `OpenAI.FunctionToolParam`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes |  |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |
| `strict` | `boolean \| null` | No |  |
| `type` | `enum` | Yes | _Default:_ `"function"` _Constant:_ `function` |
| `defer_loading` | `boolean` | No | Whether this function should be deferred and discovered via tool search. |

- **`OpenAI.CustomToolParam`** — `OpenAI.CustomToolParam`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`tool_search`** — `tool_search (OpenAI.ToolSearchToolParam)`

Hosted or BYOT tool search configuration for deferred tools.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `tool_search`. _Default:_ `"tool_search"` _Constant:_ `tool_search` |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search is executed by the server or by the client. _Enum:_ `server`, `client` |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |

##### `reasoning` — `reasoning (OpenAI.InputItemReasoningItem)`

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](/docs/guides/conversation-state).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `reasoning`. _Constant:_ `reasoning` |
| `id` | `string` | Yes | The unique identifier of the reasoning content. |
| `encrypted_content` | `string \| null` | No |  |
| `summary` | `(OpenAI.TextContent \| OpenAI.ComputerScreenshotContent \| OpenAI.MessageContentInputTextContent \| OpenAI.MessageContentOutputTextContent \| OpenAI.MessageContentReasoningTextContent \| OpenAI.MessageContentRefusalContent \| OpenAI.MessageContentInputImageContent \| OpenAI.MessageContentInputFileContent \| OpenAI.SummaryTextContent)[]` | Yes | Reasoning summary content. |
| `content` | `OpenAI.ReasoningTextContent[]` | No | Reasoning text content. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `summary` — `(OpenAI.TextContent | OpenAI.ComputerScreenshotContent | OpenAI.MessageContentInputTextContent | OpenAI.MessageContentOutputTextContent | OpenAI.MessageContentReasoningTextContent | OpenAI.MessageContentRefusalContent | OpenAI.MessageContentInputImageContent | OpenAI.MessageContentInputFileContent | OpenAI.SummaryTextContent)[]`

Reasoning summary content.

**One of the following:**

- **`text`** — `text (OpenAI.TextContent)`

A text content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Default:_ `"text"` _Constant:_ `text` |
| `text` | `string` | Yes |  |

- **`computer_screenshot`** — `computer_screenshot (OpenAI.ComputerScreenshotContent)`

A screenshot of a computer.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string \| null` | Yes |  |
| `file_id` | `string \| null` | Yes |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the screenshot image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_text`** — `input_text (OpenAI.MessageContentInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`output_text`** — `output_text (OpenAI.MessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`reasoning_text`** — `reasoning_text (OpenAI.MessageContentReasoningTextContent)`

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

- **`refusal`** — `refusal (OpenAI.MessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

- **`input_image`** — `input_image (OpenAI.MessageContentInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.MessageContentInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

- **`summary_text`** — `summary_text (OpenAI.SummaryTextContent)`

A summary text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `summary_text`. _Default:_ `"summary_text"` _Constant:_ `summary_text` |
| `text` | `string` | Yes | A summary of the reasoning output from the model so far. |

###### `content` — `OpenAI.ReasoningTextContent[]`

Reasoning text content.

**Array of** `OpenAI.ReasoningTextContent`**:**

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

##### `compaction` — `compaction (OpenAI.InputItemCompactionSummaryItemParam)`

A compaction item generated by the [`v1/responses/compact` API](/docs/api-reference/responses/compact).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `compaction`. _Default:_ `"compaction"` _Constant:_ `compaction` |
| `id` | `string \| null` | No |  |
| `encrypted_content` | `string` | Yes | The encrypted content of the compaction summary. |

##### `image_generation_call` — `image_generation_call (OpenAI.InputItemImageGenToolCall)`

An image generation request made by the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation call. Always `image_generation_call`. _Constant:_ `image_generation_call` |
| `id` | `string` | Yes | The unique ID of the image generation call. |
| `status` | `enum` | Yes | The status of the image generation call. _Enum:_ `in_progress`, `completed`, `generating`, `failed` |
| `result` | `string \| null` | Yes |  |

##### `code_interpreter_call` — `code_interpreter_call (OpenAI.InputItemCodeInterpreterToolCall)`

A tool call to run code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool call. Always `code_interpreter_call`. _Default:_ `"code_interpreter_call"` _Constant:_ `code_interpreter_call` |
| `id` | `string` | Yes | The unique ID of the code interpreter tool call. |
| `status` | `enum` | Yes | The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `interpreting`, `failed` |
| `container_id` | `string` | Yes | The ID of the container used to run the code. |
| `code` | `string \| null` | Yes |  |
| `outputs` | `(OpenAI.CodeInterpreterOutputLogs \| OpenAI.CodeInterpreterOutputImage)[] \| null` | Yes |  |

###### `outputs` — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[] | null`

**One of the following:**

- **`(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`** — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`

**One of the following:**

- **`OpenAI.CodeInterpreterOutputLogs`** — `OpenAI.CodeInterpreterOutputLogs`

The logs output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `logs`. _Default:_ `"logs"` _Constant:_ `logs` |
| `logs` | `string` | Yes | The logs output from the code interpreter. |

- **`OpenAI.CodeInterpreterOutputImage`** — `OpenAI.CodeInterpreterOutputImage`

The image output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `image`. _Default:_ `"image"` _Constant:_ `image` |
| `url` | `string` | Yes | The URL of the image output from the code interpreter. _Format:_ `uri` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `local_shell_call` — `local_shell_call (OpenAI.InputItemLocalShellToolCall)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell call. Always `local_shell_call`. _Constant:_ `local_shell_call` |
| `id` | `string` | Yes | The unique ID of the local shell call. |
| `call_id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `action` | `OpenAI.LocalShellExecAction` | Yes | Execute a shell command on the server. |
| `status` | `enum` | Yes | The status of the local shell call. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `action` — `OpenAI.LocalShellExecAction`

Execute a shell command on the server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell action. Always `exec`. _Default:_ `"exec"` _Constant:_ `exec` |
| `command` | `string[]` | Yes | The command to run. |
| `timeout_ms` | `OpenAI.integer \| null` | No |  |
| `working_directory` | `string \| null` | No |  |
| `env` | `object` | Yes | Environment variables to set for the command. |
| `user` | `string \| null` | No |  |

##### `local_shell_call_output` — `local_shell_call_output (OpenAI.InputItemLocalShellToolCallOutput)`

The output of a local shell tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool call output. Always `local_shell_call_output`. _Constant:_ `local_shell_call_output` |
| `id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `output` | `string` | Yes | A JSON string of the output of the local shell tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

##### `shell_call` — `shell_call (OpenAI.InputItemFunctionShellCallItemParam)`

A tool representing a request to execute one or more shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `shell_call`. _Default:_ `"shell_call"` _Constant:_ `shell_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `action` | `OpenAI.FunctionShellActionParam` | Yes | The shell commands and limits that describe how to run the tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |
| `environment` | `OpenAI.FunctionShellCallItemParamEnvironment \| null` | No |  |

###### `action` — `OpenAI.FunctionShellActionParam`

The shell commands and limits that describe how to run the tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `commands` | `string[]` | Yes | Ordered shell commands for the execution environment to run. |
| `timeout_ms` | `OpenAI.integer \| null` | No |  |
| `max_output_length` | `OpenAI.integer \| null` | No |  |

###### `environment` — `OpenAI.FunctionShellCallItemParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellCallItemParamEnvironment`** — `OpenAI.FunctionShellCallItemParamEnvironment`

The environment to execute the shell commands in.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `shell_call_output` — `shell_call_output (OpenAI.InputItemFunctionShellCallOutputItemParam)`

The streamed output items emitted by a shell tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `shell_call_output`. _Default:_ `"shell_call_output"` _Constant:_ `shell_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `output` | `OpenAI.FunctionShellCallOutputContentParam[]` | Yes | Captured chunks of stdout and stderr output, along with their associated outcomes. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |
| `max_output_length` | `OpenAI.integer \| null` | No |  |

###### `output` — `OpenAI.FunctionShellCallOutputContentParam[]`

Captured chunks of stdout and stderr output, along with their associated outcomes.

**Array of** `OpenAI.FunctionShellCallOutputContentParam`**:**

Captured stdout and stderr for a portion of a shell tool call output.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `stdout` | `string` | Yes | Captured stdout output for the shell call. |
| `stderr` | `string` | Yes | Captured stderr output for the shell call. |
| `outcome` | `OpenAI.FunctionShellCallOutputTimeoutOutcomeParam \| OpenAI.FunctionShellCallOutputExitOutcomeParam` | Yes | The exit or timeout outcome associated with this shell call. |

- **`outcome`** — `OpenAI.FunctionShellCallOutputTimeoutOutcomeParam | OpenAI.FunctionShellCallOutputExitOutcomeParam`

The exit or timeout outcome associated with this shell call.

**One of the following:**

- **`timeout`** — `timeout (OpenAI.FunctionShellCallOutputTimeoutOutcomeParam)`

Indicates that the shell call exceeded its configured time limit.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `timeout`. _Default:_ `"timeout"` _Constant:_ `timeout` |

- **`exit`** — `exit (OpenAI.FunctionShellCallOutputExitOutcomeParam)`

Indicates that the shell commands finished and returned an exit code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `exit`. _Default:_ `"exit"` _Constant:_ `exit` |
| `exit_code` | `OpenAI.integer` | Yes | The exit code returned by the shell process. _Format:_ `int64` |

##### `apply_patch_call` — `apply_patch_call (OpenAI.InputItemApplyPatchToolCallItemParam)`

A tool call representing a request to create, delete, or update files using diff patches.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call`. _Default:_ `"apply_patch_call"` _Constant:_ `apply_patch_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallStatusParam` | Yes | The status of the apply patch tool call. One of `in_progress` or `completed`. _Enum:_ `in_progress`, `completed` |
| `operation` | `OpenAI.ApplyPatchCreateFileOperationParam \| OpenAI.ApplyPatchDeleteFileOperationParam \| OpenAI.ApplyPatchUpdateFileOperationParam` | Yes | The specific create, delete, or update instruction for the apply_patch tool call. |

###### `operation` — `OpenAI.ApplyPatchCreateFileOperationParam | OpenAI.ApplyPatchDeleteFileOperationParam | OpenAI.ApplyPatchUpdateFileOperationParam`

The specific create, delete, or update instruction for the apply_patch tool call.

**One of the following:**

- **`create_file`** — `create_file (OpenAI.ApplyPatchCreateFileOperationParam)`

Instruction for creating a new file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `create_file`. _Default:_ `"create_file"` _Constant:_ `create_file` |
| `path` | `string` | Yes | Path of the file to create relative to the workspace root. |
| `diff` | `string` | Yes | Unified diff content to apply when creating the file. |

- **`delete_file`** — `delete_file (OpenAI.ApplyPatchDeleteFileOperationParam)`

Instruction for deleting an existing file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `delete_file`. _Default:_ `"delete_file"` _Constant:_ `delete_file` |
| `path` | `string` | Yes | Path of the file to delete relative to the workspace root. |

- **`update_file`** — `update_file (OpenAI.ApplyPatchUpdateFileOperationParam)`

Instruction for updating an existing file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `update_file`. _Default:_ `"update_file"` _Constant:_ `update_file` |
| `path` | `string` | Yes | Path of the file to update relative to the workspace root. |
| `diff` | `string` | Yes | Unified diff content to apply to the existing file. |

##### `apply_patch_call_output` — `apply_patch_call_output (OpenAI.InputItemApplyPatchToolCallOutputItemParam)`

The streamed output emitted by an apply patch tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call_output`. _Default:_ `"apply_patch_call_output"` _Constant:_ `apply_patch_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallOutputStatusParam` | Yes | The status of the apply patch tool call output. One of `completed` or `failed`. _Enum:_ `completed`, `failed` |
| `output` | `string \| null` | No |  |

##### `mcp_list_tools` — `mcp_list_tools (OpenAI.InputItemMcpListTools)`

A list of tools available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_list_tools`. _Constant:_ `mcp_list_tools` |
| `id` | `string` | Yes | The unique ID of the list. |
| `server_label` | `string` | Yes | The label of the MCP server. |
| `tools` | `OpenAI.MCPListToolsTool[]` | Yes | The tools available on the server. |
| `error` | `OpenAI.RealtimeMCPProtocolError \| OpenAI.RealtimeMCPToolExecutionError \| OpenAI.RealtimeMCPHTTPError` | No |  |

###### `tools` — `OpenAI.MCPListToolsTool[]`

The tools available on the server.

**Array of** `OpenAI.MCPListToolsTool`**:**

A tool available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the tool. |
| `description` | `string \| null` | No |  |
| `input_schema` | `OpenAI.MCPListToolsToolInputSchema` | Yes | The JSON schema describing the tool's input. |
| `annotations` | `OpenAI.MCPListToolsToolAnnotations \| null` | No |  |

###### `error` — `OpenAI.RealtimeMCPProtocolError | OpenAI.RealtimeMCPToolExecutionError | OpenAI.RealtimeMCPHTTPError`

**One of the following:**

- **`protocol_error`** — `protocol_error (OpenAI.RealtimeMCPProtocolError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `protocol_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

- **`tool_execution_error`** — `tool_execution_error (OpenAI.RealtimeMCPToolExecutionError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `tool_execution_error` |
| `message` | `string` | Yes |  |

- **`http_error`** — `http_error (OpenAI.RealtimeMCPHTTPError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `http_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

##### `mcp_approval_request` — `mcp_approval_request (OpenAI.InputItemMcpApprovalRequest)`

A request for human approval of a tool invocation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_request`. _Constant:_ `mcp_approval_request` |
| `id` | `string` | Yes | The unique ID of the approval request. |
| `server_label` | `string` | Yes | The label of the MCP server making the request. |
| `name` | `string` | Yes | The name of the tool to run. |
| `arguments` | `string` | Yes | A JSON string of arguments for the tool. |

##### `mcp_approval_response` — `mcp_approval_response (OpenAI.InputItemMcpApprovalResponse)`

A response to an MCP approval request.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_response`. _Constant:_ `mcp_approval_response` |
| `id` | `string \| null` | No |  |
| `approval_request_id` | `string` | Yes | The ID of the approval request being answered. |
| `approve` | `boolean` | Yes | Whether the request was approved. |
| `reason` | `string \| null` | No |  |

##### `mcp_call` — `mcp_call (OpenAI.InputItemMcpToolCall)`

An invocation of a tool on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_call`. _Constant:_ `mcp_call` |
| `id` | `string` | Yes | The unique ID of the tool call. |
| `server_label` | `string` | Yes | The label of the MCP server running the tool. |
| `name` | `string` | Yes | The name of the tool that was run. |
| `arguments` | `string` | Yes | A JSON string of the arguments passed to the tool. |
| `output` | `string \| null` | No |  |
| `error` | `object` | No |  |
| `status` | `OpenAI.MCPToolCallStatus` | No | The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `calling`, `failed` |
| `approval_request_id` | `string \| null` | No |  |

##### `custom_tool_call_output` — `custom_tool_call_output (OpenAI.InputItemCustomToolCallOutput)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call output. Always `custom_tool_call_output`. _Constant:_ `custom_tool_call_output` |
| `id` | `string` | No | The unique ID of the custom tool call output in the OpenAI platform. |
| `call_id` | `string` | Yes | The call ID, used to map this custom tool call output to a custom tool call. |
| `output` | `string \| (OpenAI.FunctionAndCustomToolCallOutputInputTextContent \| OpenAI.FunctionAndCustomToolCallOutputInputImageContent \| OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]` | Yes | The output from the custom tool call generated by your code. Can be a string or an list of output content. |

###### `output` — `string | (OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

The output from the custom tool call generated by your code. Can be a string or an list of output content.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`** — `(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

**One of the following:**

- **`input_text`** — `input_text (OpenAI.FunctionAndCustomToolCallOutputInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.FunctionAndCustomToolCallOutputInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.FunctionAndCustomToolCallOutputInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

##### `custom_tool_call` — `custom_tool_call (OpenAI.InputItemCustomToolCall)`

A call to a custom tool created by the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call. Always `custom_tool_call`. _Constant:_ `custom_tool_call` |
| `id` | `string` | No | The unique ID of the custom tool call in the OpenAI platform. |
| `call_id` | `string` | Yes | An identifier used to map this custom tool call to a tool call output. |
| `namespace` | `string` | No | The namespace of the custom tool being called. |
| `name` | `string` | Yes | The name of the custom tool being called. |
| `input` | `string` | Yes | The input for the custom tool call generated by the model. |

### `include` — `enum[] | null`

**One of the following:**

#### `enum[]` — `enum[]`

Type: `enum[]`

#### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

### `stream_options` — `OpenAI.ResponseStreamOptions | null`

**One of the following:**

#### `OpenAI.ResponseStreamOptions` — `OpenAI.ResponseStreamOptions`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `include_obfuscation` | `boolean` | No | 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. |

#### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

### `conversation` — `string | OpenAI.ConversationParam-2 | null`

**One of the following:**

#### `OpenAI.ConversationParam` — `string | 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.

**One of the following:**

##### `string` — `string`

| Type | Description |
|------|-------------|
| `string` | — |

##### `OpenAI.ConversationParam-2` — `OpenAI.ConversationParam-2`

The conversation that this response belongs to.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The unique ID of the conversation. |

#### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

### `context_management` — `OpenAI.ContextManagementParam[] | null`

Context management configuration for this request.

**One of the following:**

#### `OpenAI.ContextManagementParam[]` — `OpenAI.ContextManagementParam[]`

**Array of** `OpenAI.ContextManagementParam`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `string` | Yes | The context management entry type. Currently only 'compaction' is supported. |
| `compact_threshold` | `OpenAI.integer \| null` | No |  |

#### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

### `agent_reference` — `AgentReference`

The agent to use for generating the response.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

## Responses

### 200 — The request has succeeded.

Content-Type: `application/json`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `metadata` | `OpenAI.Metadata \| null` | No |  |
| `top_logprobs` | `OpenAI.integer \| null` | No |  |
| `temperature` | `OpenAI.numeric \| null` | No | _Default:_ `1` |
| `top_p` | `OpenAI.numeric \| null` | No | _Default:_ `1` |
| `user` | `string` | No | 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](/docs/guides/safety-best-practices#safety-identifiers). |
| `safety_identifier` | `string` | No | 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, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). |
| `prompt_cache_key` | `string` | No | Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). |
| `service_tier` | `enum` | No | Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. _Enum:_ `auto`, `default`, `flex`, `scale`, `priority` |
| `prompt_cache_retention` | `enum` | No | _Enum:_ `in_memory`, `24h` |
| `previous_response_id` | `string \| null` | No |  |
| `model` | `string` | No | The model deployment to use for the creation of this response. |
| `reasoning` | `OpenAI.Reasoning \| null` | No |  |
| `background` | `boolean \| null` | No |  |
| `max_tool_calls` | `OpenAI.integer \| null` | No |  |
| `text` | `OpenAI.ResponseTextParam` | No | Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](/docs/guides/text) - [Structured Outputs](/docs/guides/structured-outputs) |
| `tools` | `(BingGroundingTool \| MicrosoftFabricPreviewTool \| SharepointPreviewTool \| AzureAISearchTool \| OpenApiTool \| BingCustomSearchPreviewTool \| BrowserAutomationPreviewTool \| AzureFunctionTool \| CaptureStructuredOutputsTool \| A2APreviewTool \| WorkIQPreviewTool \| FabricIQPreviewTool \| MemorySearchPreviewTool \| ToolboxSearchPreviewTool \| OpenAI.CodeInterpreterTool \| OpenAI.FunctionTool \| OpenAI.FileSearchTool \| OpenAI.ComputerUsePreviewTool \| OpenAI.WebSearchTool \| OpenAI.MCPTool \| OpenAI.ImageGenTool \| OpenAI.LocalShellToolParam \| OpenAI.FunctionShellToolParam \| OpenAI.CustomToolParam \| OpenAI.WebSearchPreviewTool \| OpenAI.ApplyPatchToolParam \| OpenAI.ComputerTool \| OpenAI.NamespaceToolParam \| OpenAI.ToolSearchToolParam)[]` | No | 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](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search). Learn more about [built-in tools](/docs/guides/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](/docs/guides/tools-connectors-mcp). - **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](/docs/guides/function-calling). You can also use custom tools to call your own code. |
| `tool_choice` | `OpenAI.ToolChoiceOptions \| OpenAI.ToolChoiceParam` | No | _Enum:_ `none`, `auto`, `required` |
| `prompt` | `OpenAI.Prompt` | No | Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). |
| `truncation` | `enum` | No | _Default:_ `"disabled"` _Enum:_ `auto`, `disabled` |
| `id` | `string` | Yes | Unique identifier for this Response. |
| `object` | `enum` | Yes | The object type of this resource - always set to `response`. _Constant:_ `response` |
| `status` | `enum` | No | The status of the response generation. One of `completed`, `failed`, `in_progress`, `cancelled`, `queued`, or `incomplete`. _Enum:_ `completed`, `failed`, `in_progress`, `cancelled`, `queued`, `incomplete` |
| `created_at` | `integer` | Yes | Unix timestamp (in seconds) of when this Response was created. _Format:_ `unixtime` |
| `completed_at` | `string \| null` | No | _Format:_ `unixTimestamp` |
| `error` | `OpenAI.ResponseError \| null` | Yes |  |
| `incomplete_details` | `OpenAI.ResponseIncompleteDetails \| null` | Yes |  |
| `output` | `(StructuredOutputsOutputItem \| WorkflowActionOutputItem \| OAuthConsentRequestOutputItem \| BingGroundingToolCall \| BingGroundingToolCallOutput \| SharepointGroundingToolCall \| SharepointGroundingToolCallOutput \| AzureAISearchToolCall \| AzureAISearchToolCallOutput \| BingCustomSearchToolCall \| BingCustomSearchToolCallOutput \| OpenApiToolCall \| OpenApiToolCallOutput \| BrowserAutomationToolCall \| BrowserAutomationToolCallOutput \| FabricDataAgentToolCall \| FabricDataAgentToolCallOutput \| AzureFunctionToolCall \| AzureFunctionToolCallOutput \| A2AToolCall \| A2AToolCallOutput \| MemorySearchToolCall \| MemoryCommandToolCall \| MemoryCommandToolCallOutput \| OpenAI.OutputItemOutputMessage \| OpenAI.OutputItemFileSearchToolCall \| OpenAI.OutputItemFunctionToolCall \| OpenAI.OutputItemFunctionToolCallOutput \| OpenAI.OutputItemWebSearchToolCall \| OpenAI.OutputItemComputerToolCall \| OpenAI.OutputItemComputerToolCallOutput \| OpenAI.OutputItemReasoningItem \| OpenAI.OutputItemToolSearchCall \| OpenAI.OutputItemToolSearchOutput \| OpenAI.OutputItemCompactionBody \| OpenAI.OutputItemImageGenToolCall \| OpenAI.OutputItemCodeInterpreterToolCall \| OpenAI.OutputItemLocalShellToolCall \| OpenAI.OutputItemLocalShellToolCallOutput \| OpenAI.OutputItemFunctionShellCall \| OpenAI.OutputItemFunctionShellCallOutput \| OpenAI.OutputItemApplyPatchToolCall \| OpenAI.OutputItemApplyPatchToolCallOutput \| OpenAI.OutputItemMcpToolCall \| OpenAI.OutputItemMcpListTools \| OpenAI.OutputItemMcpApprovalRequest \| OpenAI.OutputItemMcpApprovalResponseResource \| OpenAI.OutputItemCustomToolCallResource \| OpenAI.OutputItemCustomToolCallOutputResource)[]` | Yes | 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. |
| `instructions` | `string \| (OpenAI.EasyInputMessage \| OpenAI.ItemReferenceParam \| OpenAI.InputItemOutputMessage \| OpenAI.InputItemFileSearchToolCall \| OpenAI.InputItemComputerToolCall \| OpenAI.InputItemComputerCallOutputItemParam \| OpenAI.InputItemWebSearchToolCall \| OpenAI.InputItemFunctionToolCall \| OpenAI.InputItemFunctionCallOutputItemParam \| OpenAI.InputItemToolSearchCallItemParam \| OpenAI.InputItemToolSearchOutputItemParam \| OpenAI.InputItemReasoningItem \| OpenAI.InputItemCompactionSummaryItemParam \| OpenAI.InputItemImageGenToolCall \| OpenAI.InputItemCodeInterpreterToolCall \| OpenAI.InputItemLocalShellToolCall \| OpenAI.InputItemLocalShellToolCallOutput \| OpenAI.InputItemFunctionShellCallItemParam \| OpenAI.InputItemFunctionShellCallOutputItemParam \| OpenAI.InputItemApplyPatchToolCallItemParam \| OpenAI.InputItemApplyPatchToolCallOutputItemParam \| OpenAI.InputItemMcpListTools \| OpenAI.InputItemMcpApprovalRequest \| OpenAI.InputItemMcpApprovalResponse \| OpenAI.InputItemMcpToolCall \| OpenAI.InputItemCustomToolCallOutput \| OpenAI.InputItemCustomToolCall)[] \| null` | Yes |  |
| `output_text` | `string \| null` | No |  |
| `usage` | `OpenAI.ResponseUsage` | No | Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. |
| `parallel_tool_calls` | `boolean` | Yes | Whether to allow the model to run tool calls in parallel. _Default:_ `true` |
| `conversation` | `OpenAI.ConversationReference \| null` | No |  |
| `max_output_tokens` | `OpenAI.integer \| null` | No |  |
| `agent_reference` | `AgentReference \| null` | Yes | The agent used for this response |
| `content_filters` | `ContentFilterResult[]` | No | The content filter evaluation results. |

#### `reasoning` — `OpenAI.Reasoning | null`

**One of the following:**

##### `OpenAI.Reasoning` — `OpenAI.Reasoning`

**gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `effort` | `enum` | No | Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). 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`. _Enum:_ `none`, `minimal`, `low`, `medium`, `high`, `xhigh` |
| `summary` | `enum` | No | _Enum:_ `auto`, `concise`, `detailed` |
| `generate_summary` | `enum` | No | _Enum:_ `auto`, `concise`, `detailed` |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `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](/docs/guides/text) - [Structured Outputs](/docs/guides/structured-outputs)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `format` | `OpenAI.TextResponseFormatJsonSchema \| OpenAI.TextResponseFormatConfigurationResponseFormatText \| OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject` | No | 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 [Structured Outputs guide](/docs/guides/structured-outputs). 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. |
| `verbosity` | `enum` | No | 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`. _Enum:_ `low`, `medium`, `high` |

##### `format` — `OpenAI.TextResponseFormatJsonSchema | OpenAI.TextResponseFormatConfigurationResponseFormatText | OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject`

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 [Structured Outputs guide](/docs/guides/structured-outputs). 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.

**One of the following:**

###### `json_schema` — `json_schema (OpenAI.TextResponseFormatJsonSchema)`

JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](/docs/guides/structured-outputs).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `json_schema`. _Constant:_ `json_schema` |
| `description` | `string` | No | A description of what the response format is for, used by the model to determine how to respond in the format. |
| `name` | `string` | Yes | 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. |
| `schema` | `OpenAI.ResponseFormatJsonSchemaSchema` | Yes | The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). |
| `strict` | `boolean \| null` | No |  |

###### `text` — `text (OpenAI.TextResponseFormatConfigurationResponseFormatText)`

Default response format. Used to generate text responses.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `text`. _Constant:_ `text` |

###### `json_object` — `json_object (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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of response format being defined. Always `json_object`. _Constant:_ `json_object` |

#### `tools` — `(BingGroundingTool | MicrosoftFabricPreviewTool | SharepointPreviewTool | AzureAISearchTool | OpenApiTool | BingCustomSearchPreviewTool | BrowserAutomationPreviewTool | AzureFunctionTool | CaptureStructuredOutputsTool | A2APreviewTool | WorkIQPreviewTool | FabricIQPreviewTool | MemorySearchPreviewTool | ToolboxSearchPreviewTool | OpenAI.CodeInterpreterTool | OpenAI.FunctionTool | OpenAI.FileSearchTool | OpenAI.ComputerUsePreviewTool | OpenAI.WebSearchTool | OpenAI.MCPTool | OpenAI.ImageGenTool | OpenAI.LocalShellToolParam | OpenAI.FunctionShellToolParam | OpenAI.CustomToolParam | OpenAI.WebSearchPreviewTool | OpenAI.ApplyPatchToolParam | OpenAI.ComputerTool | OpenAI.NamespaceToolParam | OpenAI.ToolSearchToolParam)[]`

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](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search). Learn more about [built-in tools](/docs/guides/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](/docs/guides/tools-connectors-mcp). - **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](/docs/guides/function-calling). You can also use custom tools to call your own code.

**One of the following:**

##### `bing_grounding` — `bing_grounding (BingGroundingTool)`

The input definition information for a bing grounding search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_grounding'. _Constant:_ `bing_grounding` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_grounding` | `BingGroundingSearchToolParameters` | Yes | The bing grounding search tool parameters. |

###### `bing_grounding` — `BingGroundingSearchToolParameters`

The bing grounding search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingGroundingSearchConfiguration[]` | Yes | The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. |

- **`search_configurations`** — `BingGroundingSearchConfiguration[]`

The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool.

**Array of** `BingGroundingSearchConfiguration`**:**

Search configuration for Bing Grounding

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

##### `fabric_dataagent_preview` — `fabric_dataagent_preview (MicrosoftFabricPreviewTool)`

The input definition information for a Microsoft Fabric tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_dataagent_preview'. _Constant:_ `fabric_dataagent_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `fabric_dataagent_preview` | `FabricDataAgentToolParameters` | Yes | The fabric data agent tool parameters. |

###### `fabric_dataagent_preview` — `FabricDataAgentToolParameters`

The fabric data agent tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

##### `sharepoint_grounding_preview` — `sharepoint_grounding_preview (SharepointPreviewTool)`

The input definition information for a sharepoint tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'sharepoint_grounding_preview'. _Constant:_ `sharepoint_grounding_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `sharepoint_grounding_preview` | `SharepointGroundingToolParameters` | Yes | The sharepoint grounding tool parameters. |

###### `sharepoint_grounding_preview` — `SharepointGroundingToolParameters`

The sharepoint grounding tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

##### `azure_ai_search` — `azure_ai_search (AzureAISearchTool)`

The input definition information for an Azure AI search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'azure_ai_search'. _Constant:_ `azure_ai_search` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `azure_ai_search` | `AzureAISearchToolResource` | Yes | The azure ai search index resource. |

###### `azure_ai_search` — `AzureAISearchToolResource`

The azure ai search index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `indexes` | `AISearchIndexResource[]` | Yes | The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. |

- **`indexes`** — `AISearchIndexResource[]`

The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent.

**Array of** `AISearchIndexResource`**:**

A AI Search Index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | No | An index connection ID in an IndexResource attached to this agent. |
| `index_name` | `string` | No | The name of an index in an IndexResource attached to this agent. |
| `query_type` | `enum` | No | Type of query in an AIIndexResource attached to this agent. _Enum:_ `simple`, `semantic`, `vector`, `vector_simple_hybrid`, `vector_semantic_hybrid` |
| `top_k` | `integer` | No | Number of documents to retrieve from search and present to the model. _Format:_ `int32` |
| `filter` | `string` | No | filter string for search resource. [Learn more here](https://learn.microsoft.com/azure/search/search-filters). |
| `index_asset_id` | `string` | No | Index asset id for search resource. |

##### `openapi` — `openapi (OpenApiTool)`

The input definition information for an OpenAPI tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'openapi'. _Constant:_ `openapi` |
| `openapi` | `OpenApiFunctionDefinition` | Yes | The openapi function definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `openapi` — `OpenApiFunctionDefinition`

The openapi function definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the function to be called. |
| `description` | `string` | No | A description of what the function does, used by the model to choose when and how to call the function. |
| `spec` | `object` | Yes | The openapi function shape, described as a JSON Schema object. |
| `auth` | `OpenApiAnonymousAuthDetails \| OpenApiProjectConnectionAuthDetails \| OpenApiManagedAuthDetails` | Yes | Open API authentication details |
| `default_params` | `string[]` | No | List of OpenAPI spec parameters that will use user-provided defaults |
| `functions` | `object[]` | No | List of function definitions used by OpenApi tool |

- **`auth`** — `OpenApiAnonymousAuthDetails | OpenApiProjectConnectionAuthDetails | OpenApiManagedAuthDetails`

Open API authentication details

**One of the following:**

- **`anonymous`** — `anonymous (OpenApiAnonymousAuthDetails)`

Security details for OpenApi anonymous authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'anonymous'. _Constant:_ `anonymous` |

- **`project_connection`** — `project_connection (OpenApiProjectConnectionAuthDetails)`

Security details for OpenApi project connection authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'project_connection'. _Constant:_ `project_connection` |
| `security_scheme` | `OpenApiProjectConnectionSecurityScheme` | Yes | Project connection auth security details |

- **`security_scheme`** — `OpenApiProjectConnectionSecurityScheme`

Project connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for Project Connection auth type |

- **`managed_identity`** — `managed_identity (OpenApiManagedAuthDetails)`

Security details for OpenApi managed_identity authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'managed_identity'. _Constant:_ `managed_identity` |
| `security_scheme` | `OpenApiManagedSecurityScheme` | Yes | Connection auth security details |

- **`security_scheme`** — `OpenApiManagedSecurityScheme`

Connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `audience` | `string` | Yes | Authentication scope for managed_identity auth type |

- **`functions`** — `object[]`

List of function definitions used by OpenApi tool

**Array of** `object`**:**

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

##### `bing_custom_search_preview` — `bing_custom_search_preview (BingCustomSearchPreviewTool)`

The input definition information for a Bing custom search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_custom_search_preview'. _Constant:_ `bing_custom_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_custom_search_preview` | `BingCustomSearchToolParameters` | Yes | The bing custom search tool parameters. |

###### `bing_custom_search_preview` — `BingCustomSearchToolParameters`

The bing custom search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingCustomSearchConfiguration[]` | Yes | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`search_configurations`** — `BingCustomSearchConfiguration[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `BingCustomSearchConfiguration`**:**

A bing custom search configuration.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

##### `browser_automation_preview` — `browser_automation_preview (BrowserAutomationPreviewTool)`

The input definition information for a Browser Automation Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation_preview'. _Constant:_ `browser_automation_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `browser_automation_preview` | `BrowserAutomationToolParameters` | Yes | The Browser Automation Tool parameters. |

###### `browser_automation_preview` — `BrowserAutomationToolParameters`

The Browser Automation Tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `connection` | `BrowserAutomationToolConnectionParameters` | Yes | The project connection parameters associated with the Browser Automation Tool. |

- **`connection`** — `BrowserAutomationToolConnectionParameters`

The project connection parameters associated with the Browser Automation Tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | The ID of the project connection to your Azure Playwright resource. |

##### `azure_function` — `azure_function (AzureFunctionTool)`

The input definition information for an Azure Function Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation'. _Constant:_ `azure_function` |
| `azure_function` | `AzureFunctionDefinition` | Yes | The Azure Function Tool definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `azure_function` — `AzureFunctionDefinition`

The Azure Function Tool definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `function` | `object` | Yes | The definition of azure function and its parameters. |
| `input_binding` | `AzureFunctionBinding` | Yes | Input storage queue. The queue storage trigger runs a function as messages are added to it. |
| `output_binding` | `AzureFunctionBinding` | Yes | Output storage queue. The function writes output to this queue when the input items are processed. |

- **`function`** — `object`

The definition of azure function and its parameters.

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

- **`input_binding`** — `AzureFunctionBinding`

Input storage queue. The queue storage trigger runs a function as messages are added to it.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`output_binding`** — `AzureFunctionBinding`

Output storage queue. The function writes output to this queue when the input items are processed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

##### `capture_structured_outputs` — `capture_structured_outputs (CaptureStructuredOutputsTool)`

A tool for capturing structured outputs

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `capture_structured_outputs`. _Constant:_ `capture_structured_outputs` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `outputs` | `StructuredOutputDefinition` | Yes | The structured outputs to capture from the model. |

###### `outputs` — `StructuredOutputDefinition`

The structured outputs to capture from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the structured output. |
| `description` | `string` | Yes | A description of the output to emit. Used by the model to determine when to emit the output. |
| `schema` | `object` | Yes | The JSON schema for the structured output. |
| `strict` | `boolean \| null` | Yes | Whether to enforce strict validation. Default `true`. |

##### `a2a_preview` — `a2a_preview (A2APreviewTool)`

An agent implementing the A2A protocol.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `"a2a_preview`. _Constant:_ `a2a_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `base_url` | `string` | No | Base URL of the agent. _Format:_ `uri` |
| `agent_card_path` | `string` | No | The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json` |
| `project_connection_id` | `string` | No | The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server. |

##### `work_iq_preview` — `work_iq_preview (WorkIQPreviewTool)`

A WorkIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'work_iq_preview'. _Constant:_ `work_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the WorkIQ project connection. |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `fabric_iq_preview` — `fabric_iq_preview (FabricIQPreviewTool)`

A FabricIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_iq_preview'. _Constant:_ `fabric_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the FabricIQ project connection. |
| `server_label` | `string` | No | (Optional) The label of the FabricIQ MCP server to connect to. |
| `server_url` | `string` | No | (Optional) The URL of the FabricIQ MCP server. If not provided, the URL from the project connection will be used. _Format:_ `uri` |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| string \| null` | No | (Optional) Whether the agent requires approval before executing actions. Default is always. _Default:_ `"always"` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `require_approval` — `OpenAI.MCPToolRequireApproval | string | null`

(Optional) Whether the agent requires approval before executing actions. Default is always.

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `memory_search_preview` — `memory_search_preview (MemorySearchPreviewTool)`

A tool for integrating memories into the agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `memory_search_preview`. _Constant:_ `memory_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `memory_store_name` | `string` | Yes | The name of the memory store to use. |
| `scope` | `string` | Yes | The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user. |
| `search_options` | `MemorySearchOptions` | No | Options for searching the memory store. |
| `update_delay` | `integer` | No | Time to wait before updating memories after inactivity (seconds). Default 300. _Default:_ `300` _Format:_ `int32` |

###### `search_options` — `MemorySearchOptions`

Options for searching the memory store.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `max_memories` | `integer` | No | Maximum number of memory items to return. _Format:_ `int32` |

##### `toolbox_search_preview` — `toolbox_search_preview (ToolboxSearchPreviewTool)`

A tool for searching over the agent's toolbox. When present, deferred tools are hidden from `tools/list` and only discoverable via `search_tools` queries at runtime.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `toolbox_search_preview`. _Constant:_ `toolbox_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `code_interpreter` — `code_interpreter (OpenAI.CodeInterpreterTool)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool. Always `code_interpreter`. _Constant:_ `code_interpreter` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `container` | `string \| OpenAI.AutoCodeInterpreterToolParam` | No | 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. If not provided, the service assumes auto. |

###### `container` — `string | OpenAI.AutoCodeInterpreterToolParam`

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. If not provided, the service assumes auto.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.AutoCodeInterpreterToolParam`** — `OpenAI.AutoCodeInterpreterToolParam`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Always `auto`. _Default:_ `"auto"` _Constant:_ `auto` |
| `file_ids` | `string[]` | No | An optional list of uploaded files to make available to your code. |
| `memory_limit` | `enum` | No | _Enum:_ `1g`, `4g`, `16g`, `64g` |
| `network_policy` | `OpenAI.ContainerNetworkPolicyDisabledParam \| OpenAI.ContainerNetworkPolicyAllowlistParam` | No | Network access policy for the container. |

- **`network_policy`** — `OpenAI.ContainerNetworkPolicyDisabledParam | OpenAI.ContainerNetworkPolicyAllowlistParam`

Network access policy for the container.

**One of the following:**

- **`disabled`** — `disabled (OpenAI.ContainerNetworkPolicyDisabledParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Disable outbound network access. Always `disabled`. _Default:_ `"disabled"` _Constant:_ `disabled` |

- **`allowlist`** — `allowlist (OpenAI.ContainerNetworkPolicyAllowlistParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Allow outbound network access only to specified domains. Always `allowlist`. _Default:_ `"allowlist"` _Constant:_ `allowlist` |
| `allowed_domains` | `string[]` | Yes | A list of allowed domains when type is `allowlist`. |

##### `function` — `function (OpenAI.FunctionTool)`

Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool. Always `function`. _Default:_ `"function"` _Constant:_ `function` |
| `name` | `string` | Yes | The name of the function to call. |
| `description` | `string \| null` | No |  |
| `parameters` | `object \| null` | Yes |  |
| `strict` | `boolean \| null` | Yes |  |
| `defer_loading` | `boolean` | No | Whether this function is deferred and loaded via tool search. |

##### `file_search` — `file_search (OpenAI.FileSearchTool)`

A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool. Always `file_search`. _Default:_ `"file_search"` _Constant:_ `file_search` |
| `vector_store_ids` | `string[]` | Yes | The IDs of the vector stores to search. |
| `max_num_results` | `OpenAI.integer` | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. _Format:_ `int64` |
| `ranking_options` | `OpenAI.RankingOptions` | No | Ranking options for search. |
| `filters` | `OpenAI.ComparisonFilter \| OpenAI.CompoundFilter \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `ranking_options` — `OpenAI.RankingOptions`

Ranking options for search.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `ranker` | `OpenAI.RankerVersionType` | No | The ranker to use for the file search. _Enum:_ `auto`, `default-2024-11-15` |
| `score_threshold` | `OpenAI.numeric` | No | 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. _Format:_ `double` |
| `hybrid_search` | `OpenAI.HybridSearchOptions` | No | Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. |

- **`hybrid_search`** — `OpenAI.HybridSearchOptions`

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `embedding_weight` | `OpenAI.numeric` | Yes | The weight of the embedding in the reciprocal ranking fusion. _Format:_ `double` |
| `text_weight` | `OpenAI.numeric` | Yes | The weight of the text in the reciprocal ranking fusion. _Format:_ `double` |

###### `filters` — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter | null`

**One of the following:**

- **`OpenAI.Filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter`

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`OpenAI.CompoundFilter`** — `OpenAI.CompoundFilter`

Combine multiple filters using `and` or `or`.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Type of operation: `and` or `or`. _Enum:_ `and`, `or` |
| `filters` | `(OpenAI.ComparisonFilter \| any)[]` | Yes | Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. |

- **`filters`** — `(OpenAI.ComparisonFilter | any)[]`

Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`any`** — `any`

| Type | Description |
|------|-------------|
| `any` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `computer_use_preview` — `computer_use_preview (OpenAI.ComputerUsePreviewTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer use tool. Always `computer_use_preview`. _Default:_ `"computer_use_preview"` _Constant:_ `computer_use_preview` |
| `environment` | `OpenAI.ComputerEnvironment` | Yes | The type of computer environment to control. _Enum:_ `windows`, `mac`, `linux`, `ubuntu`, `browser` |
| `display_width` | `OpenAI.integer` | Yes | The width of the computer display. _Format:_ `int64` |
| `display_height` | `OpenAI.integer` | Yes | The height of the computer display. _Format:_ `int64` |

##### `web_search` — `web_search (OpenAI.WebSearchTool)`

Search the Internet for sources related to the prompt. Learn more about the [web search tool](/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. _Default:_ `"web_search"` _Constant:_ `web_search` |
| `filters` | `OpenAI.WebSearchToolFilters \| null` | No |  |
| `user_location` | `OpenAI.WebSearchApproximateLocation \| null` | No |  |
| `search_context_size` | `enum` | No | 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. _Default:_ `"medium"` _Enum:_ `low`, `medium`, `high` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `custom_search_configuration` | `WebSearchConfiguration` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

###### `filters` — `OpenAI.WebSearchToolFilters | null`

**One of the following:**

- **`OpenAI.WebSearchToolFilters`** — `OpenAI.WebSearchToolFilters`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `allowed_domains` | `string[] \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `user_location` — `OpenAI.WebSearchApproximateLocation | null`

**One of the following:**

- **`OpenAI.WebSearchApproximateLocation`** — `OpenAI.WebSearchApproximateLocation`

The approximate location of the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `custom_search_configuration` — `WebSearchConfiguration`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing custom search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |

##### `mcp` — `mcp (OpenAI.MCPTool)`

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the MCP tool. Always `mcp`. _Constant:_ `mcp` |
| `server_label` | `string` | Yes | A label for this MCP server, used to identify it in tool calls. |
| `server_url` | `string` | No | The URL for the MCP server. One of `server_url` or `connector_id` must be provided. _Format:_ `uri` |
| `connector_id` | `enum` | No | Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors [here](/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` _Enum:_ `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint` |
| `authorization` | `string` | No | An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. |
| `server_description` | `string` | No | Optional description of the MCP server, used to provide more context. |
| `headers` | `object \| null` | No |  |
| `allowed_tools` | `string[] \| OpenAI.MCPToolFilter \| null` | No |  |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| enum \| null` | No | _Default:_ `"always"` _Enum:_ `always`, `never` |
| `defer_loading` | `boolean` | No | Whether this MCP tool is deferred and discovered via tool search. |
| `project_connection_id` | `string` | No | The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `allowed_tools` — `string[] | OpenAI.MCPToolFilter | null`

**One of the following:**

- **`string[]`** — `string[]`

Type: `string[]`

- **`OpenAI.MCPToolFilter`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `require_approval` — `OpenAI.MCPToolRequireApproval | enum | null`

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`enum`** — `enum`

| Type | Description |
|------|-------------|
| `enum` | _Enum:_ `always`, `never` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `image_generation` — `image_generation (OpenAI.ImageGenTool)`

A tool that generates images using the GPT image models.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation tool. Always `image_generation`. _Default:_ `"image_generation"` _Constant:_ `image_generation` |
| `model` | `enum` | No | _Default:_ `"gpt-image-1"` _Enum:_ `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5` |
| `quality` | `enum` | No | The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `low`, `medium`, `high`, `auto` |
| `size` | `enum` | No | The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. _Default:_ `"auto"` _Enum:_ `1024x1024`, `1024x1536`, `1536x1024`, `auto` |
| `output_format` | `enum` | No | The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. _Default:_ `"png"` _Enum:_ `png`, `webp`, `jpeg` |
| `output_compression` | `OpenAI.integer` | No | Compression level for the output image. Default: 100. _Default:_ `100` _Format:_ `int64` |
| `moderation` | `enum` | No | Moderation level for the generated image. Default: `auto`. _Default:_ `"auto"` _Enum:_ `auto`, `low` |
| `background` | `enum` | No | Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `transparent`, `opaque`, `auto` |
| `input_fidelity` | `enum` | No | _Enum:_ `high`, `low` |
| `input_image_mask` | `OpenAI.ImageGenToolInputImageMask` | No | Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). |
| `partial_images` | `OpenAI.integer` | No | Number of partial images to generate in streaming mode, from 0 (default value) to 3. _Format:_ `int64` |
| `action` | `OpenAI.ImageGenActionEnum` | No | Whether to generate a new image or edit an existing image. Default: `auto`. _Enum:_ `generate`, `edit`, `auto` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `input_image_mask` — `OpenAI.ImageGenToolInputImageMask`

Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `image_url` | `string` | No | _Format:_ `uri` |
| `file_id` | `string` | No |  |

##### `local_shell` — `local_shell (OpenAI.LocalShellToolParam)`

A tool that allows the model to execute shell commands in a local environment.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool. Always `local_shell`. _Default:_ `"local_shell"` _Constant:_ `local_shell` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

##### `shell` — `shell (OpenAI.FunctionShellToolParam)`

A tool that allows the model to execute shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell tool. Always `shell`. _Default:_ `"shell"` _Constant:_ `shell` |
| `environment` | `OpenAI.FunctionShellToolParamEnvironment \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

###### `environment` — `OpenAI.FunctionShellToolParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellToolParamEnvironment`** — `OpenAI.FunctionShellToolParamEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `container_auto`, `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `custom` — `custom (OpenAI.CustomToolParam)`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

###### `format` — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

##### `web_search_preview` — `web_search_preview (OpenAI.WebSearchPreviewTool)`

This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. _Default:_ `"web_search_preview"` _Constant:_ `web_search_preview` |
| `user_location` | `OpenAI.ApproximateLocation \| null` | No |  |
| `search_context_size` | `OpenAI.SearchContextSize` | No | 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. _Enum:_ `low`, `medium`, `high` |
| `search_content_types` | `OpenAI.SearchContentType[]` | No | _Enum:_ `text`, `image` |

###### `user_location` — `OpenAI.ApproximateLocation | null`

**One of the following:**

- **`OpenAI.ApproximateLocation`** — `OpenAI.ApproximateLocation`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `apply_patch` — `apply_patch (OpenAI.ApplyPatchToolParam)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `apply_patch`. _Default:_ `"apply_patch"` _Constant:_ `apply_patch` |

##### `computer` — `computer (OpenAI.ComputerTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool. Always `computer`. _Default:_ `"computer"` _Constant:_ `computer` |

##### `namespace` — `namespace (OpenAI.NamespaceToolParam)`

Groups function/custom tools under a shared namespace.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `namespace`. _Default:_ `"namespace"` _Constant:_ `namespace` |
| `name` | `string` | Yes | The namespace name used in tool calls (for example, `crm`). |
| `description` | `string` | Yes | A description of the namespace shown to the model. |
| `tools` | `(OpenAI.FunctionToolParam \| OpenAI.CustomToolParam)[]` | Yes | The function/custom tools available inside this namespace. |

###### `tools` — `(OpenAI.FunctionToolParam | OpenAI.CustomToolParam)[]`

The function/custom tools available inside this namespace.

**One of the following:**

- **`OpenAI.FunctionToolParam`** — `OpenAI.FunctionToolParam`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes |  |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |
| `strict` | `boolean \| null` | No |  |
| `type` | `enum` | Yes | _Default:_ `"function"` _Constant:_ `function` |
| `defer_loading` | `boolean` | No | Whether this function should be deferred and discovered via tool search. |

- **`OpenAI.CustomToolParam`** — `OpenAI.CustomToolParam`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

##### `tool_search` — `tool_search (OpenAI.ToolSearchToolParam)`

Hosted or BYOT tool search configuration for deferred tools.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `tool_search`. _Default:_ `"tool_search"` _Constant:_ `tool_search` |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search is executed by the server or by the client. _Enum:_ `server`, `client` |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |

#### `tool_choice` — `OpenAI.ToolChoiceOptions | OpenAI.ToolChoiceParam`

**One of the following:**

##### `OpenAI.ToolChoiceOptions` — `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.

| Type | Description |
|------|-------------|
| `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. _Enum:_ `none`, `auto`, `required` |

##### `OpenAI.ToolChoiceParam` — `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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `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`, `computer`, `computer_use` |

#### `prompt` — `OpenAI.Prompt`

Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The unique identifier of the prompt template to use. |
| `version` | `string \| null` | No |  |
| `variables` | `OpenAI.ResponsePromptVariables \| null` | No |  |

#### `error` — `OpenAI.ResponseError | null`

**One of the following:**

##### `OpenAI.ResponseError` — `OpenAI.ResponseError`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `code` | `OpenAI.ResponseErrorCode` | Yes | The error code for the response. _Enum:_ `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` |
| `message` | `string` | Yes | A human-readable description of the error. |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `incomplete_details` — `OpenAI.ResponseIncompleteDetails | null`

**One of the following:**

##### `OpenAI.ResponseIncompleteDetails` — `OpenAI.ResponseIncompleteDetails`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `reason` | `enum` | No | _Enum:_ `max_output_tokens`, `content_filter` |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `output` — `(StructuredOutputsOutputItem | WorkflowActionOutputItem | OAuthConsentRequestOutputItem | BingGroundingToolCall | BingGroundingToolCallOutput | SharepointGroundingToolCall | SharepointGroundingToolCallOutput | AzureAISearchToolCall | AzureAISearchToolCallOutput | BingCustomSearchToolCall | BingCustomSearchToolCallOutput | OpenApiToolCall | OpenApiToolCallOutput | BrowserAutomationToolCall | BrowserAutomationToolCallOutput | FabricDataAgentToolCall | FabricDataAgentToolCallOutput | AzureFunctionToolCall | AzureFunctionToolCallOutput | A2AToolCall | A2AToolCallOutput | MemorySearchToolCall | MemoryCommandToolCall | MemoryCommandToolCallOutput | OpenAI.OutputItemOutputMessage | OpenAI.OutputItemFileSearchToolCall | OpenAI.OutputItemFunctionToolCall | OpenAI.OutputItemFunctionToolCallOutput | OpenAI.OutputItemWebSearchToolCall | OpenAI.OutputItemComputerToolCall | OpenAI.OutputItemComputerToolCallOutput | OpenAI.OutputItemReasoningItem | OpenAI.OutputItemToolSearchCall | OpenAI.OutputItemToolSearchOutput | OpenAI.OutputItemCompactionBody | OpenAI.OutputItemImageGenToolCall | OpenAI.OutputItemCodeInterpreterToolCall | OpenAI.OutputItemLocalShellToolCall | OpenAI.OutputItemLocalShellToolCallOutput | OpenAI.OutputItemFunctionShellCall | OpenAI.OutputItemFunctionShellCallOutput | OpenAI.OutputItemApplyPatchToolCall | OpenAI.OutputItemApplyPatchToolCallOutput | OpenAI.OutputItemMcpToolCall | OpenAI.OutputItemMcpListTools | OpenAI.OutputItemMcpApprovalRequest | OpenAI.OutputItemMcpApprovalResponseResource | OpenAI.OutputItemCustomToolCallResource | OpenAI.OutputItemCustomToolCallOutputResource)[]`

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.

**One of the following:**

##### `structured_outputs` — `structured_outputs (StructuredOutputsOutputItem)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `structured_outputs` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `output` | `any` | Yes | The structured output captured during the response. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `workflow_action` — `workflow_action (WorkflowActionOutputItem)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `workflow_action` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `kind` | `string` | Yes | The kind of CSDL action (e.g., 'SetVariable', 'InvokeAzureAgent'). |
| `action_id` | `string` | Yes | Unique identifier for the action. |
| `parent_action_id` | `string` | No | ID of the parent action if this is a nested action. |
| `previous_action_id` | `string` | No | ID of the previous action if this action follows another. |
| `status` | `enum` | Yes | Status of the action (e.g., 'in_progress', 'completed', 'failed', 'cancelled'). _Enum:_ `completed`, `failed`, `in_progress`, `cancelled` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `oauth_consent_request` — `oauth_consent_request (OAuthConsentRequestOutputItem)`

Request from the service for the user to perform OAuth consent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `oauth_consent_request` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes |  |
| `consent_link` | `string` | Yes | The link the user can use to perform OAuth consent. |
| `server_label` | `string` | Yes | The server label for the OAuth consent request. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `bing_grounding_call` — `bing_grounding_call (BingGroundingToolCall)`

A Bing grounding tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `bing_grounding_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `bing_grounding_call_output` — `bing_grounding_call_output (BingGroundingToolCallOutput)`

The output of a Bing grounding tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `bing_grounding_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the Bing grounding tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `sharepoint_grounding_preview_call` — `sharepoint_grounding_preview_call (SharepointGroundingToolCall)`

A SharePoint grounding tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `sharepoint_grounding_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `sharepoint_grounding_preview_call_output` — `sharepoint_grounding_preview_call_output (SharepointGroundingToolCallOutput)`

The output of a SharePoint grounding tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `sharepoint_grounding_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the SharePoint grounding tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `azure_ai_search_call` — `azure_ai_search_call (AzureAISearchToolCall)`

An Azure AI Search tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `azure_ai_search_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `azure_ai_search_call_output` — `azure_ai_search_call_output (AzureAISearchToolCallOutput)`

The output of an Azure AI Search tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `azure_ai_search_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the Azure AI Search tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `bing_custom_search_preview_call` — `bing_custom_search_preview_call (BingCustomSearchToolCall)`

A Bing custom search tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `bing_custom_search_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `bing_custom_search_preview_call_output` — `bing_custom_search_preview_call_output (BingCustomSearchToolCallOutput)`

The output of a Bing custom search tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `bing_custom_search_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the Bing custom search tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `openapi_call` — `openapi_call (OpenApiToolCall)`

An OpenAPI tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `openapi_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the OpenAPI operation being called. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `openapi_call_output` — `openapi_call_output (OpenApiToolCallOutput)`

The output of an OpenAPI tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `openapi_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the OpenAPI operation that was called. |
| `output` | `object \| string \| any[]` | No | The output from the OpenAPI tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `browser_automation_preview_call` — `browser_automation_preview_call (BrowserAutomationToolCall)`

A browser automation tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `browser_automation_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `browser_automation_preview_call_output` — `browser_automation_preview_call_output (BrowserAutomationToolCallOutput)`

The output of a browser automation tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `browser_automation_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the browser automation tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `fabric_dataagent_preview_call` — `fabric_dataagent_preview_call (FabricDataAgentToolCall)`

A Fabric data agent tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `fabric_dataagent_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `fabric_dataagent_preview_call_output` — `fabric_dataagent_preview_call_output (FabricDataAgentToolCallOutput)`

The output of a Fabric data agent tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `fabric_dataagent_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `output` | `object \| string \| any[]` | No | The output from the Fabric data agent tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `azure_function_call` — `azure_function_call (AzureFunctionToolCall)`

An Azure Function tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `azure_function_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the Azure Function being called. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `azure_function_call_output` — `azure_function_call_output (AzureFunctionToolCallOutput)`

The output of an Azure Function tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `azure_function_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the Azure Function that was called. |
| `output` | `object \| string \| any[]` | No | The output from the Azure Function tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `a2a_preview_call` — `a2a_preview_call (A2AToolCall)`

An A2A (Agent-to-Agent) tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `a2a_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the A2A agent card being called. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `a2a_preview_call_output` — `a2a_preview_call_output (A2AToolCallOutput)`

The output of an A2A (Agent-to-Agent) tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `a2a_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `name` | `string` | Yes | The name of the A2A agent card that was called. |
| `output` | `object \| string \| any[]` | No | The output from the A2A tool call. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `memory_search_call` — `memory_search_call (MemorySearchToolCall)`

A memory search tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `memory_search_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |
| `memories` | `(UserProfileMemoryItem \| ChatSummaryMemoryItem \| ProceduralMemoryItem)[] \| null` | No | The results returned from the memory search. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `memories` — `(UserProfileMemoryItem | ChatSummaryMemoryItem | ProceduralMemoryItem)[] | null`

The results returned from the memory search.

**One of the following:**

- **`(UserProfileMemoryItem | ChatSummaryMemoryItem | ProceduralMemoryItem)[]`** — `(UserProfileMemoryItem | ChatSummaryMemoryItem | ProceduralMemoryItem)[]`

**One of the following:**

- **`user_profile`** — `user_profile (UserProfileMemoryItem)`

A memory item specifically containing user profile information extracted from conversations, such as preferences, interests, and personal details.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `memory_id` | `string` | Yes | The unique ID of the memory item. |
| `updated_at` | `FoundryTimestamp` | Yes | The last update time of the memory item. _Format:_ `unixtime` |
| `scope` | `string` | Yes | The namespace that logically groups and isolates memories, such as a user ID. |
| `content` | `string` | Yes | The content of the memory. |
| `kind` | `enum` | Yes | The kind of the memory item. _Constant:_ `user_profile` |

- **`chat_summary`** — `chat_summary (ChatSummaryMemoryItem)`

A memory item containing a summary extracted from conversations.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `memory_id` | `string` | Yes | The unique ID of the memory item. |
| `updated_at` | `FoundryTimestamp` | Yes | The last update time of the memory item. _Format:_ `unixtime` |
| `scope` | `string` | Yes | The namespace that logically groups and isolates memories, such as a user ID. |
| `content` | `string` | Yes | The content of the memory. |
| `kind` | `enum` | Yes | The kind of the memory item. _Constant:_ `chat_summary` |

- **`procedural`** — `procedural (ProceduralMemoryItem)`

A memory item containing a procedure extracted from conversations.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `memory_id` | `string` | Yes | The unique ID of the memory item. |
| `updated_at` | `FoundryTimestamp` | Yes | The last update time of the memory item. _Format:_ `unixtime` |
| `scope` | `string` | Yes | The namespace that logically groups and isolates memories, such as a user ID. |
| `content` | `string` | Yes | The content of the memory. |
| `kind` | `enum` | Yes | The kind of the memory item. _Constant:_ `procedural` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `memory_command_preview_call` — `memory_command_preview_call (MemoryCommandToolCall)`

A memory command tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `memory_command_preview_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the tool, including `action` (`remember` or `forget`) and `content`. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `memory_command_preview_call_output` — `memory_command_preview_call_output (MemoryCommandToolCallOutput)`

The output of a memory command tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `memory_command_preview_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `call_id` | `string` | Yes | The unique ID of the tool call generated by the model. |
| `status` | `ToolCallStatus` | Yes | The status of the tool call. _Enum:_ `in_progress`, `completed`, `incomplete`, `failed` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `output_message` — `output_message (OpenAI.OutputItemOutputMessage)`

An output message from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output message. Always `message`. _Constant:_ `output_message` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the output message. |
| `role` | `enum` | Yes | The role of the output message. Always `assistant`. _Constant:_ `assistant` |
| `content` | `(OpenAI.OutputMessageContentOutputTextContent \| OpenAI.OutputMessageContentRefusalContent)[]` | Yes | The content of the output message. |
| `phase` | `enum` | No | _Enum:_ `commentary`, `final_answer` |
| `status` | `enum` | Yes | The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `content` — `(OpenAI.OutputMessageContentOutputTextContent | OpenAI.OutputMessageContentRefusalContent)[]`

The content of the output message.

**One of the following:**

- **`output_text`** — `output_text (OpenAI.OutputMessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`refusal`** — `refusal (OpenAI.OutputMessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

##### `file_search_call` — `file_search_call (OpenAI.OutputItemFileSearchToolCall)`

The results of a file search tool call. See the [file search guide](/docs/guides/tools-file-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool call. Always `file_search_call`. _Constant:_ `file_search_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the file search tool call. |
| `status` | `enum` | Yes | The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, _Enum:_ `in_progress`, `searching`, `completed`, `incomplete`, `failed` |
| `queries` | `string[]` | Yes | The queries used to search for files. |
| `results` | `OpenAI.FileSearchToolCallResults[] \| null` | No |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `results` — `OpenAI.FileSearchToolCallResults[] | null`

**One of the following:**

- **`OpenAI.FileSearchToolCallResults[]`** — `OpenAI.FileSearchToolCallResults[]`

**Array of** `OpenAI.FileSearchToolCallResults`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `file_id` | `string` | No |  |
| `text` | `string` | No |  |
| `filename` | `string` | No |  |
| `attributes` | `OpenAI.VectorStoreFileAttributes \| null` | No |  |
| `score` | `number` | No | _Format:_ `float` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `function_call` — `function_call (OpenAI.OutputItemFunctionToolCall)`

A tool call to run a function. See the [function calling guide](/docs/guides/function-calling) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call. Always `function_call`. _Constant:_ `function_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the function tool call. |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `namespace` | `string` | No | The namespace of the function to run. |
| `name` | `string` | Yes | The name of the function to run. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the function. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `function_call_output` — `function_call_output (OpenAI.OutputItemFunctionToolCallOutput)`

The output of a function tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call output. Always `function_call_output`. _Constant:_ `function_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the function tool call output. Populated when this item is returned via API. |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `output` | `string \| (OpenAI.FunctionAndCustomToolCallOutputInputTextContent \| OpenAI.FunctionAndCustomToolCallOutputInputImageContent \| OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]` | Yes | The output from the function call generated by your code. Can be a string or an list of output content. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `output` — `string | (OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

The output from the function call generated by your code. Can be a string or an list of output content.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`** — `(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

**One of the following:**

- **`input_text`** — `input_text (OpenAI.FunctionAndCustomToolCallOutputInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.FunctionAndCustomToolCallOutputInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.FunctionAndCustomToolCallOutputInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

##### `web_search_call` — `web_search_call (OpenAI.OutputItemWebSearchToolCall)`

The results of a web search tool call. See the [web search guide](/docs/guides/tools-web-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool call. Always `web_search_call`. _Constant:_ `web_search_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the web search tool call. |
| `status` | `enum` | Yes | The status of the web search tool call. _Enum:_ `in_progress`, `searching`, `completed`, `failed` |
| `action` | `OpenAI.WebSearchActionSearch \| OpenAI.WebSearchActionOpenPage \| OpenAI.WebSearchActionFind` | Yes | 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_in_page). |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `action` — `OpenAI.WebSearchActionSearch | OpenAI.WebSearchActionOpenPage | 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_in_page).

**One of the following:**

- **`OpenAI.WebSearchActionSearch`** — `OpenAI.WebSearchActionSearch`

Action type "search" - Performs a web search query.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `search` |
| `query` | `string` | Yes | [DEPRECATED] The search query. |
| `queries` | `string[]` | No | The search queries. |
| `sources` | `OpenAI.WebSearchActionSearchSources[]` | No | The sources used in the search. |

- **`sources`** — `OpenAI.WebSearchActionSearchSources[]`

The sources used in the search.

**Array of** `OpenAI.WebSearchActionSearchSources`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `url` |
| `url` | `string` | Yes | _Format:_ `uri` |

- **`OpenAI.WebSearchActionOpenPage`** — `OpenAI.WebSearchActionOpenPage`

Action type "open_page" - Opens a specific URL from search results.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `open_page` |
| `url` | `string \| null` | No | The URL opened by the model. |

- **`OpenAI.WebSearchActionFind`** — `OpenAI.WebSearchActionFind`

Action type "find_in_page": Searches for a pattern within a loaded page.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `find_in_page` |
| `url` | `string` | Yes | The URL of the page searched for the pattern. _Format:_ `uri` |
| `pattern` | `string` | Yes | The pattern or text to search for within the page. |

##### `computer_call` — `computer_call (OpenAI.OutputItemComputerToolCall)`

A tool call to a computer use tool. See the [computer use guide](/docs/guides/tools-computer-use) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer call. Always `computer_call`. _Default:_ `"computer_call"` _Constant:_ `computer_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the computer call. |
| `call_id` | `string` | Yes | An identifier used when responding to the tool call with output. |
| `action` | `OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam` | No |  |
| `actions` | `(OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam)[]` | No | Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. |
| `pending_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[]` | Yes | The pending safety checks for the computer call. |
| `status` | `enum` | Yes | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `action` — `OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam`

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

###### `actions` — `(OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam)[]`

Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields.

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

###### `pending_safety_checks` — `OpenAI.ComputerCallSafetyCheckParam[]`

The pending safety checks for the computer call.

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

##### `computer_call_output` — `computer_call_output (OpenAI.OutputItemComputerToolCallOutput)`

The output of a computer tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool call output. Always `computer_call_output`. _Default:_ `"computer_call_output"` _Constant:_ `computer_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The ID of the computer tool call output. |
| `call_id` | `string` | Yes | The ID of the computer tool call that produced the output. |
| `acknowledged_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[]` | No | The safety checks reported by the API that have been acknowledged by the developer. |
| `output` | `OpenAI.ComputerScreenshotImage` | Yes | A computer screenshot image used with the computer use tool. |
| `status` | `enum` | No | The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `acknowledged_safety_checks` — `OpenAI.ComputerCallSafetyCheckParam[]`

The safety checks reported by the API that have been acknowledged by the developer.

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

###### `output` — `OpenAI.ComputerScreenshotImage`

A computer screenshot image used with the computer use tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string` | No | The URL of the screenshot image. _Format:_ `uri` |
| `file_id` | `string` | No | The identifier of an uploaded file that contains the screenshot. |

##### `reasoning` — `reasoning (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](/docs/guides/conversation-state).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `reasoning`. _Constant:_ `reasoning` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique identifier of the reasoning content. |
| `encrypted_content` | `string \| null` | No |  |
| `summary` | `(OpenAI.TextContent \| OpenAI.ComputerScreenshotContent \| OpenAI.MessageContentInputTextContent \| OpenAI.MessageContentOutputTextContent \| OpenAI.MessageContentReasoningTextContent \| OpenAI.MessageContentRefusalContent \| OpenAI.MessageContentInputImageContent \| OpenAI.MessageContentInputFileContent \| OpenAI.SummaryTextContent)[]` | Yes | Reasoning summary content. |
| `content` | `OpenAI.ReasoningTextContent[]` | No | Reasoning text content. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `summary` — `(OpenAI.TextContent | OpenAI.ComputerScreenshotContent | OpenAI.MessageContentInputTextContent | OpenAI.MessageContentOutputTextContent | OpenAI.MessageContentReasoningTextContent | OpenAI.MessageContentRefusalContent | OpenAI.MessageContentInputImageContent | OpenAI.MessageContentInputFileContent | OpenAI.SummaryTextContent)[]`

Reasoning summary content.

**One of the following:**

- **`text`** — `text (OpenAI.TextContent)`

A text content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Default:_ `"text"` _Constant:_ `text` |
| `text` | `string` | Yes |  |

- **`computer_screenshot`** — `computer_screenshot (OpenAI.ComputerScreenshotContent)`

A screenshot of a computer.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string \| null` | Yes |  |
| `file_id` | `string \| null` | Yes |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the screenshot image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_text`** — `input_text (OpenAI.MessageContentInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`output_text`** — `output_text (OpenAI.MessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`reasoning_text`** — `reasoning_text (OpenAI.MessageContentReasoningTextContent)`

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

- **`refusal`** — `refusal (OpenAI.MessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

- **`input_image`** — `input_image (OpenAI.MessageContentInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.MessageContentInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

- **`summary_text`** — `summary_text (OpenAI.SummaryTextContent)`

A summary text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `summary_text`. _Default:_ `"summary_text"` _Constant:_ `summary_text` |
| `text` | `string` | Yes | A summary of the reasoning output from the model so far. |

###### `content` — `OpenAI.ReasoningTextContent[]`

Reasoning text content.

**Array of** `OpenAI.ReasoningTextContent`**:**

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

##### `tool_search_call` — `tool_search_call (OpenAI.OutputItemToolSearchCall)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `tool_search_call`. _Default:_ `"tool_search_call"` _Constant:_ `tool_search_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the tool search call item. |
| `call_id` | `string \| null` | Yes |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | Yes | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `arguments` | `any` | Yes | Arguments used for the tool search call. |
| `status` | `OpenAI.FunctionCallStatus` | Yes | The status of the tool search call item that was recorded. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `tool_search_output` — `tool_search_output (OpenAI.OutputItemToolSearchOutput)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `tool_search_output`. _Default:_ `"tool_search_output"` _Constant:_ `tool_search_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the tool search output item. |
| `call_id` | `string \| null` | Yes |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | Yes | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `tools` | `(BingGroundingTool \| MicrosoftFabricPreviewTool \| SharepointPreviewTool \| AzureAISearchTool \| OpenApiTool \| BingCustomSearchPreviewTool \| BrowserAutomationPreviewTool \| AzureFunctionTool \| CaptureStructuredOutputsTool \| A2APreviewTool \| WorkIQPreviewTool \| FabricIQPreviewTool \| MemorySearchPreviewTool \| ToolboxSearchPreviewTool \| OpenAI.CodeInterpreterTool \| OpenAI.FunctionTool \| OpenAI.FileSearchTool \| OpenAI.ComputerUsePreviewTool \| OpenAI.WebSearchTool \| OpenAI.MCPTool \| OpenAI.ImageGenTool \| OpenAI.LocalShellToolParam \| OpenAI.FunctionShellToolParam \| OpenAI.CustomToolParam \| OpenAI.WebSearchPreviewTool \| OpenAI.ApplyPatchToolParam \| OpenAI.ComputerTool \| OpenAI.NamespaceToolParam \| OpenAI.ToolSearchToolParam)[]` | Yes | The loaded tool definitions returned by tool search. |
| `status` | `OpenAI.FunctionCallOutputStatusEnum` | Yes | The status of the tool search output item that was recorded. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `tools` — `(BingGroundingTool | MicrosoftFabricPreviewTool | SharepointPreviewTool | AzureAISearchTool | OpenApiTool | BingCustomSearchPreviewTool | BrowserAutomationPreviewTool | AzureFunctionTool | CaptureStructuredOutputsTool | A2APreviewTool | WorkIQPreviewTool | FabricIQPreviewTool | MemorySearchPreviewTool | ToolboxSearchPreviewTool | OpenAI.CodeInterpreterTool | OpenAI.FunctionTool | OpenAI.FileSearchTool | OpenAI.ComputerUsePreviewTool | OpenAI.WebSearchTool | OpenAI.MCPTool | OpenAI.ImageGenTool | OpenAI.LocalShellToolParam | OpenAI.FunctionShellToolParam | OpenAI.CustomToolParam | OpenAI.WebSearchPreviewTool | OpenAI.ApplyPatchToolParam | OpenAI.ComputerTool | OpenAI.NamespaceToolParam | OpenAI.ToolSearchToolParam)[]`

The loaded tool definitions returned by tool search.

**One of the following:**

- **`bing_grounding`** — `bing_grounding (BingGroundingTool)`

The input definition information for a bing grounding search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_grounding'. _Constant:_ `bing_grounding` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_grounding` | `BingGroundingSearchToolParameters` | Yes | The bing grounding search tool parameters. |

- **`bing_grounding`** — `BingGroundingSearchToolParameters`

The bing grounding search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingGroundingSearchConfiguration[]` | Yes | The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. |

- **`search_configurations`** — `BingGroundingSearchConfiguration[]`

The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool.

**Array of** `BingGroundingSearchConfiguration`**:**

Search configuration for Bing Grounding

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`fabric_dataagent_preview`** — `fabric_dataagent_preview (MicrosoftFabricPreviewTool)`

The input definition information for a Microsoft Fabric tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_dataagent_preview'. _Constant:_ `fabric_dataagent_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `fabric_dataagent_preview` | `FabricDataAgentToolParameters` | Yes | The fabric data agent tool parameters. |

- **`fabric_dataagent_preview`** — `FabricDataAgentToolParameters`

The fabric data agent tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`sharepoint_grounding_preview`** — `sharepoint_grounding_preview (SharepointPreviewTool)`

The input definition information for a sharepoint tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'sharepoint_grounding_preview'. _Constant:_ `sharepoint_grounding_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `sharepoint_grounding_preview` | `SharepointGroundingToolParameters` | Yes | The sharepoint grounding tool parameters. |

- **`sharepoint_grounding_preview`** — `SharepointGroundingToolParameters`

The sharepoint grounding tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`azure_ai_search`** — `azure_ai_search (AzureAISearchTool)`

The input definition information for an Azure AI search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'azure_ai_search'. _Constant:_ `azure_ai_search` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `azure_ai_search` | `AzureAISearchToolResource` | Yes | The azure ai search index resource. |

- **`azure_ai_search`** — `AzureAISearchToolResource`

The azure ai search index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `indexes` | `AISearchIndexResource[]` | Yes | The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. |

- **`indexes`** — `AISearchIndexResource[]`

The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent.

**Array of** `AISearchIndexResource`**:**

A AI Search Index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | No | An index connection ID in an IndexResource attached to this agent. |
| `index_name` | `string` | No | The name of an index in an IndexResource attached to this agent. |
| `query_type` | `enum` | No | Type of query in an AIIndexResource attached to this agent. _Enum:_ `simple`, `semantic`, `vector`, `vector_simple_hybrid`, `vector_semantic_hybrid` |
| `top_k` | `integer` | No | Number of documents to retrieve from search and present to the model. _Format:_ `int32` |
| `filter` | `string` | No | filter string for search resource. [Learn more here](https://learn.microsoft.com/azure/search/search-filters). |
| `index_asset_id` | `string` | No | Index asset id for search resource. |

- **`openapi`** — `openapi (OpenApiTool)`

The input definition information for an OpenAPI tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'openapi'. _Constant:_ `openapi` |
| `openapi` | `OpenApiFunctionDefinition` | Yes | The openapi function definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`openapi`** — `OpenApiFunctionDefinition`

The openapi function definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the function to be called. |
| `description` | `string` | No | A description of what the function does, used by the model to choose when and how to call the function. |
| `spec` | `object` | Yes | The openapi function shape, described as a JSON Schema object. |
| `auth` | `OpenApiAnonymousAuthDetails \| OpenApiProjectConnectionAuthDetails \| OpenApiManagedAuthDetails` | Yes | Open API authentication details |
| `default_params` | `string[]` | No | List of OpenAPI spec parameters that will use user-provided defaults |
| `functions` | `object[]` | No | List of function definitions used by OpenApi tool |

- **`auth`** — `OpenApiAnonymousAuthDetails | OpenApiProjectConnectionAuthDetails | OpenApiManagedAuthDetails`

Open API authentication details

**One of the following:**

- **`anonymous`** — `anonymous (OpenApiAnonymousAuthDetails)`

Security details for OpenApi anonymous authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'anonymous'. _Constant:_ `anonymous` |

- **`project_connection`** — `project_connection (OpenApiProjectConnectionAuthDetails)`

Security details for OpenApi project connection authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'project_connection'. _Constant:_ `project_connection` |
| `security_scheme` | `OpenApiProjectConnectionSecurityScheme` | Yes | Project connection auth security details |

- **`security_scheme`** — `OpenApiProjectConnectionSecurityScheme`

Project connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for Project Connection auth type |

- **`managed_identity`** — `managed_identity (OpenApiManagedAuthDetails)`

Security details for OpenApi managed_identity authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'managed_identity'. _Constant:_ `managed_identity` |
| `security_scheme` | `OpenApiManagedSecurityScheme` | Yes | Connection auth security details |

- **`security_scheme`** — `OpenApiManagedSecurityScheme`

Connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `audience` | `string` | Yes | Authentication scope for managed_identity auth type |

- **`functions`** — `object[]`

List of function definitions used by OpenApi tool

**Array of** `object`**:**

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

- **`bing_custom_search_preview`** — `bing_custom_search_preview (BingCustomSearchPreviewTool)`

The input definition information for a Bing custom search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_custom_search_preview'. _Constant:_ `bing_custom_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_custom_search_preview` | `BingCustomSearchToolParameters` | Yes | The bing custom search tool parameters. |

- **`bing_custom_search_preview`** — `BingCustomSearchToolParameters`

The bing custom search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingCustomSearchConfiguration[]` | Yes | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`search_configurations`** — `BingCustomSearchConfiguration[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `BingCustomSearchConfiguration`**:**

A bing custom search configuration.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`browser_automation_preview`** — `browser_automation_preview (BrowserAutomationPreviewTool)`

The input definition information for a Browser Automation Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation_preview'. _Constant:_ `browser_automation_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `browser_automation_preview` | `BrowserAutomationToolParameters` | Yes | The Browser Automation Tool parameters. |

- **`browser_automation_preview`** — `BrowserAutomationToolParameters`

The Browser Automation Tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `connection` | `BrowserAutomationToolConnectionParameters` | Yes | The project connection parameters associated with the Browser Automation Tool. |

- **`connection`** — `BrowserAutomationToolConnectionParameters`

The project connection parameters associated with the Browser Automation Tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | The ID of the project connection to your Azure Playwright resource. |

- **`azure_function`** — `azure_function (AzureFunctionTool)`

The input definition information for an Azure Function Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation'. _Constant:_ `azure_function` |
| `azure_function` | `AzureFunctionDefinition` | Yes | The Azure Function Tool definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`azure_function`** — `AzureFunctionDefinition`

The Azure Function Tool definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `function` | `object` | Yes | The definition of azure function and its parameters. |
| `input_binding` | `AzureFunctionBinding` | Yes | Input storage queue. The queue storage trigger runs a function as messages are added to it. |
| `output_binding` | `AzureFunctionBinding` | Yes | Output storage queue. The function writes output to this queue when the input items are processed. |

- **`function`** — `object`

The definition of azure function and its parameters.

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

- **`input_binding`** — `AzureFunctionBinding`

Input storage queue. The queue storage trigger runs a function as messages are added to it.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`output_binding`** — `AzureFunctionBinding`

Output storage queue. The function writes output to this queue when the input items are processed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`capture_structured_outputs`** — `capture_structured_outputs (CaptureStructuredOutputsTool)`

A tool for capturing structured outputs

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `capture_structured_outputs`. _Constant:_ `capture_structured_outputs` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `outputs` | `StructuredOutputDefinition` | Yes | The structured outputs to capture from the model. |

- **`outputs`** — `StructuredOutputDefinition`

The structured outputs to capture from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the structured output. |
| `description` | `string` | Yes | A description of the output to emit. Used by the model to determine when to emit the output. |
| `schema` | `object` | Yes | The JSON schema for the structured output. |
| `strict` | `boolean \| null` | Yes | Whether to enforce strict validation. Default `true`. |

- **`a2a_preview`** — `a2a_preview (A2APreviewTool)`

An agent implementing the A2A protocol.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `"a2a_preview`. _Constant:_ `a2a_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `base_url` | `string` | No | Base URL of the agent. _Format:_ `uri` |
| `agent_card_path` | `string` | No | The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json` |
| `project_connection_id` | `string` | No | The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server. |

- **`work_iq_preview`** — `work_iq_preview (WorkIQPreviewTool)`

A WorkIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'work_iq_preview'. _Constant:_ `work_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the WorkIQ project connection. |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`fabric_iq_preview`** — `fabric_iq_preview (FabricIQPreviewTool)`

A FabricIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_iq_preview'. _Constant:_ `fabric_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the FabricIQ project connection. |
| `server_label` | `string` | No | (Optional) The label of the FabricIQ MCP server to connect to. |
| `server_url` | `string` | No | (Optional) The URL of the FabricIQ MCP server. If not provided, the URL from the project connection will be used. _Format:_ `uri` |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| string \| null` | No | (Optional) Whether the agent requires approval before executing actions. Default is always. _Default:_ `"always"` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | string | null`

(Optional) Whether the agent requires approval before executing actions. Default is always.

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`memory_search_preview`** — `memory_search_preview (MemorySearchPreviewTool)`

A tool for integrating memories into the agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `memory_search_preview`. _Constant:_ `memory_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `memory_store_name` | `string` | Yes | The name of the memory store to use. |
| `scope` | `string` | Yes | The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user. |
| `search_options` | `MemorySearchOptions` | No | Options for searching the memory store. |
| `update_delay` | `integer` | No | Time to wait before updating memories after inactivity (seconds). Default 300. _Default:_ `300` _Format:_ `int32` |

- **`search_options`** — `MemorySearchOptions`

Options for searching the memory store.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `max_memories` | `integer` | No | Maximum number of memory items to return. _Format:_ `int32` |

- **`toolbox_search_preview`** — `toolbox_search_preview (ToolboxSearchPreviewTool)`

A tool for searching over the agent's toolbox. When present, deferred tools are hidden from `tools/list` and only discoverable via `search_tools` queries at runtime.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `toolbox_search_preview`. _Constant:_ `toolbox_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`code_interpreter`** — `code_interpreter (OpenAI.CodeInterpreterTool)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool. Always `code_interpreter`. _Constant:_ `code_interpreter` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `container` | `string \| OpenAI.AutoCodeInterpreterToolParam` | No | 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. If not provided, the service assumes auto. |

- **`container`** — `string | OpenAI.AutoCodeInterpreterToolParam`

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. If not provided, the service assumes auto.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.AutoCodeInterpreterToolParam`** — `OpenAI.AutoCodeInterpreterToolParam`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Always `auto`. _Default:_ `"auto"` _Constant:_ `auto` |
| `file_ids` | `string[]` | No | An optional list of uploaded files to make available to your code. |
| `memory_limit` | `enum` | No | _Enum:_ `1g`, `4g`, `16g`, `64g` |
| `network_policy` | `OpenAI.ContainerNetworkPolicyDisabledParam \| OpenAI.ContainerNetworkPolicyAllowlistParam` | No | Network access policy for the container. |

- **`network_policy`** — `OpenAI.ContainerNetworkPolicyDisabledParam | OpenAI.ContainerNetworkPolicyAllowlistParam`

Network access policy for the container.

**One of the following:**

- **`disabled`** — `disabled (OpenAI.ContainerNetworkPolicyDisabledParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Disable outbound network access. Always `disabled`. _Default:_ `"disabled"` _Constant:_ `disabled` |

- **`allowlist`** — `allowlist (OpenAI.ContainerNetworkPolicyAllowlistParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Allow outbound network access only to specified domains. Always `allowlist`. _Default:_ `"allowlist"` _Constant:_ `allowlist` |
| `allowed_domains` | `string[]` | Yes | A list of allowed domains when type is `allowlist`. |

- **`function`** — `function (OpenAI.FunctionTool)`

Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool. Always `function`. _Default:_ `"function"` _Constant:_ `function` |
| `name` | `string` | Yes | The name of the function to call. |
| `description` | `string \| null` | No |  |
| `parameters` | `object \| null` | Yes |  |
| `strict` | `boolean \| null` | Yes |  |
| `defer_loading` | `boolean` | No | Whether this function is deferred and loaded via tool search. |

- **`file_search`** — `file_search (OpenAI.FileSearchTool)`

A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool. Always `file_search`. _Default:_ `"file_search"` _Constant:_ `file_search` |
| `vector_store_ids` | `string[]` | Yes | The IDs of the vector stores to search. |
| `max_num_results` | `OpenAI.integer` | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. _Format:_ `int64` |
| `ranking_options` | `OpenAI.RankingOptions` | No | Ranking options for search. |
| `filters` | `OpenAI.ComparisonFilter \| OpenAI.CompoundFilter \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`ranking_options`** — `OpenAI.RankingOptions`

Ranking options for search.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `ranker` | `OpenAI.RankerVersionType` | No | The ranker to use for the file search. _Enum:_ `auto`, `default-2024-11-15` |
| `score_threshold` | `OpenAI.numeric` | No | 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. _Format:_ `double` |
| `hybrid_search` | `OpenAI.HybridSearchOptions` | No | Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. |

- **`hybrid_search`** — `OpenAI.HybridSearchOptions`

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `embedding_weight` | `OpenAI.numeric` | Yes | The weight of the embedding in the reciprocal ranking fusion. _Format:_ `double` |
| `text_weight` | `OpenAI.numeric` | Yes | The weight of the text in the reciprocal ranking fusion. _Format:_ `double` |

- **`filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter | null`

**One of the following:**

- **`OpenAI.Filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter`

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`OpenAI.CompoundFilter`** — `OpenAI.CompoundFilter`

Combine multiple filters using `and` or `or`.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Type of operation: `and` or `or`. _Enum:_ `and`, `or` |
| `filters` | `(OpenAI.ComparisonFilter \| any)[]` | Yes | Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. |

- **`filters`** — `(OpenAI.ComparisonFilter | any)[]`

Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`any`** — `any`

| Type | Description |
|------|-------------|
| `any` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`computer_use_preview`** — `computer_use_preview (OpenAI.ComputerUsePreviewTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer use tool. Always `computer_use_preview`. _Default:_ `"computer_use_preview"` _Constant:_ `computer_use_preview` |
| `environment` | `OpenAI.ComputerEnvironment` | Yes | The type of computer environment to control. _Enum:_ `windows`, `mac`, `linux`, `ubuntu`, `browser` |
| `display_width` | `OpenAI.integer` | Yes | The width of the computer display. _Format:_ `int64` |
| `display_height` | `OpenAI.integer` | Yes | The height of the computer display. _Format:_ `int64` |

- **`web_search`** — `web_search (OpenAI.WebSearchTool)`

Search the Internet for sources related to the prompt. Learn more about the [web search tool](/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. _Default:_ `"web_search"` _Constant:_ `web_search` |
| `filters` | `OpenAI.WebSearchToolFilters \| null` | No |  |
| `user_location` | `OpenAI.WebSearchApproximateLocation \| null` | No |  |
| `search_context_size` | `enum` | No | 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. _Default:_ `"medium"` _Enum:_ `low`, `medium`, `high` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `custom_search_configuration` | `WebSearchConfiguration` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`filters`** — `OpenAI.WebSearchToolFilters | null`

**One of the following:**

- **`OpenAI.WebSearchToolFilters`** — `OpenAI.WebSearchToolFilters`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `allowed_domains` | `string[] \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`user_location`** — `OpenAI.WebSearchApproximateLocation | null`

**One of the following:**

- **`OpenAI.WebSearchApproximateLocation`** — `OpenAI.WebSearchApproximateLocation`

The approximate location of the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom_search_configuration`** — `WebSearchConfiguration`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing custom search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |

- **`mcp`** — `mcp (OpenAI.MCPTool)`

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the MCP tool. Always `mcp`. _Constant:_ `mcp` |
| `server_label` | `string` | Yes | A label for this MCP server, used to identify it in tool calls. |
| `server_url` | `string` | No | The URL for the MCP server. One of `server_url` or `connector_id` must be provided. _Format:_ `uri` |
| `connector_id` | `enum` | No | Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors [here](/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` _Enum:_ `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint` |
| `authorization` | `string` | No | An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. |
| `server_description` | `string` | No | Optional description of the MCP server, used to provide more context. |
| `headers` | `object \| null` | No |  |
| `allowed_tools` | `string[] \| OpenAI.MCPToolFilter \| null` | No |  |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| enum \| null` | No | _Default:_ `"always"` _Enum:_ `always`, `never` |
| `defer_loading` | `boolean` | No | Whether this MCP tool is deferred and discovered via tool search. |
| `project_connection_id` | `string` | No | The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`allowed_tools`** — `string[] | OpenAI.MCPToolFilter | null`

**One of the following:**

- **`string[]`** — `string[]`

Type: `string[]`

- **`OpenAI.MCPToolFilter`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | enum | null`

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`enum`** — `enum`

| Type | Description |
|------|-------------|
| `enum` | _Enum:_ `always`, `never` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`image_generation`** — `image_generation (OpenAI.ImageGenTool)`

A tool that generates images using the GPT image models.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation tool. Always `image_generation`. _Default:_ `"image_generation"` _Constant:_ `image_generation` |
| `model` | `enum` | No | _Default:_ `"gpt-image-1"` _Enum:_ `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5` |
| `quality` | `enum` | No | The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `low`, `medium`, `high`, `auto` |
| `size` | `enum` | No | The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. _Default:_ `"auto"` _Enum:_ `1024x1024`, `1024x1536`, `1536x1024`, `auto` |
| `output_format` | `enum` | No | The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. _Default:_ `"png"` _Enum:_ `png`, `webp`, `jpeg` |
| `output_compression` | `OpenAI.integer` | No | Compression level for the output image. Default: 100. _Default:_ `100` _Format:_ `int64` |
| `moderation` | `enum` | No | Moderation level for the generated image. Default: `auto`. _Default:_ `"auto"` _Enum:_ `auto`, `low` |
| `background` | `enum` | No | Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `transparent`, `opaque`, `auto` |
| `input_fidelity` | `enum` | No | _Enum:_ `high`, `low` |
| `input_image_mask` | `OpenAI.ImageGenToolInputImageMask` | No | Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). |
| `partial_images` | `OpenAI.integer` | No | Number of partial images to generate in streaming mode, from 0 (default value) to 3. _Format:_ `int64` |
| `action` | `OpenAI.ImageGenActionEnum` | No | Whether to generate a new image or edit an existing image. Default: `auto`. _Enum:_ `generate`, `edit`, `auto` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`input_image_mask`** — `OpenAI.ImageGenToolInputImageMask`

Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `image_url` | `string` | No | _Format:_ `uri` |
| `file_id` | `string` | No |  |

- **`local_shell`** — `local_shell (OpenAI.LocalShellToolParam)`

A tool that allows the model to execute shell commands in a local environment.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool. Always `local_shell`. _Default:_ `"local_shell"` _Constant:_ `local_shell` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`shell`** — `shell (OpenAI.FunctionShellToolParam)`

A tool that allows the model to execute shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell tool. Always `shell`. _Default:_ `"shell"` _Constant:_ `shell` |
| `environment` | `OpenAI.FunctionShellToolParamEnvironment \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`environment`** — `OpenAI.FunctionShellToolParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellToolParamEnvironment`** — `OpenAI.FunctionShellToolParamEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `container_auto`, `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom`** — `custom (OpenAI.CustomToolParam)`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`web_search_preview`** — `web_search_preview (OpenAI.WebSearchPreviewTool)`

This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. _Default:_ `"web_search_preview"` _Constant:_ `web_search_preview` |
| `user_location` | `OpenAI.ApproximateLocation \| null` | No |  |
| `search_context_size` | `OpenAI.SearchContextSize` | No | 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. _Enum:_ `low`, `medium`, `high` |
| `search_content_types` | `OpenAI.SearchContentType[]` | No | _Enum:_ `text`, `image` |

- **`user_location`** — `OpenAI.ApproximateLocation | null`

**One of the following:**

- **`OpenAI.ApproximateLocation`** — `OpenAI.ApproximateLocation`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`apply_patch`** — `apply_patch (OpenAI.ApplyPatchToolParam)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `apply_patch`. _Default:_ `"apply_patch"` _Constant:_ `apply_patch` |

- **`computer`** — `computer (OpenAI.ComputerTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool. Always `computer`. _Default:_ `"computer"` _Constant:_ `computer` |

- **`namespace`** — `namespace (OpenAI.NamespaceToolParam)`

Groups function/custom tools under a shared namespace.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `namespace`. _Default:_ `"namespace"` _Constant:_ `namespace` |
| `name` | `string` | Yes | The namespace name used in tool calls (for example, `crm`). |
| `description` | `string` | Yes | A description of the namespace shown to the model. |
| `tools` | `(OpenAI.FunctionToolParam \| OpenAI.CustomToolParam)[]` | Yes | The function/custom tools available inside this namespace. |

- **`tools`** — `(OpenAI.FunctionToolParam | OpenAI.CustomToolParam)[]`

The function/custom tools available inside this namespace.

**One of the following:**

- **`OpenAI.FunctionToolParam`** — `OpenAI.FunctionToolParam`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes |  |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |
| `strict` | `boolean \| null` | No |  |
| `type` | `enum` | Yes | _Default:_ `"function"` _Constant:_ `function` |
| `defer_loading` | `boolean` | No | Whether this function should be deferred and discovered via tool search. |

- **`OpenAI.CustomToolParam`** — `OpenAI.CustomToolParam`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`tool_search`** — `tool_search (OpenAI.ToolSearchToolParam)`

Hosted or BYOT tool search configuration for deferred tools.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `tool_search`. _Default:_ `"tool_search"` _Constant:_ `tool_search` |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search is executed by the server or by the client. _Enum:_ `server`, `client` |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |

##### `compaction` — `compaction (OpenAI.OutputItemCompactionBody)`

A compaction item generated by the [`v1/responses/compact` API](/docs/api-reference/responses/compact).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `compaction`. _Default:_ `"compaction"` _Constant:_ `compaction` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the compaction item. |
| `encrypted_content` | `string` | Yes | The encrypted content that was produced by compaction. |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `image_generation_call` — `image_generation_call (OpenAI.OutputItemImageGenToolCall)`

An image generation request made by the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation call. Always `image_generation_call`. _Constant:_ `image_generation_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the image generation call. |
| `status` | `enum` | Yes | The status of the image generation call. _Enum:_ `in_progress`, `completed`, `generating`, `failed` |
| `result` | `string \| null` | Yes |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `code_interpreter_call` — `code_interpreter_call (OpenAI.OutputItemCodeInterpreterToolCall)`

A tool call to run code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool call. Always `code_interpreter_call`. _Default:_ `"code_interpreter_call"` _Constant:_ `code_interpreter_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the code interpreter tool call. |
| `status` | `enum` | Yes | The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `interpreting`, `failed` |
| `container_id` | `string` | Yes | The ID of the container used to run the code. |
| `code` | `string \| null` | Yes |  |
| `outputs` | `(OpenAI.CodeInterpreterOutputLogs \| OpenAI.CodeInterpreterOutputImage)[] \| null` | Yes |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `outputs` — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[] | null`

**One of the following:**

- **`(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`** — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`

**One of the following:**

- **`OpenAI.CodeInterpreterOutputLogs`** — `OpenAI.CodeInterpreterOutputLogs`

The logs output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `logs`. _Default:_ `"logs"` _Constant:_ `logs` |
| `logs` | `string` | Yes | The logs output from the code interpreter. |

- **`OpenAI.CodeInterpreterOutputImage`** — `OpenAI.CodeInterpreterOutputImage`

The image output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `image`. _Default:_ `"image"` _Constant:_ `image` |
| `url` | `string` | Yes | The URL of the image output from the code interpreter. _Format:_ `uri` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `local_shell_call` — `local_shell_call (OpenAI.OutputItemLocalShellToolCall)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell call. Always `local_shell_call`. _Constant:_ `local_shell_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the local shell call. |
| `call_id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `action` | `OpenAI.LocalShellExecAction` | Yes | Execute a shell command on the server. |
| `status` | `enum` | Yes | The status of the local shell call. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `action` — `OpenAI.LocalShellExecAction`

Execute a shell command on the server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell action. Always `exec`. _Default:_ `"exec"` _Constant:_ `exec` |
| `command` | `string[]` | Yes | The command to run. |
| `timeout_ms` | `OpenAI.integer \| null` | No |  |
| `working_directory` | `string \| null` | No |  |
| `env` | `object` | Yes | Environment variables to set for the command. |
| `user` | `string \| null` | No |  |

##### `local_shell_call_output` — `local_shell_call_output (OpenAI.OutputItemLocalShellToolCallOutput)`

The output of a local shell tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool call output. Always `local_shell_call_output`. _Constant:_ `local_shell_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `output` | `string` | Yes | A JSON string of the output of the local shell tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `shell_call` — `shell_call (OpenAI.OutputItemFunctionShellCall)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `shell_call`. _Default:_ `"shell_call"` _Constant:_ `shell_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the shell tool call. Populated when this item is returned via API. |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `action` | `OpenAI.FunctionShellAction` | Yes | The shell commands and limits that describe how to run the tool call. |
| `status` | `OpenAI.FunctionShellCallStatus` | Yes | The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `environment` | `OpenAI.FunctionShellCallEnvironment \| null` | Yes |  |
| `created_by` | `string` | No | The ID of the entity that created this tool call. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `action` — `OpenAI.FunctionShellAction`

The shell commands and limits that describe how to run the tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `commands` | `string[]` | Yes |  |
| `timeout_ms` | `OpenAI.integer \| null` | Yes |  |
| `max_output_length` | `OpenAI.integer \| null` | Yes |  |

###### `environment` — `OpenAI.FunctionShellCallEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellCallEnvironment`** — `OpenAI.FunctionShellCallEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

##### `shell_call_output` — `shell_call_output (OpenAI.OutputItemFunctionShellCallOutput)`

The output of a shell tool call that was emitted.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell call output. Always `shell_call_output`. _Default:_ `"shell_call_output"` _Constant:_ `shell_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the shell call output. Populated when this item is returned via API. |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `status` | `OpenAI.FunctionShellCallOutputStatusEnum` | Yes | The status of the shell call output. One of `in_progress`, `completed`, or `incomplete`. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `output` | `OpenAI.FunctionShellCallOutputContent[]` | Yes | An array of shell call output contents |
| `max_output_length` | `OpenAI.integer \| null` | Yes |  |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `output` — `OpenAI.FunctionShellCallOutputContent[]`

An array of shell call output contents

**Array of** `OpenAI.FunctionShellCallOutputContent`**:**

The content of a shell tool call output that was emitted.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `stdout` | `string` | Yes | The standard output that was captured. |
| `stderr` | `string` | Yes | The standard error output that was captured. |
| `outcome` | `OpenAI.FunctionShellCallOutputTimeoutOutcome \| OpenAI.FunctionShellCallOutputExitOutcome` | Yes | Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk. |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

- **`outcome`** — `OpenAI.FunctionShellCallOutputTimeoutOutcome | OpenAI.FunctionShellCallOutputExitOutcome`

Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.

**One of the following:**

- **`timeout`** — `timeout (OpenAI.FunctionShellCallOutputTimeoutOutcome)`

Indicates that the shell call exceeded its configured time limit.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `timeout`. _Default:_ `"timeout"` _Constant:_ `timeout` |

- **`exit`** — `exit (OpenAI.FunctionShellCallOutputExitOutcome)`

Indicates that the shell commands finished and returned an exit code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `exit`. _Default:_ `"exit"` _Constant:_ `exit` |
| `exit_code` | `OpenAI.integer` | Yes | Exit code from the shell process. _Format:_ `int64` |

##### `apply_patch_call` — `apply_patch_call (OpenAI.OutputItemApplyPatchToolCall)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call`. _Default:_ `"apply_patch_call"` _Constant:_ `apply_patch_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the apply patch tool call. Populated when this item is returned via API. |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallStatus` | Yes | The status of the apply patch tool call. One of `in_progress` or `completed`. _Enum:_ `in_progress`, `completed` |
| `operation` | `OpenAI.ApplyPatchCreateFileOperation \| OpenAI.ApplyPatchDeleteFileOperation \| OpenAI.ApplyPatchUpdateFileOperation` | Yes | One of the create_file, delete_file, or update_file operations applied via apply_patch. |
| `created_by` | `string` | No | The ID of the entity that created this tool call. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `operation` — `OpenAI.ApplyPatchCreateFileOperation | OpenAI.ApplyPatchDeleteFileOperation | OpenAI.ApplyPatchUpdateFileOperation`

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

**One of the following:**

- **`create_file`** — `create_file (OpenAI.ApplyPatchCreateFileOperation)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Create a new file with the provided diff. _Default:_ `"create_file"` _Constant:_ `create_file` |
| `path` | `string` | Yes | Path of the file to create. |
| `diff` | `string` | Yes | Diff to apply. |

- **`delete_file`** — `delete_file (OpenAI.ApplyPatchDeleteFileOperation)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Delete the specified file. _Default:_ `"delete_file"` _Constant:_ `delete_file` |
| `path` | `string` | Yes | Path of the file to delete. |

- **`update_file`** — `update_file (OpenAI.ApplyPatchUpdateFileOperation)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Update an existing file with the provided diff. _Default:_ `"update_file"` _Constant:_ `update_file` |
| `path` | `string` | Yes | Path of the file to update. |
| `diff` | `string` | Yes | Diff to apply. |

##### `apply_patch_call_output` — `apply_patch_call_output (OpenAI.OutputItemApplyPatchToolCallOutput)`

The output emitted by an apply patch tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call_output`. _Default:_ `"apply_patch_call_output"` _Constant:_ `apply_patch_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the apply patch tool call output. Populated when this item is returned via API. |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallOutputStatus` | Yes | The status of the apply patch tool call output. One of `completed` or `failed`. _Enum:_ `completed`, `failed` |
| `output` | `string \| null` | No |  |
| `created_by` | `string` | No | The ID of the entity that created this tool call output. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `mcp_call` — `mcp_call (OpenAI.OutputItemMcpToolCall)`

An invocation of a tool on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_call`. _Constant:_ `mcp_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the tool call. |
| `server_label` | `string` | Yes | The label of the MCP server running the tool. |
| `name` | `string` | Yes | The name of the tool that was run. |
| `arguments` | `string` | Yes | A JSON string of the arguments passed to the tool. |
| `output` | `string \| null` | No |  |
| `error` | `object` | No |  |
| `status` | `OpenAI.MCPToolCallStatus` | No | The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `calling`, `failed` |
| `approval_request_id` | `string \| null` | No |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `mcp_list_tools` — `mcp_list_tools (OpenAI.OutputItemMcpListTools)`

A list of tools available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_list_tools`. _Constant:_ `mcp_list_tools` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the list. |
| `server_label` | `string` | Yes | The label of the MCP server. |
| `tools` | `OpenAI.MCPListToolsTool[]` | Yes | The tools available on the server. |
| `error` | `OpenAI.RealtimeMCPProtocolError \| OpenAI.RealtimeMCPToolExecutionError \| OpenAI.RealtimeMCPHTTPError` | No |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `tools` — `OpenAI.MCPListToolsTool[]`

The tools available on the server.

**Array of** `OpenAI.MCPListToolsTool`**:**

A tool available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the tool. |
| `description` | `string \| null` | No |  |
| `input_schema` | `OpenAI.MCPListToolsToolInputSchema` | Yes | The JSON schema describing the tool's input. |
| `annotations` | `OpenAI.MCPListToolsToolAnnotations \| null` | No |  |

###### `error` — `OpenAI.RealtimeMCPProtocolError | OpenAI.RealtimeMCPToolExecutionError | OpenAI.RealtimeMCPHTTPError`

**One of the following:**

- **`protocol_error`** — `protocol_error (OpenAI.RealtimeMCPProtocolError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `protocol_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

- **`tool_execution_error`** — `tool_execution_error (OpenAI.RealtimeMCPToolExecutionError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `tool_execution_error` |
| `message` | `string` | Yes |  |

- **`http_error`** — `http_error (OpenAI.RealtimeMCPHTTPError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `http_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

##### `mcp_approval_request` — `mcp_approval_request (OpenAI.OutputItemMcpApprovalRequest)`

A request for human approval of a tool invocation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_request`. _Constant:_ `mcp_approval_request` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the approval request. |
| `server_label` | `string` | Yes | The label of the MCP server making the request. |
| `name` | `string` | Yes | The name of the tool to run. |
| `arguments` | `string` | Yes | A JSON string of arguments for the tool. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `mcp_approval_response` — `mcp_approval_response (OpenAI.OutputItemMcpApprovalResponseResource)`

A response to an MCP approval request.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_response`. _Constant:_ `mcp_approval_response` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | Yes | The unique ID of the approval response |
| `approval_request_id` | `string` | Yes | The ID of the approval request being answered. |
| `approve` | `boolean` | Yes | Whether the request was approved. |
| `reason` | `string \| null` | No |  |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `custom_tool_call` — `custom_tool_call (OpenAI.OutputItemCustomToolCallResource)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call. Always `custom_tool_call`. _Constant:_ `custom_tool_call` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | No | The unique ID of the custom tool call in the OpenAI platform. |
| `call_id` | `string` | Yes | An identifier used to map this custom tool call to a tool call output. |
| `namespace` | `string` | No | The namespace of the custom tool being called. |
| `name` | `string` | Yes | The name of the custom tool being called. |
| `input` | `string` | Yes | The input for the custom tool call generated by the model. |
| `status` | `OpenAI.FunctionCallStatus` | Yes | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `custom_tool_call_output` — `custom_tool_call_output (OpenAI.OutputItemCustomToolCallOutputResource)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call output. Always `custom_tool_call_output`. _Constant:_ `custom_tool_call_output` |
| `agent_reference` | `AgentReference` | No | The agent that created the item. |
| `response_id` | `string` | No | The response on which the item is created. |
| `id` | `string` | No | The unique ID of the custom tool call output in the OpenAI platform. |
| `call_id` | `string` | Yes | The call ID, used to map this custom tool call output to a custom tool call. |
| `output` | `string \| (OpenAI.FunctionAndCustomToolCallOutputInputTextContent \| OpenAI.FunctionAndCustomToolCallOutputInputImageContent \| OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]` | Yes | The output from the custom tool call generated by your code. Can be a string or an list of output content. |
| `status` | `OpenAI.FunctionCallOutputStatusEnum` | Yes | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |
| `created_by` | `string` | No | The identifier of the actor that created the item. |

###### `agent_reference` — `AgentReference`

The agent that created the item.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

###### `output` — `string | (OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

The output from the custom tool call generated by your code. Can be a string or an list of output content.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`** — `(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

**One of the following:**

- **`input_text`** — `input_text (OpenAI.FunctionAndCustomToolCallOutputInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.FunctionAndCustomToolCallOutputInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.FunctionAndCustomToolCallOutputInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

#### `instructions` — `string | (OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[] | null`

**One of the following:**

##### `string` — `string`

| Type | Description |
|------|-------------|
| `string` | — |

##### `(OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[]` — `(OpenAI.EasyInputMessage | OpenAI.ItemReferenceParam | OpenAI.InputItemOutputMessage | OpenAI.InputItemFileSearchToolCall | OpenAI.InputItemComputerToolCall | OpenAI.InputItemComputerCallOutputItemParam | OpenAI.InputItemWebSearchToolCall | OpenAI.InputItemFunctionToolCall | OpenAI.InputItemFunctionCallOutputItemParam | OpenAI.InputItemToolSearchCallItemParam | OpenAI.InputItemToolSearchOutputItemParam | OpenAI.InputItemReasoningItem | OpenAI.InputItemCompactionSummaryItemParam | OpenAI.InputItemImageGenToolCall | OpenAI.InputItemCodeInterpreterToolCall | OpenAI.InputItemLocalShellToolCall | OpenAI.InputItemLocalShellToolCallOutput | OpenAI.InputItemFunctionShellCallItemParam | OpenAI.InputItemFunctionShellCallOutputItemParam | OpenAI.InputItemApplyPatchToolCallItemParam | OpenAI.InputItemApplyPatchToolCallOutputItemParam | OpenAI.InputItemMcpListTools | OpenAI.InputItemMcpApprovalRequest | OpenAI.InputItemMcpApprovalResponse | OpenAI.InputItemMcpToolCall | OpenAI.InputItemCustomToolCallOutput | OpenAI.InputItemCustomToolCall)[]`

**One of the following:**

###### `message` — `message (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.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the message input. Always `message`. _Constant:_ `message` |
| `role` | `enum` | Yes | The role of the message input. One of `user`, `assistant`, `system`, or `developer`. _Enum:_ `user`, `assistant`, `system`, `developer` |
| `content` | `string \| (OpenAI.InputContentInputTextContent \| OpenAI.InputContentInputImageContent \| OpenAI.InputContentInputFileContent)[]` | Yes | Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. |
| `phase` | `enum` | No | _Enum:_ `commentary`, `final_answer` |
| `status` | `enum` | No | The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`content`** — `string | (OpenAI.InputContentInputTextContent | OpenAI.InputContentInputImageContent | OpenAI.InputContentInputFileContent)[]`

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

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.InputMessageContentList`** — `OpenAI.InputMessageContentList ((OpenAI.InputContentInputTextContent | OpenAI.InputContentInputImageContent | OpenAI.InputContentInputFileContent)[])`

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

**One of the following:**

- **`input_text`** — `input_text (OpenAI.InputContentInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.InputContentInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.InputContentInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

###### `item_reference` — `item_reference (OpenAI.ItemReferenceParam)`

An internal identifier for an item to reference.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of item to reference. Always `item_reference`. _Default:_ `"item_reference"` _Constant:_ `item_reference` |
| `id` | `string` | Yes | The ID of the item to reference. |

###### `output_message` — `output_message (OpenAI.InputItemOutputMessage)`

An output message from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output message. Always `message`. _Constant:_ `output_message` |
| `id` | `string` | Yes | The unique ID of the output message. |
| `role` | `enum` | Yes | The role of the output message. Always `assistant`. _Constant:_ `assistant` |
| `content` | `(OpenAI.OutputMessageContentOutputTextContent \| OpenAI.OutputMessageContentRefusalContent)[]` | Yes | The content of the output message. |
| `phase` | `enum` | No | _Enum:_ `commentary`, `final_answer` |
| `status` | `enum` | Yes | The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`content`** — `(OpenAI.OutputMessageContentOutputTextContent | OpenAI.OutputMessageContentRefusalContent)[]`

The content of the output message.

**One of the following:**

- **`output_text`** — `output_text (OpenAI.OutputMessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`refusal`** — `refusal (OpenAI.OutputMessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

###### `file_search_call` — `file_search_call (OpenAI.InputItemFileSearchToolCall)`

The results of a file search tool call. See the [file search guide](/docs/guides/tools-file-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool call. Always `file_search_call`. _Constant:_ `file_search_call` |
| `id` | `string` | Yes | The unique ID of the file search tool call. |
| `status` | `enum` | Yes | The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, _Enum:_ `in_progress`, `searching`, `completed`, `incomplete`, `failed` |
| `queries` | `string[]` | Yes | The queries used to search for files. |
| `results` | `OpenAI.FileSearchToolCallResults[] \| null` | No |  |

- **`results`** — `OpenAI.FileSearchToolCallResults[] | null`

**One of the following:**

- **`OpenAI.FileSearchToolCallResults[]`** — `OpenAI.FileSearchToolCallResults[]`

**Array of** `OpenAI.FileSearchToolCallResults`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `file_id` | `string` | No |  |
| `text` | `string` | No |  |
| `filename` | `string` | No |  |
| `attributes` | `OpenAI.VectorStoreFileAttributes \| null` | No |  |
| `score` | `number` | No | _Format:_ `float` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `computer_call` — `computer_call (OpenAI.InputItemComputerToolCall)`

A tool call to a computer use tool. See the [computer use guide](/docs/guides/tools-computer-use) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer call. Always `computer_call`. _Default:_ `"computer_call"` _Constant:_ `computer_call` |
| `id` | `string` | Yes | The unique ID of the computer call. |
| `call_id` | `string` | Yes | An identifier used when responding to the tool call with output. |
| `action` | `OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam` | No |  |
| `actions` | `(OpenAI.ClickParam \| OpenAI.DoubleClickAction \| OpenAI.DragParam \| OpenAI.KeyPressAction \| OpenAI.MoveParam \| OpenAI.ScreenshotParam \| OpenAI.ScrollParam \| OpenAI.TypeParam \| OpenAI.WaitParam)[]` | No | Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. |
| `pending_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[]` | Yes | The pending safety checks for the computer call. |
| `status` | `enum` | Yes | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`action`** — `OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam`

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

- **`actions`** — `(OpenAI.ClickParam | OpenAI.DoubleClickAction | OpenAI.DragParam | OpenAI.KeyPressAction | OpenAI.MoveParam | OpenAI.ScreenshotParam | OpenAI.ScrollParam | OpenAI.TypeParam | OpenAI.WaitParam)[]`

Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields.

**One of the following:**

- **`click`** — `click (OpenAI.ClickParam)`

A click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a click action, this property is always `click`. _Default:_ `"click"` _Constant:_ `click` |
| `button` | `OpenAI.ClickButtonType` | Yes | Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. _Enum:_ `left`, `right`, `wheel`, `back`, `forward` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`double_click`** — `double_click (OpenAI.DoubleClickAction)`

A double click action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a double click action, this property is always set to `double_click`. _Default:_ `"double_click"` _Constant:_ `double_click` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the double click occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the double click occurred. _Format:_ `int64` |
| `keys` | `string[] \| null` | Yes |  |

- **`drag`** — `drag (OpenAI.DragParam)`

A drag action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a drag action, this property is always set to `drag`. _Default:_ `"drag"` _Constant:_ `drag` |
| `path` | `OpenAI.CoordParam[]` | Yes | An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` |
| `keys` | `string[] \| null` | No |  |

- **`path`** — `OpenAI.CoordParam[]`

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ```

**Array of** `OpenAI.CoordParam`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `x` | `OpenAI.integer` | Yes | The x-coordinate. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate. _Format:_ `int64` |

- **`keypress`** — `keypress (OpenAI.KeyPressAction)`

A collection of keypresses the model would like to perform.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a keypress action, this property is always set to `keypress`. _Default:_ `"keypress"` _Constant:_ `keypress` |
| `keys` | `string[]` | Yes | The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. |

- **`move`** — `move (OpenAI.MoveParam)`

A mouse move action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a move action, this property is always set to `move`. _Default:_ `"move"` _Constant:_ `move` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate to move to. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate to move to. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`screenshot`** — `screenshot (OpenAI.ScreenshotParam)`

A screenshot action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a screenshot action, this property is always set to `screenshot`. _Default:_ `"screenshot"` _Constant:_ `screenshot` |

- **`scroll`** — `scroll (OpenAI.ScrollParam)`

A scroll action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a scroll action, this property is always set to `scroll`. _Default:_ `"scroll"` _Constant:_ `scroll` |
| `x` | `OpenAI.integer` | Yes | The x-coordinate where the scroll occurred. _Format:_ `int64` |
| `y` | `OpenAI.integer` | Yes | The y-coordinate where the scroll occurred. _Format:_ `int64` |
| `scroll_x` | `OpenAI.integer` | Yes | The horizontal scroll distance. _Format:_ `int64` |
| `scroll_y` | `OpenAI.integer` | Yes | The vertical scroll distance. _Format:_ `int64` |
| `keys` | `string[] \| null` | No |  |

- **`type`** — `type (OpenAI.TypeParam)`

An action to type in text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a type action, this property is always set to `type`. _Default:_ `"type"` _Constant:_ `type` |
| `text` | `string` | Yes | The text to type. |

- **`wait`** — `wait (OpenAI.WaitParam)`

A wait action.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a wait action, this property is always set to `wait`. _Default:_ `"wait"` _Constant:_ `wait` |

- **`pending_safety_checks`** — `OpenAI.ComputerCallSafetyCheckParam[]`

The pending safety checks for the computer call.

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

###### `computer_call_output` — `computer_call_output (OpenAI.InputItemComputerCallOutputItemParam)`

The output of a computer tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool call output. Always `computer_call_output`. _Default:_ `"computer_call_output"` _Constant:_ `computer_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The ID of the computer tool call that produced the output. |
| `output` | `OpenAI.ComputerScreenshotImage` | Yes | A computer screenshot image used with the computer use tool. |
| `acknowledged_safety_checks` | `OpenAI.ComputerCallSafetyCheckParam[] \| null` | No |  |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`output`** — `OpenAI.ComputerScreenshotImage`

A computer screenshot image used with the computer use tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string` | No | The URL of the screenshot image. _Format:_ `uri` |
| `file_id` | `string` | No | The identifier of an uploaded file that contains the screenshot. |

- **`acknowledged_safety_checks`** — `OpenAI.ComputerCallSafetyCheckParam[] | null`

**One of the following:**

- **`OpenAI.ComputerCallSafetyCheckParam[]`** — `OpenAI.ComputerCallSafetyCheckParam[]`

**Array of** `OpenAI.ComputerCallSafetyCheckParam`**:**

A pending safety check for the computer call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the pending safety check. |
| `code` | `string \| null` | No |  |
| `message` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `web_search_call` — `web_search_call (OpenAI.InputItemWebSearchToolCall)`

The results of a web search tool call. See the [web search guide](/docs/guides/tools-web-search) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool call. Always `web_search_call`. _Constant:_ `web_search_call` |
| `id` | `string` | Yes | The unique ID of the web search tool call. |
| `status` | `enum` | Yes | The status of the web search tool call. _Enum:_ `in_progress`, `searching`, `completed`, `failed` |
| `action` | `OpenAI.WebSearchActionSearch \| OpenAI.WebSearchActionOpenPage \| OpenAI.WebSearchActionFind` | Yes | 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_in_page). |

- **`action`** — `OpenAI.WebSearchActionSearch | OpenAI.WebSearchActionOpenPage | 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_in_page).

**One of the following:**

- **`OpenAI.WebSearchActionSearch`** — `OpenAI.WebSearchActionSearch`

Action type "search" - Performs a web search query.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `search` |
| `query` | `string` | Yes | [DEPRECATED] The search query. |
| `queries` | `string[]` | No | The search queries. |
| `sources` | `OpenAI.WebSearchActionSearchSources[]` | No | The sources used in the search. |

- **`sources`** — `OpenAI.WebSearchActionSearchSources[]`

The sources used in the search.

**Array of** `OpenAI.WebSearchActionSearchSources`**:**

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `url` |
| `url` | `string` | Yes | _Format:_ `uri` |

- **`OpenAI.WebSearchActionOpenPage`** — `OpenAI.WebSearchActionOpenPage`

Action type "open_page" - Opens a specific URL from search results.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `open_page` |
| `url` | `string \| null` | No | The URL opened by the model. |

- **`OpenAI.WebSearchActionFind`** — `OpenAI.WebSearchActionFind`

Action type "find_in_page": Searches for a pattern within a loaded page.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The action type. _Constant:_ `find_in_page` |
| `url` | `string` | Yes | The URL of the page searched for the pattern. _Format:_ `uri` |
| `pattern` | `string` | Yes | The pattern or text to search for within the page. |

###### `function_call` — `function_call (OpenAI.InputItemFunctionToolCall)`

A tool call to run a function. See the [function calling guide](/docs/guides/function-calling) for more information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call. Always `function_call`. _Constant:_ `function_call` |
| `id` | `string` | Yes | The unique ID of the function tool call. |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `namespace` | `string` | No | The namespace of the function to run. |
| `name` | `string` | Yes | The name of the function to run. |
| `arguments` | `string` | Yes | A JSON string of the arguments to pass to the function. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `function_call_output` — `function_call_output (OpenAI.InputItemFunctionCallOutputItemParam)`

The output of a function tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool call output. Always `function_call_output`. _Default:_ `"function_call_output"` _Constant:_ `function_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the function tool call generated by the model. |
| `output` | `string \| (OpenAI.InputTextContentParam \| OpenAI.InputImageContentParamAutoParam \| OpenAI.InputFileContentParam)[]` | Yes | Text, image, or file output of the function tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`output`** — `string | (OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`

Text, image, or file output of the function tool call.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`** — `(OpenAI.InputTextContentParam | OpenAI.InputImageContentParamAutoParam | OpenAI.InputFileContentParam)[]`

**One of the following:**

- **`OpenAI.InputTextContentParam`** — `OpenAI.InputTextContentParam`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`OpenAI.InputImageContentParamAutoParam`** — `OpenAI.InputImageContentParamAutoParam`

An image input to the model. Learn about [image inputs](/docs/guides/vision)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `enum` | No | _Enum:_ `low`, `high`, `auto`, `original` |

- **`OpenAI.InputFileContentParam`** — `OpenAI.InputFileContentParam`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string \| null` | No |  |
| `file_data` | `string \| null` | No |  |
| `file_url` | `string \| null` | No |  |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

###### `tool_search_call` — `tool_search_call (OpenAI.InputItemToolSearchCallItemParam)`

An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The item type. Always `tool_search_call`. _Default:_ `"tool_search_call"` _Constant:_ `tool_search_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string \| null` | No |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `arguments` | `OpenAI.EmptyModelParam` | Yes | The arguments supplied to the tool search call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `tool_search_output` — `tool_search_output (OpenAI.InputItemToolSearchOutputItemParam)`

An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The item type. Always `tool_search_output`. _Default:_ `"tool_search_output"` _Constant:_ `tool_search_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string \| null` | No |  |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search was executed by the server or by the client. _Enum:_ `server`, `client` |
| `tools` | `(BingGroundingTool \| MicrosoftFabricPreviewTool \| SharepointPreviewTool \| AzureAISearchTool \| OpenApiTool \| BingCustomSearchPreviewTool \| BrowserAutomationPreviewTool \| AzureFunctionTool \| CaptureStructuredOutputsTool \| A2APreviewTool \| WorkIQPreviewTool \| FabricIQPreviewTool \| MemorySearchPreviewTool \| ToolboxSearchPreviewTool \| OpenAI.CodeInterpreterTool \| OpenAI.FunctionTool \| OpenAI.FileSearchTool \| OpenAI.ComputerUsePreviewTool \| OpenAI.WebSearchTool \| OpenAI.MCPTool \| OpenAI.ImageGenTool \| OpenAI.LocalShellToolParam \| OpenAI.FunctionShellToolParam \| OpenAI.CustomToolParam \| OpenAI.WebSearchPreviewTool \| OpenAI.ApplyPatchToolParam \| OpenAI.ComputerTool \| OpenAI.NamespaceToolParam \| OpenAI.ToolSearchToolParam)[]` | Yes | The loaded tool definitions returned by the tool search output. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`tools`** — `(BingGroundingTool | MicrosoftFabricPreviewTool | SharepointPreviewTool | AzureAISearchTool | OpenApiTool | BingCustomSearchPreviewTool | BrowserAutomationPreviewTool | AzureFunctionTool | CaptureStructuredOutputsTool | A2APreviewTool | WorkIQPreviewTool | FabricIQPreviewTool | MemorySearchPreviewTool | ToolboxSearchPreviewTool | OpenAI.CodeInterpreterTool | OpenAI.FunctionTool | OpenAI.FileSearchTool | OpenAI.ComputerUsePreviewTool | OpenAI.WebSearchTool | OpenAI.MCPTool | OpenAI.ImageGenTool | OpenAI.LocalShellToolParam | OpenAI.FunctionShellToolParam | OpenAI.CustomToolParam | OpenAI.WebSearchPreviewTool | OpenAI.ApplyPatchToolParam | OpenAI.ComputerTool | OpenAI.NamespaceToolParam | OpenAI.ToolSearchToolParam)[]`

The loaded tool definitions returned by the tool search output.

**One of the following:**

- **`bing_grounding`** — `bing_grounding (BingGroundingTool)`

The input definition information for a bing grounding search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_grounding'. _Constant:_ `bing_grounding` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_grounding` | `BingGroundingSearchToolParameters` | Yes | The bing grounding search tool parameters. |

- **`bing_grounding`** — `BingGroundingSearchToolParameters`

The bing grounding search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingGroundingSearchConfiguration[]` | Yes | The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. |

- **`search_configurations`** — `BingGroundingSearchConfiguration[]`

The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool.

**Array of** `BingGroundingSearchConfiguration`**:**

Search configuration for Bing Grounding

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`fabric_dataagent_preview`** — `fabric_dataagent_preview (MicrosoftFabricPreviewTool)`

The input definition information for a Microsoft Fabric tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_dataagent_preview'. _Constant:_ `fabric_dataagent_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `fabric_dataagent_preview` | `FabricDataAgentToolParameters` | Yes | The fabric data agent tool parameters. |

- **`fabric_dataagent_preview`** — `FabricDataAgentToolParameters`

The fabric data agent tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`sharepoint_grounding_preview`** — `sharepoint_grounding_preview (SharepointPreviewTool)`

The input definition information for a sharepoint tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'sharepoint_grounding_preview'. _Constant:_ `sharepoint_grounding_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `sharepoint_grounding_preview` | `SharepointGroundingToolParameters` | Yes | The sharepoint grounding tool parameters. |

- **`sharepoint_grounding_preview`** — `SharepointGroundingToolParameters`

The sharepoint grounding tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connections` | `ToolProjectConnection[]` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`project_connections`** — `ToolProjectConnection[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `ToolProjectConnection`**:**

A project connection resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | A project connection in a ToolProjectConnectionList attached to this tool. |

- **`azure_ai_search`** — `azure_ai_search (AzureAISearchTool)`

The input definition information for an Azure AI search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'azure_ai_search'. _Constant:_ `azure_ai_search` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `azure_ai_search` | `AzureAISearchToolResource` | Yes | The azure ai search index resource. |

- **`azure_ai_search`** — `AzureAISearchToolResource`

The azure ai search index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `indexes` | `AISearchIndexResource[]` | Yes | The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. |

- **`indexes`** — `AISearchIndexResource[]`

The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent.

**Array of** `AISearchIndexResource`**:**

A AI Search Index resource.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | No | An index connection ID in an IndexResource attached to this agent. |
| `index_name` | `string` | No | The name of an index in an IndexResource attached to this agent. |
| `query_type` | `enum` | No | Type of query in an AIIndexResource attached to this agent. _Enum:_ `simple`, `semantic`, `vector`, `vector_simple_hybrid`, `vector_semantic_hybrid` |
| `top_k` | `integer` | No | Number of documents to retrieve from search and present to the model. _Format:_ `int32` |
| `filter` | `string` | No | filter string for search resource. [Learn more here](https://learn.microsoft.com/azure/search/search-filters). |
| `index_asset_id` | `string` | No | Index asset id for search resource. |

- **`openapi`** — `openapi (OpenApiTool)`

The input definition information for an OpenAPI tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'openapi'. _Constant:_ `openapi` |
| `openapi` | `OpenApiFunctionDefinition` | Yes | The openapi function definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`openapi`** — `OpenApiFunctionDefinition`

The openapi function definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the function to be called. |
| `description` | `string` | No | A description of what the function does, used by the model to choose when and how to call the function. |
| `spec` | `object` | Yes | The openapi function shape, described as a JSON Schema object. |
| `auth` | `OpenApiAnonymousAuthDetails \| OpenApiProjectConnectionAuthDetails \| OpenApiManagedAuthDetails` | Yes | Open API authentication details |
| `default_params` | `string[]` | No | List of OpenAPI spec parameters that will use user-provided defaults |
| `functions` | `object[]` | No | List of function definitions used by OpenApi tool |

- **`auth`** — `OpenApiAnonymousAuthDetails | OpenApiProjectConnectionAuthDetails | OpenApiManagedAuthDetails`

Open API authentication details

**One of the following:**

- **`anonymous`** — `anonymous (OpenApiAnonymousAuthDetails)`

Security details for OpenApi anonymous authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'anonymous'. _Constant:_ `anonymous` |

- **`project_connection`** — `project_connection (OpenApiProjectConnectionAuthDetails)`

Security details for OpenApi project connection authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'project_connection'. _Constant:_ `project_connection` |
| `security_scheme` | `OpenApiProjectConnectionSecurityScheme` | Yes | Project connection auth security details |

- **`security_scheme`** — `OpenApiProjectConnectionSecurityScheme`

Project connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for Project Connection auth type |

- **`managed_identity`** — `managed_identity (OpenApiManagedAuthDetails)`

Security details for OpenApi managed_identity authentication

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'managed_identity'. _Constant:_ `managed_identity` |
| `security_scheme` | `OpenApiManagedSecurityScheme` | Yes | Connection auth security details |

- **`security_scheme`** — `OpenApiManagedSecurityScheme`

Connection auth security details

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `audience` | `string` | Yes | Authentication scope for managed_identity auth type |

- **`functions`** — `object[]`

List of function definitions used by OpenApi tool

**Array of** `object`**:**

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

- **`bing_custom_search_preview`** — `bing_custom_search_preview (BingCustomSearchPreviewTool)`

The input definition information for a Bing custom search tool as used to configure an agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'bing_custom_search_preview'. _Constant:_ `bing_custom_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `bing_custom_search_preview` | `BingCustomSearchToolParameters` | Yes | The bing custom search tool parameters. |

- **`bing_custom_search_preview`** — `BingCustomSearchToolParameters`

The bing custom search tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `search_configurations` | `BingCustomSearchConfiguration[]` | Yes | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`search_configurations`** — `BingCustomSearchConfiguration[]`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

**Array of** `BingCustomSearchConfiguration`**:**

A bing custom search configuration.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |
| `market` | `string` | No | The market where the results come from. |
| `set_lang` | `string` | No | The language to use for user interface strings when calling Bing API. |
| `count` | `integer` | No | The number of search results to return in the bing api response _Format:_ `int64` |
| `freshness` | `string` | No | Filter search results by a specific time range. See [accepted values here](https://learn.microsoft.com/bing/search-apis/bing-web-search/reference/query-parameters). |

- **`browser_automation_preview`** — `browser_automation_preview (BrowserAutomationPreviewTool)`

The input definition information for a Browser Automation Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation_preview'. _Constant:_ `browser_automation_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `browser_automation_preview` | `BrowserAutomationToolParameters` | Yes | The Browser Automation Tool parameters. |

- **`browser_automation_preview`** — `BrowserAutomationToolParameters`

The Browser Automation Tool parameters.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `connection` | `BrowserAutomationToolConnectionParameters` | Yes | The project connection parameters associated with the Browser Automation Tool. |

- **`connection`** — `BrowserAutomationToolConnectionParameters`

The project connection parameters associated with the Browser Automation Tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | The ID of the project connection to your Azure Playwright resource. |

- **`azure_function`** — `azure_function (AzureFunctionTool)`

The input definition information for an Azure Function Tool, as used to configure an Agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'browser_automation'. _Constant:_ `azure_function` |
| `azure_function` | `AzureFunctionDefinition` | Yes | The Azure Function Tool definition. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`azure_function`** — `AzureFunctionDefinition`

The Azure Function Tool definition.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `function` | `object` | Yes | The definition of azure function and its parameters. |
| `input_binding` | `AzureFunctionBinding` | Yes | Input storage queue. The queue storage trigger runs a function as messages are added to it. |
| `output_binding` | `AzureFunctionBinding` | Yes | Output storage queue. The function writes output to this queue when the input items are processed. |

- **`function`** — `object`

The definition of azure function and its parameters.

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

- **`input_binding`** — `AzureFunctionBinding`

Input storage queue. The queue storage trigger runs a function as messages are added to it.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`output_binding`** — `AzureFunctionBinding`

Output storage queue. The function writes output to this queue when the input items are processed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of binding, which is always 'storage_queue'. _Constant:_ `storage_queue` |
| `storage_queue` | `AzureFunctionStorageQueue` | Yes | Storage queue. |

- **`storage_queue`** — `AzureFunctionStorageQueue`

Storage queue.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `queue_service_endpoint` | `string` | Yes | URI to the Azure Storage Queue service allowing you to manipulate a queue. |
| `queue_name` | `string` | Yes | The name of an Azure function storage queue. |

- **`capture_structured_outputs`** — `capture_structured_outputs (CaptureStructuredOutputsTool)`

A tool for capturing structured outputs

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `capture_structured_outputs`. _Constant:_ `capture_structured_outputs` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `outputs` | `StructuredOutputDefinition` | Yes | The structured outputs to capture from the model. |

- **`outputs`** — `StructuredOutputDefinition`

The structured outputs to capture from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the structured output. |
| `description` | `string` | Yes | A description of the output to emit. Used by the model to determine when to emit the output. |
| `schema` | `object` | Yes | The JSON schema for the structured output. |
| `strict` | `boolean \| null` | Yes | Whether to enforce strict validation. Default `true`. |

- **`a2a_preview`** — `a2a_preview (A2APreviewTool)`

An agent implementing the A2A protocol.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `"a2a_preview`. _Constant:_ `a2a_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `base_url` | `string` | No | Base URL of the agent. _Format:_ `uri` |
| `agent_card_path` | `string` | No | The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json` |
| `project_connection_id` | `string` | No | The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server. |

- **`work_iq_preview`** — `work_iq_preview (WorkIQPreviewTool)`

A WorkIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'work_iq_preview'. _Constant:_ `work_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the WorkIQ project connection. |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`fabric_iq_preview`** — `fabric_iq_preview (FabricIQPreviewTool)`

A FabricIQ server-side tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The object type, which is always 'fabric_iq_preview'. _Constant:_ `fabric_iq_preview` |
| `project_connection_id` | `string` | Yes | The ID of the FabricIQ project connection. |
| `server_label` | `string` | No | (Optional) The label of the FabricIQ MCP server to connect to. |
| `server_url` | `string` | No | (Optional) The URL of the FabricIQ MCP server. If not provided, the URL from the project connection will be used. _Format:_ `uri` |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| string \| null` | No | (Optional) Whether the agent requires approval before executing actions. Default is always. _Default:_ `"always"` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | string | null`

(Optional) Whether the agent requires approval before executing actions. Default is always.

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`memory_search_preview`** — `memory_search_preview (MemorySearchPreviewTool)`

A tool for integrating memories into the agent.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `memory_search_preview`. _Constant:_ `memory_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `memory_store_name` | `string` | Yes | The name of the memory store to use. |
| `scope` | `string` | Yes | The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user. |
| `search_options` | `MemorySearchOptions` | No | Options for searching the memory store. |
| `update_delay` | `integer` | No | Time to wait before updating memories after inactivity (seconds). Default 300. _Default:_ `300` _Format:_ `int32` |

- **`search_options`** — `MemorySearchOptions`

Options for searching the memory store.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `max_memories` | `integer` | No | Maximum number of memory items to return. _Format:_ `int32` |

- **`toolbox_search_preview`** — `toolbox_search_preview (ToolboxSearchPreviewTool)`

A tool for searching over the agent's toolbox. When present, deferred tools are hidden from `tools/list` and only discoverable via `search_tools` queries at runtime.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `toolbox_search_preview`. _Constant:_ `toolbox_search_preview` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`code_interpreter`** — `code_interpreter (OpenAI.CodeInterpreterTool)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool. Always `code_interpreter`. _Constant:_ `code_interpreter` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `container` | `string \| OpenAI.AutoCodeInterpreterToolParam` | No | 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. If not provided, the service assumes auto. |

- **`container`** — `string | OpenAI.AutoCodeInterpreterToolParam`

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. If not provided, the service assumes auto.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.AutoCodeInterpreterToolParam`** — `OpenAI.AutoCodeInterpreterToolParam`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Always `auto`. _Default:_ `"auto"` _Constant:_ `auto` |
| `file_ids` | `string[]` | No | An optional list of uploaded files to make available to your code. |
| `memory_limit` | `enum` | No | _Enum:_ `1g`, `4g`, `16g`, `64g` |
| `network_policy` | `OpenAI.ContainerNetworkPolicyDisabledParam \| OpenAI.ContainerNetworkPolicyAllowlistParam` | No | Network access policy for the container. |

- **`network_policy`** — `OpenAI.ContainerNetworkPolicyDisabledParam | OpenAI.ContainerNetworkPolicyAllowlistParam`

Network access policy for the container.

**One of the following:**

- **`disabled`** — `disabled (OpenAI.ContainerNetworkPolicyDisabledParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Disable outbound network access. Always `disabled`. _Default:_ `"disabled"` _Constant:_ `disabled` |

- **`allowlist`** — `allowlist (OpenAI.ContainerNetworkPolicyAllowlistParam)`

Network access policy for the container.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Allow outbound network access only to specified domains. Always `allowlist`. _Default:_ `"allowlist"` _Constant:_ `allowlist` |
| `allowed_domains` | `string[]` | Yes | A list of allowed domains when type is `allowlist`. |

- **`function`** — `function (OpenAI.FunctionTool)`

Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the function tool. Always `function`. _Default:_ `"function"` _Constant:_ `function` |
| `name` | `string` | Yes | The name of the function to call. |
| `description` | `string \| null` | No |  |
| `parameters` | `object \| null` | Yes |  |
| `strict` | `boolean \| null` | Yes |  |
| `defer_loading` | `boolean` | No | Whether this function is deferred and loaded via tool search. |

- **`file_search`** — `file_search (OpenAI.FileSearchTool)`

A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file search tool. Always `file_search`. _Default:_ `"file_search"` _Constant:_ `file_search` |
| `vector_store_ids` | `string[]` | Yes | The IDs of the vector stores to search. |
| `max_num_results` | `OpenAI.integer` | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. _Format:_ `int64` |
| `ranking_options` | `OpenAI.RankingOptions` | No | Ranking options for search. |
| `filters` | `OpenAI.ComparisonFilter \| OpenAI.CompoundFilter \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`ranking_options`** — `OpenAI.RankingOptions`

Ranking options for search.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `ranker` | `OpenAI.RankerVersionType` | No | The ranker to use for the file search. _Enum:_ `auto`, `default-2024-11-15` |
| `score_threshold` | `OpenAI.numeric` | No | 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. _Format:_ `double` |
| `hybrid_search` | `OpenAI.HybridSearchOptions` | No | Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. |

- **`hybrid_search`** — `OpenAI.HybridSearchOptions`

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `embedding_weight` | `OpenAI.numeric` | Yes | The weight of the embedding in the reciprocal ranking fusion. _Format:_ `double` |
| `text_weight` | `OpenAI.numeric` | Yes | The weight of the text in the reciprocal ranking fusion. _Format:_ `double` |

- **`filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter | null`

**One of the following:**

- **`OpenAI.Filters`** — `OpenAI.ComparisonFilter | OpenAI.CompoundFilter`

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`OpenAI.CompoundFilter`** — `OpenAI.CompoundFilter`

Combine multiple filters using `and` or `or`.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Type of operation: `and` or `or`. _Enum:_ `and`, `or` |
| `filters` | `(OpenAI.ComparisonFilter \| any)[]` | Yes | Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. |

- **`filters`** — `(OpenAI.ComparisonFilter | any)[]`

Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

**One of the following:**

- **`OpenAI.ComparisonFilter`** — `OpenAI.ComparisonFilter`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | 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 _Default:_ `"eq"` _Enum:_ `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin` |
| `key` | `string` | Yes | The key to compare against the value. |
| `value` | `string \| OpenAI.numeric \| boolean \| (string \| OpenAI.numeric)[]` | Yes | The value to compare against the attribute key; supports string, number, or boolean types. |

- **`value`** — `string | OpenAI.numeric | boolean | (string | OpenAI.numeric)[]`

The value to compare against the attribute key; supports string, number, or boolean types.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`OpenAI.numeric`** — `OpenAI.numeric`

| Type | Description |
|------|-------------|
| `OpenAI.numeric` | _Format:_ `double` |

- **`boolean`** — `boolean`

| Type | Description |
|------|-------------|
| `boolean` | — |

- **`(string | OpenAI.numeric)[]`** — `(string | OpenAI.numeric)[]`

Type: `(string | OpenAI.numeric)[]`

- **`any`** — `any`

| Type | Description |
|------|-------------|
| `any` | — |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`computer_use_preview`** — `computer_use_preview (OpenAI.ComputerUsePreviewTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer use tool. Always `computer_use_preview`. _Default:_ `"computer_use_preview"` _Constant:_ `computer_use_preview` |
| `environment` | `OpenAI.ComputerEnvironment` | Yes | The type of computer environment to control. _Enum:_ `windows`, `mac`, `linux`, `ubuntu`, `browser` |
| `display_width` | `OpenAI.integer` | Yes | The width of the computer display. _Format:_ `int64` |
| `display_height` | `OpenAI.integer` | Yes | The height of the computer display. _Format:_ `int64` |

- **`web_search`** — `web_search (OpenAI.WebSearchTool)`

Search the Internet for sources related to the prompt. Learn more about the [web search tool](/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. _Default:_ `"web_search"` _Constant:_ `web_search` |
| `filters` | `OpenAI.WebSearchToolFilters \| null` | No |  |
| `user_location` | `OpenAI.WebSearchApproximateLocation \| null` | No |  |
| `search_context_size` | `enum` | No | 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. _Default:_ `"medium"` _Enum:_ `low`, `medium`, `high` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |
| `custom_search_configuration` | `WebSearchConfiguration` | No | The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. |

- **`filters`** — `OpenAI.WebSearchToolFilters | null`

**One of the following:**

- **`OpenAI.WebSearchToolFilters`** — `OpenAI.WebSearchToolFilters`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `allowed_domains` | `string[] \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`user_location`** — `OpenAI.WebSearchApproximateLocation | null`

**One of the following:**

- **`OpenAI.WebSearchApproximateLocation`** — `OpenAI.WebSearchApproximateLocation`

The approximate location of the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom_search_configuration`** — `WebSearchConfiguration`

The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `project_connection_id` | `string` | Yes | Project connection id for grounding with bing custom search |
| `instance_name` | `string` | Yes | Name of the custom configuration instance given to config. |

- **`mcp`** — `mcp (OpenAI.MCPTool)`

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the MCP tool. Always `mcp`. _Constant:_ `mcp` |
| `server_label` | `string` | Yes | A label for this MCP server, used to identify it in tool calls. |
| `server_url` | `string` | No | The URL for the MCP server. One of `server_url` or `connector_id` must be provided. _Format:_ `uri` |
| `connector_id` | `enum` | No | Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors [here](/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` _Enum:_ `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint` |
| `authorization` | `string` | No | An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. |
| `server_description` | `string` | No | Optional description of the MCP server, used to provide more context. |
| `headers` | `object \| null` | No |  |
| `allowed_tools` | `string[] \| OpenAI.MCPToolFilter \| null` | No |  |
| `require_approval` | `OpenAI.MCPToolRequireApproval \| enum \| null` | No | _Default:_ `"always"` _Enum:_ `always`, `never` |
| `defer_loading` | `boolean` | No | Whether this MCP tool is deferred and discovered via tool search. |
| `project_connection_id` | `string` | No | The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`allowed_tools`** — `string[] | OpenAI.MCPToolFilter | null`

**One of the following:**

- **`string[]`** — `string[]`

Type: `string[]`

- **`OpenAI.MCPToolFilter`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`require_approval`** — `OpenAI.MCPToolRequireApproval | enum | null`

**One of the following:**

- **`OpenAI.MCPToolRequireApproval`** — `OpenAI.MCPToolRequireApproval`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `always` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |
| `never` | `OpenAI.MCPToolFilter` | No | A filter object to specify which tools are allowed. |

- **`always`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`never`** — `OpenAI.MCPToolFilter`

A filter object to specify which tools are allowed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `tool_names` | `string[]` | No | List of allowed tool names. |
| `read_only` | `boolean` | No | Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. |

- **`enum`** — `enum`

| Type | Description |
|------|-------------|
| `enum` | _Enum:_ `always`, `never` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`image_generation`** — `image_generation (OpenAI.ImageGenTool)`

A tool that generates images using the GPT image models.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation tool. Always `image_generation`. _Default:_ `"image_generation"` _Constant:_ `image_generation` |
| `model` | `enum` | No | _Default:_ `"gpt-image-1"` _Enum:_ `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5` |
| `quality` | `enum` | No | The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `low`, `medium`, `high`, `auto` |
| `size` | `enum` | No | The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. _Default:_ `"auto"` _Enum:_ `1024x1024`, `1024x1536`, `1536x1024`, `auto` |
| `output_format` | `enum` | No | The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. _Default:_ `"png"` _Enum:_ `png`, `webp`, `jpeg` |
| `output_compression` | `OpenAI.integer` | No | Compression level for the output image. Default: 100. _Default:_ `100` _Format:_ `int64` |
| `moderation` | `enum` | No | Moderation level for the generated image. Default: `auto`. _Default:_ `"auto"` _Enum:_ `auto`, `low` |
| `background` | `enum` | No | Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. _Default:_ `"auto"` _Enum:_ `transparent`, `opaque`, `auto` |
| `input_fidelity` | `enum` | No | _Enum:_ `high`, `low` |
| `input_image_mask` | `OpenAI.ImageGenToolInputImageMask` | No | Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). |
| `partial_images` | `OpenAI.integer` | No | Number of partial images to generate in streaming mode, from 0 (default value) to 3. _Format:_ `int64` |
| `action` | `OpenAI.ImageGenActionEnum` | No | Whether to generate a new image or edit an existing image. Default: `auto`. _Enum:_ `generate`, `edit`, `auto` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`input_image_mask`** — `OpenAI.ImageGenToolInputImageMask`

Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `image_url` | `string` | No | _Format:_ `uri` |
| `file_id` | `string` | No |  |

- **`local_shell`** — `local_shell (OpenAI.LocalShellToolParam)`

A tool that allows the model to execute shell commands in a local environment.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool. Always `local_shell`. _Default:_ `"local_shell"` _Constant:_ `local_shell` |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`shell`** — `shell (OpenAI.FunctionShellToolParam)`

A tool that allows the model to execute shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the shell tool. Always `shell`. _Default:_ `"shell"` _Constant:_ `shell` |
| `environment` | `OpenAI.FunctionShellToolParamEnvironment \| null` | No |  |
| `name` | `string` | No | Optional user-defined name for this tool or configuration. |
| `description` | `string` | No | Optional user-defined description for this tool or configuration. |
| `tool_configs` | `object` | No | Per-tool configuration map. Keys are tool names or `*` (catch-all default). Resolution order: exact tool name match takes priority over `*`. Unknown tool names are silently ignored at runtime. |

- **`environment`** — `OpenAI.FunctionShellToolParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellToolParamEnvironment`** — `OpenAI.FunctionShellToolParamEnvironment`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `container_auto`, `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`custom`** — `custom (OpenAI.CustomToolParam)`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`web_search_preview`** — `web_search_preview (OpenAI.WebSearchPreviewTool)`

This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. _Default:_ `"web_search_preview"` _Constant:_ `web_search_preview` |
| `user_location` | `OpenAI.ApproximateLocation \| null` | No |  |
| `search_context_size` | `OpenAI.SearchContextSize` | No | 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. _Enum:_ `low`, `medium`, `high` |
| `search_content_types` | `OpenAI.SearchContentType[]` | No | _Enum:_ `text`, `image` |

- **`user_location`** — `OpenAI.ApproximateLocation | null`

**One of the following:**

- **`OpenAI.ApproximateLocation`** — `OpenAI.ApproximateLocation`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of location approximation. Always `approximate`. _Default:_ `"approximate"` _Constant:_ `approximate` |
| `country` | `string \| null` | No |  |
| `region` | `string \| null` | No |  |
| `city` | `string \| null` | No |  |
| `timezone` | `string \| null` | No |  |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

- **`apply_patch`** — `apply_patch (OpenAI.ApplyPatchToolParam)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `apply_patch`. _Default:_ `"apply_patch"` _Constant:_ `apply_patch` |

- **`computer`** — `computer (OpenAI.ComputerTool)`

A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the computer tool. Always `computer`. _Default:_ `"computer"` _Constant:_ `computer` |

- **`namespace`** — `namespace (OpenAI.NamespaceToolParam)`

Groups function/custom tools under a shared namespace.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `namespace`. _Default:_ `"namespace"` _Constant:_ `namespace` |
| `name` | `string` | Yes | The namespace name used in tool calls (for example, `crm`). |
| `description` | `string` | Yes | A description of the namespace shown to the model. |
| `tools` | `(OpenAI.FunctionToolParam \| OpenAI.CustomToolParam)[]` | Yes | The function/custom tools available inside this namespace. |

- **`tools`** — `(OpenAI.FunctionToolParam | OpenAI.CustomToolParam)[]`

The function/custom tools available inside this namespace.

**One of the following:**

- **`OpenAI.FunctionToolParam`** — `OpenAI.FunctionToolParam`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes |  |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |
| `strict` | `boolean \| null` | No |  |
| `type` | `enum` | Yes | _Default:_ `"function"` _Constant:_ `function` |
| `defer_loading` | `boolean` | No | Whether this function should be deferred and discovered via tool search. |

- **`OpenAI.CustomToolParam`** — `OpenAI.CustomToolParam`

A custom tool that processes input using a specified format. Learn more about [custom tools](/docs/guides/function-calling#custom-tools)

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool. Always `custom`. _Default:_ `"custom"` _Constant:_ `custom` |
| `name` | `string` | Yes | The name of the custom tool, used to identify it in tool calls. |
| `description` | `string` | No | Optional description of the custom tool, used to provide more context. |
| `format` | `OpenAI.CustomTextFormatParam \| OpenAI.CustomGrammarFormatParam` | No | The input format for the custom tool. Default is unconstrained text. |
| `defer_loading` | `boolean` | No | Whether this tool should be deferred and discovered via tool search. |

- **`format`** — `OpenAI.CustomTextFormatParam | OpenAI.CustomGrammarFormatParam`

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

**One of the following:**

- **`text`** — `text (OpenAI.CustomTextFormatParam)`

Unconstrained free-form text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Unconstrained text format. Always `text`. _Default:_ `"text"` _Constant:_ `text` |

- **`grammar`** — `grammar (OpenAI.CustomGrammarFormatParam)`

A grammar defined by the user.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Grammar format. Always `grammar`. _Default:_ `"grammar"` _Constant:_ `grammar` |
| `syntax` | `OpenAI.GrammarSyntax1` | Yes | The syntax of the grammar definition. One of `lark` or `regex`. _Enum:_ `lark`, `regex` |
| `definition` | `string` | Yes | The grammar definition. |

- **`tool_search`** — `tool_search (OpenAI.ToolSearchToolParam)`

Hosted or BYOT tool search configuration for deferred tools.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the tool. Always `tool_search`. _Default:_ `"tool_search"` _Constant:_ `tool_search` |
| `execution` | `OpenAI.ToolSearchExecutionType` | No | Whether tool search is executed by the server or by the client. _Enum:_ `server`, `client` |
| `description` | `string \| null` | No |  |
| `parameters` | `OpenAI.EmptyModelParam \| null` | No |  |

###### `reasoning` — `reasoning (OpenAI.InputItemReasoningItem)`

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](/docs/guides/conversation-state).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `reasoning`. _Constant:_ `reasoning` |
| `id` | `string` | Yes | The unique identifier of the reasoning content. |
| `encrypted_content` | `string \| null` | No |  |
| `summary` | `(OpenAI.TextContent \| OpenAI.ComputerScreenshotContent \| OpenAI.MessageContentInputTextContent \| OpenAI.MessageContentOutputTextContent \| OpenAI.MessageContentReasoningTextContent \| OpenAI.MessageContentRefusalContent \| OpenAI.MessageContentInputImageContent \| OpenAI.MessageContentInputFileContent \| OpenAI.SummaryTextContent)[]` | Yes | Reasoning summary content. |
| `content` | `OpenAI.ReasoningTextContent[]` | No | Reasoning text content. |
| `status` | `enum` | No | The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`summary`** — `(OpenAI.TextContent | OpenAI.ComputerScreenshotContent | OpenAI.MessageContentInputTextContent | OpenAI.MessageContentOutputTextContent | OpenAI.MessageContentReasoningTextContent | OpenAI.MessageContentRefusalContent | OpenAI.MessageContentInputImageContent | OpenAI.MessageContentInputFileContent | OpenAI.SummaryTextContent)[]`

Reasoning summary content.

**One of the following:**

- **`text`** — `text (OpenAI.TextContent)`

A text content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Default:_ `"text"` _Constant:_ `text` |
| `text` | `string` | Yes |  |

- **`computer_screenshot`** — `computer_screenshot (OpenAI.ComputerScreenshotContent)`

A screenshot of a computer.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. _Default:_ `"computer_screenshot"` _Constant:_ `computer_screenshot` |
| `image_url` | `string \| null` | Yes |  |
| `file_id` | `string \| null` | Yes |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the screenshot image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_text`** — `input_text (OpenAI.MessageContentInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`output_text`** — `output_text (OpenAI.MessageContentOutputTextContent)`

A text output from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output text. Always `output_text`. _Default:_ `"output_text"` _Constant:_ `output_text` |
| `text` | `string` | Yes | The text output from the model. |
| `annotations` | `(OpenAI.FileCitationBody \| OpenAI.UrlCitationBody \| OpenAI.ContainerFileCitationBody \| OpenAI.FilePath)[]` | Yes | The annotations of the text output. |
| `logprobs` | `OpenAI.LogProb[]` | Yes |  |

- **`annotations`** — `(OpenAI.FileCitationBody | OpenAI.UrlCitationBody | OpenAI.ContainerFileCitationBody | OpenAI.FilePath)[]`

The annotations of the text output.

**One of the following:**

- **`file_citation`** — `file_citation (OpenAI.FileCitationBody)`

A citation to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file citation. Always `file_citation`. _Default:_ `"file_citation"` _Constant:_ `file_citation` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the file cited. |

- **`url_citation`** — `url_citation (OpenAI.UrlCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the URL citation. Always `url_citation`. _Default:_ `"url_citation"` _Constant:_ `url_citation` |
| `url` | `string` | Yes | The URL of the web resource. _Format:_ `uri` |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the URL citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the URL citation in the message. _Format:_ `int64` |
| `title` | `string` | Yes | The title of the web resource. |

- **`container_file_citation`** — `container_file_citation (OpenAI.ContainerFileCitationBody)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the container file citation. Always `container_file_citation`. _Default:_ `"container_file_citation"` _Constant:_ `container_file_citation` |
| `container_id` | `string` | Yes | The ID of the container file. |
| `file_id` | `string` | Yes | The ID of the file. |
| `start_index` | `OpenAI.integer` | Yes | The index of the first character of the container file citation in the message. _Format:_ `int64` |
| `end_index` | `OpenAI.integer` | Yes | The index of the last character of the container file citation in the message. _Format:_ `int64` |
| `filename` | `string` | Yes | The filename of the container file cited. |

- **`file_path`** — `file_path (OpenAI.FilePath)`

A path to a file.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the file path. Always `file_path`. _Constant:_ `file_path` |
| `file_id` | `string` | Yes | The ID of the file. |
| `index` | `OpenAI.integer` | Yes | The index of the file in the list of files. _Format:_ `int64` |

- **`logprobs`** — `OpenAI.LogProb[]`

**Array of** `OpenAI.LogProb`**:**

The log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |
| `top_logprobs` | `OpenAI.TopLogProb[]` | Yes |  |

- **`top_logprobs`** — `OpenAI.TopLogProb[]`

**Array of** `OpenAI.TopLogProb`**:**

The top log probability of a token.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `token` | `string` | Yes |  |
| `logprob` | `OpenAI.numeric` | Yes | _Format:_ `double` |
| `bytes` | `OpenAI.integer[]` | Yes |  |

- **`reasoning_text`** — `reasoning_text (OpenAI.MessageContentReasoningTextContent)`

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

- **`refusal`** — `refusal (OpenAI.MessageContentRefusalContent)`

A refusal from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the refusal. Always `refusal`. _Default:_ `"refusal"` _Constant:_ `refusal` |
| `refusal` | `string` | Yes | The refusal explanation from the model. |

- **`input_image`** — `input_image (OpenAI.MessageContentInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.MessageContentInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

- **`summary_text`** — `summary_text (OpenAI.SummaryTextContent)`

A summary text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the object. Always `summary_text`. _Default:_ `"summary_text"` _Constant:_ `summary_text` |
| `text` | `string` | Yes | A summary of the reasoning output from the model so far. |

- **`content`** — `OpenAI.ReasoningTextContent[]`

Reasoning text content.

**Array of** `OpenAI.ReasoningTextContent`**:**

Reasoning text from the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the reasoning text. Always `reasoning_text`. _Default:_ `"reasoning_text"` _Constant:_ `reasoning_text` |
| `text` | `string` | Yes | The reasoning text from the model. |

###### `compaction` — `compaction (OpenAI.InputItemCompactionSummaryItemParam)`

A compaction item generated by the [`v1/responses/compact` API](/docs/api-reference/responses/compact).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `compaction`. _Default:_ `"compaction"` _Constant:_ `compaction` |
| `id` | `string \| null` | No |  |
| `encrypted_content` | `string` | Yes | The encrypted content of the compaction summary. |

###### `image_generation_call` — `image_generation_call (OpenAI.InputItemImageGenToolCall)`

An image generation request made by the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the image generation call. Always `image_generation_call`. _Constant:_ `image_generation_call` |
| `id` | `string` | Yes | The unique ID of the image generation call. |
| `status` | `enum` | Yes | The status of the image generation call. _Enum:_ `in_progress`, `completed`, `generating`, `failed` |
| `result` | `string \| null` | Yes |  |

###### `code_interpreter_call` — `code_interpreter_call (OpenAI.InputItemCodeInterpreterToolCall)`

A tool call to run code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the code interpreter tool call. Always `code_interpreter_call`. _Default:_ `"code_interpreter_call"` _Constant:_ `code_interpreter_call` |
| `id` | `string` | Yes | The unique ID of the code interpreter tool call. |
| `status` | `enum` | Yes | The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `interpreting`, `failed` |
| `container_id` | `string` | Yes | The ID of the container used to run the code. |
| `code` | `string \| null` | Yes |  |
| `outputs` | `(OpenAI.CodeInterpreterOutputLogs \| OpenAI.CodeInterpreterOutputImage)[] \| null` | Yes |  |

- **`outputs`** — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[] | null`

**One of the following:**

- **`(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`** — `(OpenAI.CodeInterpreterOutputLogs | OpenAI.CodeInterpreterOutputImage)[]`

**One of the following:**

- **`OpenAI.CodeInterpreterOutputLogs`** — `OpenAI.CodeInterpreterOutputLogs`

The logs output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `logs`. _Default:_ `"logs"` _Constant:_ `logs` |
| `logs` | `string` | Yes | The logs output from the code interpreter. |

- **`OpenAI.CodeInterpreterOutputImage`** — `OpenAI.CodeInterpreterOutputImage`

The image output from the code interpreter.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the output. Always `image`. _Default:_ `"image"` _Constant:_ `image` |
| `url` | `string` | Yes | The URL of the image output from the code interpreter. _Format:_ `uri` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `local_shell_call` — `local_shell_call (OpenAI.InputItemLocalShellToolCall)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell call. Always `local_shell_call`. _Constant:_ `local_shell_call` |
| `id` | `string` | Yes | The unique ID of the local shell call. |
| `call_id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `action` | `OpenAI.LocalShellExecAction` | Yes | Execute a shell command on the server. |
| `status` | `enum` | Yes | The status of the local shell call. _Enum:_ `in_progress`, `completed`, `incomplete` |

- **`action`** — `OpenAI.LocalShellExecAction`

Execute a shell command on the server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell action. Always `exec`. _Default:_ `"exec"` _Constant:_ `exec` |
| `command` | `string[]` | Yes | The command to run. |
| `timeout_ms` | `OpenAI.integer \| null` | No |  |
| `working_directory` | `string \| null` | No |  |
| `env` | `object` | Yes | Environment variables to set for the command. |
| `user` | `string \| null` | No |  |

###### `local_shell_call_output` — `local_shell_call_output (OpenAI.InputItemLocalShellToolCallOutput)`

The output of a local shell tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the local shell tool call output. Always `local_shell_call_output`. _Constant:_ `local_shell_call_output` |
| `id` | `string` | Yes | The unique ID of the local shell tool call generated by the model. |
| `output` | `string` | Yes | A JSON string of the output of the local shell tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |

###### `shell_call` — `shell_call (OpenAI.InputItemFunctionShellCallItemParam)`

A tool representing a request to execute one or more shell commands.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `shell_call`. _Default:_ `"shell_call"` _Constant:_ `shell_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `action` | `OpenAI.FunctionShellActionParam` | Yes | The shell commands and limits that describe how to run the tool call. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |
| `environment` | `OpenAI.FunctionShellCallItemParamEnvironment \| null` | No |  |

- **`action`** — `OpenAI.FunctionShellActionParam`

The shell commands and limits that describe how to run the tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `commands` | `string[]` | Yes | Ordered shell commands for the execution environment to run. |
| `timeout_ms` | `OpenAI.integer \| null` | No |  |
| `max_output_length` | `OpenAI.integer \| null` | No |  |

- **`environment`** — `OpenAI.FunctionShellCallItemParamEnvironment | null`

**One of the following:**

- **`OpenAI.FunctionShellCallItemParamEnvironment`** — `OpenAI.FunctionShellCallItemParamEnvironment`

The environment to execute the shell commands in.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Enum:_ `local`, `container_reference` |

- **`null`** — `null`

| Type | Description |
|------|-------------|
| `null` | — |

###### `shell_call_output` — `shell_call_output (OpenAI.InputItemFunctionShellCallOutputItemParam)`

The streamed output items emitted by a shell tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `shell_call_output`. _Default:_ `"shell_call_output"` _Constant:_ `shell_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the shell tool call generated by the model. |
| `output` | `OpenAI.FunctionShellCallOutputContentParam[]` | Yes | Captured chunks of stdout and stderr output, along with their associated outcomes. |
| `status` | `enum` | No | _Enum:_ `in_progress`, `completed`, `incomplete` |
| `max_output_length` | `OpenAI.integer \| null` | No |  |

- **`output`** — `OpenAI.FunctionShellCallOutputContentParam[]`

Captured chunks of stdout and stderr output, along with their associated outcomes.

**Array of** `OpenAI.FunctionShellCallOutputContentParam`**:**

Captured stdout and stderr for a portion of a shell tool call output.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `stdout` | `string` | Yes | Captured stdout output for the shell call. |
| `stderr` | `string` | Yes | Captured stderr output for the shell call. |
| `outcome` | `OpenAI.FunctionShellCallOutputTimeoutOutcomeParam \| OpenAI.FunctionShellCallOutputExitOutcomeParam` | Yes | The exit or timeout outcome associated with this shell call. |

- **`outcome`** — `OpenAI.FunctionShellCallOutputTimeoutOutcomeParam | OpenAI.FunctionShellCallOutputExitOutcomeParam`

The exit or timeout outcome associated with this shell call.

**One of the following:**

- **`timeout`** — `timeout (OpenAI.FunctionShellCallOutputTimeoutOutcomeParam)`

Indicates that the shell call exceeded its configured time limit.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `timeout`. _Default:_ `"timeout"` _Constant:_ `timeout` |

- **`exit`** — `exit (OpenAI.FunctionShellCallOutputExitOutcomeParam)`

Indicates that the shell commands finished and returned an exit code.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The outcome type. Always `exit`. _Default:_ `"exit"` _Constant:_ `exit` |
| `exit_code` | `OpenAI.integer` | Yes | The exit code returned by the shell process. _Format:_ `int64` |

###### `apply_patch_call` — `apply_patch_call (OpenAI.InputItemApplyPatchToolCallItemParam)`

A tool call representing a request to create, delete, or update files using diff patches.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call`. _Default:_ `"apply_patch_call"` _Constant:_ `apply_patch_call` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallStatusParam` | Yes | The status of the apply patch tool call. One of `in_progress` or `completed`. _Enum:_ `in_progress`, `completed` |
| `operation` | `OpenAI.ApplyPatchCreateFileOperationParam \| OpenAI.ApplyPatchDeleteFileOperationParam \| OpenAI.ApplyPatchUpdateFileOperationParam` | Yes | The specific create, delete, or update instruction for the apply_patch tool call. |

- **`operation`** — `OpenAI.ApplyPatchCreateFileOperationParam | OpenAI.ApplyPatchDeleteFileOperationParam | OpenAI.ApplyPatchUpdateFileOperationParam`

The specific create, delete, or update instruction for the apply_patch tool call.

**One of the following:**

- **`create_file`** — `create_file (OpenAI.ApplyPatchCreateFileOperationParam)`

Instruction for creating a new file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `create_file`. _Default:_ `"create_file"` _Constant:_ `create_file` |
| `path` | `string` | Yes | Path of the file to create relative to the workspace root. |
| `diff` | `string` | Yes | Unified diff content to apply when creating the file. |

- **`delete_file`** — `delete_file (OpenAI.ApplyPatchDeleteFileOperationParam)`

Instruction for deleting an existing file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `delete_file`. _Default:_ `"delete_file"` _Constant:_ `delete_file` |
| `path` | `string` | Yes | Path of the file to delete relative to the workspace root. |

- **`update_file`** — `update_file (OpenAI.ApplyPatchUpdateFileOperationParam)`

Instruction for updating an existing file via the apply_patch tool.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The operation type. Always `update_file`. _Default:_ `"update_file"` _Constant:_ `update_file` |
| `path` | `string` | Yes | Path of the file to update relative to the workspace root. |
| `diff` | `string` | Yes | Unified diff content to apply to the existing file. |

###### `apply_patch_call_output` — `apply_patch_call_output (OpenAI.InputItemApplyPatchToolCallOutputItemParam)`

The streamed output emitted by an apply patch tool call.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `apply_patch_call_output`. _Default:_ `"apply_patch_call_output"` _Constant:_ `apply_patch_call_output` |
| `id` | `string \| null` | No |  |
| `call_id` | `string` | Yes | The unique ID of the apply patch tool call generated by the model. |
| `status` | `OpenAI.ApplyPatchCallOutputStatusParam` | Yes | The status of the apply patch tool call output. One of `completed` or `failed`. _Enum:_ `completed`, `failed` |
| `output` | `string \| null` | No |  |

###### `mcp_list_tools` — `mcp_list_tools (OpenAI.InputItemMcpListTools)`

A list of tools available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_list_tools`. _Constant:_ `mcp_list_tools` |
| `id` | `string` | Yes | The unique ID of the list. |
| `server_label` | `string` | Yes | The label of the MCP server. |
| `tools` | `OpenAI.MCPListToolsTool[]` | Yes | The tools available on the server. |
| `error` | `OpenAI.RealtimeMCPProtocolError \| OpenAI.RealtimeMCPToolExecutionError \| OpenAI.RealtimeMCPHTTPError` | No |  |

- **`tools`** — `OpenAI.MCPListToolsTool[]`

The tools available on the server.

**Array of** `OpenAI.MCPListToolsTool`**:**

A tool available on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `name` | `string` | Yes | The name of the tool. |
| `description` | `string \| null` | No |  |
| `input_schema` | `OpenAI.MCPListToolsToolInputSchema` | Yes | The JSON schema describing the tool's input. |
| `annotations` | `OpenAI.MCPListToolsToolAnnotations \| null` | No |  |

- **`error`** — `OpenAI.RealtimeMCPProtocolError | OpenAI.RealtimeMCPToolExecutionError | OpenAI.RealtimeMCPHTTPError`

**One of the following:**

- **`protocol_error`** — `protocol_error (OpenAI.RealtimeMCPProtocolError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `protocol_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

- **`tool_execution_error`** — `tool_execution_error (OpenAI.RealtimeMCPToolExecutionError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `tool_execution_error` |
| `message` | `string` | Yes |  |

- **`http_error`** — `http_error (OpenAI.RealtimeMCPHTTPError)`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `http_error` |
| `code` | `OpenAI.integer` | Yes | _Format:_ `int64` |
| `message` | `string` | Yes |  |

###### `mcp_approval_request` — `mcp_approval_request (OpenAI.InputItemMcpApprovalRequest)`

A request for human approval of a tool invocation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_request`. _Constant:_ `mcp_approval_request` |
| `id` | `string` | Yes | The unique ID of the approval request. |
| `server_label` | `string` | Yes | The label of the MCP server making the request. |
| `name` | `string` | Yes | The name of the tool to run. |
| `arguments` | `string` | Yes | A JSON string of arguments for the tool. |

###### `mcp_approval_response` — `mcp_approval_response (OpenAI.InputItemMcpApprovalResponse)`

A response to an MCP approval request.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_approval_response`. _Constant:_ `mcp_approval_response` |
| `id` | `string \| null` | No |  |
| `approval_request_id` | `string` | Yes | The ID of the approval request being answered. |
| `approve` | `boolean` | Yes | Whether the request was approved. |
| `reason` | `string \| null` | No |  |

###### `mcp_call` — `mcp_call (OpenAI.InputItemMcpToolCall)`

An invocation of a tool on an MCP server.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the item. Always `mcp_call`. _Constant:_ `mcp_call` |
| `id` | `string` | Yes | The unique ID of the tool call. |
| `server_label` | `string` | Yes | The label of the MCP server running the tool. |
| `name` | `string` | Yes | The name of the tool that was run. |
| `arguments` | `string` | Yes | A JSON string of the arguments passed to the tool. |
| `output` | `string \| null` | No |  |
| `error` | `object` | No |  |
| `status` | `OpenAI.MCPToolCallStatus` | No | The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. _Enum:_ `in_progress`, `completed`, `incomplete`, `calling`, `failed` |
| `approval_request_id` | `string \| null` | No |  |

###### `custom_tool_call_output` — `custom_tool_call_output (OpenAI.InputItemCustomToolCallOutput)`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call output. Always `custom_tool_call_output`. _Constant:_ `custom_tool_call_output` |
| `id` | `string` | No | The unique ID of the custom tool call output in the OpenAI platform. |
| `call_id` | `string` | Yes | The call ID, used to map this custom tool call output to a custom tool call. |
| `output` | `string \| (OpenAI.FunctionAndCustomToolCallOutputInputTextContent \| OpenAI.FunctionAndCustomToolCallOutputInputImageContent \| OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]` | Yes | The output from the custom tool call generated by your code. Can be a string or an list of output content. |

- **`output`** — `string | (OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

The output from the custom tool call generated by your code. Can be a string or an list of output content.

**One of the following:**

- **`string`** — `string`

| Type | Description |
|------|-------------|
| `string` | — |

- **`(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`** — `(OpenAI.FunctionAndCustomToolCallOutputInputTextContent | OpenAI.FunctionAndCustomToolCallOutputInputImageContent | OpenAI.FunctionAndCustomToolCallOutputInputFileContent)[]`

**One of the following:**

- **`input_text`** — `input_text (OpenAI.FunctionAndCustomToolCallOutputInputTextContent)`

A text input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_text`. _Default:_ `"input_text"` _Constant:_ `input_text` |
| `text` | `string` | Yes | The text input to the model. |

- **`input_image`** — `input_image (OpenAI.FunctionAndCustomToolCallOutputInputImageContent)`

An image input to the model. Learn about [image inputs](/docs/guides/vision).

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_image`. _Default:_ `"input_image"` _Constant:_ `input_image` |
| `image_url` | `string \| null` | No |  |
| `file_id` | `string \| null` | No |  |
| `detail` | `OpenAI.ImageDetail` | Yes | The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. _Enum:_ `low`, `high`, `auto`, `original` |

- **`input_file`** — `input_file (OpenAI.FunctionAndCustomToolCallOutputInputFileContent)`

A file input to the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the input item. Always `input_file`. _Default:_ `"input_file"` _Constant:_ `input_file` |
| `file_id` | `string \| null` | No |  |
| `filename` | `string` | No | The name of the file to be sent to the model. |
| `file_data` | `string` | No | The content of the file to be sent to the model. |
| `file_url` | `string` | No | The URL of the file to be sent to the model. _Format:_ `uri` |
| `detail` | `OpenAI.FileInputDetail` | No | The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`. _Enum:_ `low`, `high` |

###### `custom_tool_call` — `custom_tool_call (OpenAI.InputItemCustomToolCall)`

A call to a custom tool created by the model.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | The type of the custom tool call. Always `custom_tool_call`. _Constant:_ `custom_tool_call` |
| `id` | `string` | No | The unique ID of the custom tool call in the OpenAI platform. |
| `call_id` | `string` | Yes | An identifier used to map this custom tool call to a tool call output. |
| `namespace` | `string` | No | The namespace of the custom tool being called. |
| `name` | `string` | Yes | The name of the custom tool being called. |
| `input` | `string` | Yes | The input for the custom tool call generated by the model. |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `usage` — `OpenAI.ResponseUsage`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `input_tokens` | `OpenAI.integer` | Yes | The number of input tokens. _Format:_ `int64` |
| `input_tokens_details` | `OpenAI.ResponseUsageInputTokensDetails` | Yes | A detailed breakdown of the input tokens. |
| `output_tokens` | `OpenAI.integer` | Yes | The number of output tokens. _Format:_ `int64` |
| `output_tokens_details` | `OpenAI.ResponseUsageOutputTokensDetails` | Yes | A detailed breakdown of the output tokens. |
| `total_tokens` | `OpenAI.integer` | Yes | The total number of tokens used. _Format:_ `int64` |

##### `input_tokens_details` — `OpenAI.ResponseUsageInputTokensDetails`

A detailed breakdown of the input tokens.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `cached_tokens` | `OpenAI.integer` | Yes | _Format:_ `int64` |

##### `output_tokens_details` — `OpenAI.ResponseUsageOutputTokensDetails`

A detailed breakdown of the output tokens.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `reasoning_tokens` | `OpenAI.integer` | Yes | _Format:_ `int64` |

#### `conversation` — `OpenAI.ConversationReference | null`

**One of the following:**

##### `OpenAI.ConversationReference` — `OpenAI.ConversationReference`

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The unique ID of the conversation that this response was associated with. |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `agent_reference` — `AgentReference | null`

The agent used for this response

**One of the following:**

##### `AgentReference` — `AgentReference`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `type` | `enum` | Yes | _Constant:_ `agent_reference` |
| `name` | `string` | Yes | The name of the agent. |
| `version` | `string` | No | The version identifier of the agent. |

##### `null` — `null`

| Type | Description |
|------|-------------|
| `null` | — |

#### `content_filters` — `ContentFilterResult[]`

The content filter evaluation results.

**Array of** `ContentFilterResult`**:**

A content filter evaluation result for a specific source in the response.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `blocked` | `boolean` | Yes | Whether the content was blocked by the content filter. |
| `source_type` | `string` | Yes | The source type of the content filter evaluation (e.g., 'prompt', 'response', 'pre_tool_call', 'post_tool_call'). |
| `content_filter_results` | `AzureContentFilterResultsForResponses` | Yes | The content filter results for this evaluation. |
| `tool_call_id` | `string` | No | The ID of the tool call associated with this content filter result, if applicable. |

##### `content_filter_results` — `AzureContentFilterResultsForResponses`

The content filter results for this evaluation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `sexual` | `AzureContentFilterSeverityResult` | No | Severity result for sexual content. |
| `hate` | `AzureContentFilterSeverityResult` | No | Severity result for hate content. |
| `violence` | `AzureContentFilterSeverityResult` | No | Severity result for violence content. |
| `self_harm` | `AzureContentFilterSeverityResult` | No | Severity result for self-harm content. |
| `profanity` | `AzureContentFilterDetectionResult` | No | Detection result for profanity. |
| `custom_blocklists` | `AzureContentFilterBlocklistResult` | No | Results for configured custom blocklists. |
| `jailbreak` | `AzureContentFilterDetectionResult` | No | Detection result for jailbreak attempts. |
| `task_adherence` | `AzureContentFilterDetectionWithReasonResult` | No | Detection result for task adherence evaluation. |
| `protected_material_text` | `AzureContentFilterDetectionResult` | No | Detection result for protected material text. |
| `protected_material_code` | `AzureContentFilterDetectionWithCitationResult` | No | Detection result for protected material code with citation. |
| `ungrounded_material` | `AzureContentFilterCompletionTextSpanDetectionResult` | No | Detection result for ungrounded material with completion text span details. |
| `personally_identifiable_information` | `AzureContentFilterPersonallyIdentifiableInformationResult` | No | Detection result for Personally Identifiable Information. |
| `indirect_attack` | `AzureContentFilterDetectionResult` | No | Detection result for indirect attacks. |
| `error` | `AzureContentFilterError` | No | Error details if content filtering evaluation failed. |

###### `sexual` — `AzureContentFilterSeverityResult`

Severity result for sexual content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `severity` | `enum` | Yes | The severity level of the content. _Enum:_ `safe`, `low`, `medium`, `high` |

###### `hate` — `AzureContentFilterSeverityResult`

Severity result for hate content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `severity` | `enum` | Yes | The severity level of the content. _Enum:_ `safe`, `low`, `medium`, `high` |

###### `violence` — `AzureContentFilterSeverityResult`

Severity result for violence content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `severity` | `enum` | Yes | The severity level of the content. _Enum:_ `safe`, `low`, `medium`, `high` |

###### `self_harm` — `AzureContentFilterSeverityResult`

Severity result for self-harm content.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `severity` | `enum` | Yes | The severity level of the content. _Enum:_ `safe`, `low`, `medium`, `high` |

###### `profanity` — `AzureContentFilterDetectionResult`

Detection result for profanity.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |

###### `custom_blocklists` — `AzureContentFilterBlocklistResult`

Results for configured custom blocklists.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether any blocklist resulted in filtering. |
| `details` | `AzureContentFilterBlocklistIdResult[]` | No | The pairs of individual blocklist IDs and their filtering results. |

- **`details`** — `AzureContentFilterBlocklistIdResult[]`

The pairs of individual blocklist IDs and their filtering results.

**Array of** `AzureContentFilterBlocklistIdResult`**:**

A content filter blocklist ID result.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `id` | `string` | Yes | The ID of the custom blocklist. |
| `filtered` | `boolean` | Yes | Whether the blocklist resulted in filtering. |

###### `jailbreak` — `AzureContentFilterDetectionResult`

Detection result for jailbreak attempts.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |

###### `task_adherence` — `AzureContentFilterDetectionWithReasonResult`

Detection result for task adherence evaluation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |
| `reason` | `string` | No | A human-readable explanation of why the detection result was produced. |

###### `protected_material_text` — `AzureContentFilterDetectionResult`

Detection result for protected material text.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |

###### `protected_material_code` — `AzureContentFilterDetectionWithCitationResult`

Detection result for protected material code with citation.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |
| `citation` | `AzureContentFilterCitation` | No | Citation details describing the associated license and its location. |

- **`citation`** — `AzureContentFilterCitation`

Citation details describing the associated license and its location.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `license` | `string` | No | The license associated with the detection. |
| `url` | `string` | No | The URL associated with the license. _Format:_ `uri` |

###### `ungrounded_material` — `AzureContentFilterCompletionTextSpanDetectionResult`

Detection result for ungrounded material with completion text span details.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |
| `details` | `AzureContentFilterCompletionTextSpan[]` | Yes | Detailed information about the detected completion text spans. |

- **`details`** — `AzureContentFilterCompletionTextSpan[]`

Detailed information about the detected completion text spans.

**Array of** `AzureContentFilterCompletionTextSpan`**:**

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

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `completion_start_offset` | `integer` | Yes | Offset of the UTF32 code point which begins the span. _Format:_ `int32` |
| `completion_end_offset` | `integer` | Yes | Offset of the first UTF32 code point which is excluded from the span. _Format:_ `int32` |

###### `personally_identifiable_information` — `AzureContentFilterPersonallyIdentifiableInformationResult`

Detection result for Personally Identifiable Information.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether PII was detected in the content. |
| `sub_categories` | `AzureContentFilterPiiSubCategoryResult[]` | No | Detailed results for individual PII subcategories. |

- **`sub_categories`** — `AzureContentFilterPiiSubCategoryResult[]`

Detailed results for individual PII subcategories.

**Array of** `AzureContentFilterPiiSubCategoryResult`**:**

Result details for an individual PII subcategory.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `sub_category` | `string` | Yes | The PII subcategory that was evaluated. |
| `filtered` | `boolean` | Yes | Whether the content was filtered for this subcategory. |
| `detected` | `boolean` | Yes | Whether the subcategory was detected in the content. |

###### `indirect_attack` — `AzureContentFilterDetectionResult`

Detection result for indirect attacks.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `filtered` | `boolean` | Yes | Whether the content was filtered. |
| `detected` | `boolean` | Yes | Whether the content category was detected. |

###### `error` — `AzureContentFilterError`

Error details if content filtering evaluation failed.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `code` | `integer` | Yes | A machine-readable error code. _Format:_ `int32` |
| `message` | `string` | Yes | A human-readable error message. |

### 4XX — Client error

Content-Type: `application/json`

Error response for API failures.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `error` | `OpenAI.Error` | Yes |  |

#### `error` — `OpenAI.Error`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `code` | `string \| null` | Yes |  |
| `message` | `string` | Yes |  |
| `param` | `string \| null` | No |  |
| `type` | `string` | No |  |
| `details` | `OpenAI.Error[]` | No |  |
| `additionalInfo` | `object` | No |  |
| `debugInfo` | `object` | No |  |

### 5XX — Server error

Content-Type: `application/json`

Error response for API failures.

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `error` | `OpenAI.Error` | Yes |  |

#### `error` — `OpenAI.Error`

| Property | Type | Required | Description |
|----------|------|----------|-------------|
| `code` | `string \| null` | Yes |  |
| `message` | `string` | Yes |  |
| `param` | `string \| null` | No |  |
| `type` | `string` | No |  |
| `details` | `OpenAI.Error[]` | No |  |
| `additionalInfo` | `object` | No |  |
| `debugInfo` | `object` | No |  |