> ## Documentation Index > Fetch the complete documentation index at: https://azure-foundry.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Post responses > Creates a model response. ## OpenAPI ````yaml api-reference/openai-v1.yaml post /responses openapi: 3.0.0 info: title: Azure AI Foundry Models Service license: name: MIT url: https://github.com/openai/openai-openapi/blob/master/LICENSE version: v1 servers: - url: '{endpoint}/openai/v1' description: Azure AI Foundry Models APIs variables: endpoint: default: '' description: >- A supported Azure AI Foundry Models APIs endpoint, including protocol and hostname. For example: https://westus.api.cognitive.microsoft.com). security: - ApiKeyAuth: [] - ApiKeyAuth_: [] - OAuth2Auth: - https://cognitiveservices.azure.com/.default tags: - name: Chat - name: Embeddings - name: Evals - name: Files - name: Fine-tuning - name: Models - name: Responses - name: Vector Stores paths: /responses: post: tags: - Responses description: Creates a model response. operationId: createResponse parameters: - name: api-version in: query required: false description: >- The explicit Azure AI Foundry Models API version to use for this request. `v1` if not otherwise specified. schema: $ref: '#/components/schemas/AzureAIFoundryModelsApiVersion' default: v1 requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AzureCreateResponse' responses: '200': description: The request has succeeded. headers: apim-request-id: required: false description: A request ID used for troubleshooting purposes. schema: type: string content: application/json: schema: $ref: '#/components/schemas/AzureResponse' text/event-stream: schema: $ref: '#/components/schemas/OpenAI.ResponseStreamEvent' default: description: An unexpected error response. headers: apim-request-id: required: false description: A request ID used for troubleshooting purposes. schema: type: string content: application/json: schema: $ref: '#/components/schemas/AzureErrorResponse' components: schemas: AzureAIFoundryModelsApiVersion: type: string enum: - v1 - preview AzureCreateResponse: type: object required: - model properties: metadata: type: object additionalProperties: type: string description: >- Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. x-oaiTypeLabel: map temperature: type: number format: float nullable: true minimum: 0 maximum: 2 description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. default: 1 top_p: type: number format: float nullable: true minimum: 0 maximum: 1 description: >- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. default: 1 user: type: string description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). top_logprobs: type: integer format: int32 minimum: 0 maximum: 20 description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. previous_response_id: type: string nullable: true description: |- The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). reasoning: type: object allOf: - $ref: '#/components/schemas/OpenAI.Reasoning' nullable: true background: type: boolean nullable: true description: |- Whether to run the model response in the background. [Learn more](/docs/guides/background). default: false max_output_tokens: type: integer format: int32 nullable: true description: >- An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). max_tool_calls: type: integer format: int32 nullable: true description: >- The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. text: type: object properties: format: $ref: '#/components/schemas/OpenAI.ResponseTextFormatConfiguration' description: >- 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: type: array items: $ref: '#/components/schemas/OpenAI.Tool' description: >- 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. The two categories of tools you can provide the model are: - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like file search. - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code. tool_choice: anyOf: - $ref: '#/components/schemas/OpenAI.ToolChoiceOptions' - $ref: '#/components/schemas/OpenAI.ToolChoiceObject' description: >- 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. prompt: type: object allOf: - $ref: '#/components/schemas/OpenAI.Prompt' nullable: true truncation: type: string enum: - auto - disabled nullable: true description: >- The truncation strategy to use for the model response. - `auto`: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation. - `disabled` (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error. default: disabled input: anyOf: - type: string - type: array items: anyOf: - $ref: '#/components/schemas/OpenAI.ImplicitUserMessage' - $ref: '#/components/schemas/OpenAI.ItemParam' description: >- 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: type: array items: $ref: '#/components/schemas/OpenAI.Includable' nullable: true description: >- Specify additional output data to include in the model response. Currently supported values are: - `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items. - `computer_call_output.output.image_url`: Include image urls from the computer call output. - `file_search_call.results`: Include the search results of the file search tool call. - `message.input_image.image_url`: Include image urls from the input message. - `message.output_text.logprobs`: Include logprobs with assistant messages. - `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program). parallel_tool_calls: type: boolean nullable: true description: Whether to allow the model to run tool calls in parallel. default: true store: type: boolean nullable: true description: >- Whether to store the generated model response for later retrieval via API. default: true instructions: type: string nullable: true description: >- A system (or developer) message inserted into the model's context. When using along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. stream: type: boolean nullable: true description: >- If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](/docs/api-reference/responses-streaming) for more information. default: false model: type: string description: The model deployment to use for the creation of this response. AzureResponse: type: object required: - metadata - temperature - top_p - user - id - object - created_at - error - incomplete_details - output - instructions - parallel_tool_calls - model properties: metadata: type: object additionalProperties: type: string nullable: true description: >- Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. x-oaiTypeLabel: map temperature: type: number format: float nullable: true minimum: 0 maximum: 2 description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. top_p: type: number format: float nullable: true minimum: 0 maximum: 1 description: >- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. user: type: string nullable: true description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). top_logprobs: type: integer format: int32 nullable: true description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. previous_response_id: type: string nullable: true description: |- The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). reasoning: type: object allOf: - $ref: '#/components/schemas/OpenAI.Reasoning' nullable: true background: type: boolean nullable: true description: |- Whether to run the model response in the background. [Learn more](/docs/guides/background). default: false max_output_tokens: type: integer format: int32 nullable: true description: >- An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). max_tool_calls: type: integer format: int32 nullable: true description: >- The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. text: type: object properties: format: $ref: '#/components/schemas/OpenAI.ResponseTextFormatConfiguration' description: >- 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: type: array items: $ref: '#/components/schemas/OpenAI.Tool' description: >- 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. The two categories of tools you can provide the model are: - **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). - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code. Learn more about [function calling](/docs/guides/function-calling). tool_choice: anyOf: - $ref: '#/components/schemas/OpenAI.ToolChoiceOptions' - $ref: '#/components/schemas/OpenAI.ToolChoiceObject' description: >- 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. prompt: type: object allOf: - $ref: '#/components/schemas/OpenAI.Prompt' nullable: true truncation: type: string enum: - auto - disabled nullable: true description: >- The truncation strategy to use for the model response. - `auto`: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation. - `disabled` (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error. default: disabled id: type: string description: Unique identifier for this Response. object: type: string enum: - response description: The object type of this resource - always set to `response`. status: type: string enum: - completed - failed - in_progress - cancelled - queued - incomplete description: |- The status of the response generation. One of `completed`, `failed`, `in_progress`, `cancelled`, `queued`, or `incomplete`. created_at: type: integer format: unixtime description: Unix timestamp (in seconds) of when this Response was created. error: type: object allOf: - $ref: '#/components/schemas/OpenAI.ResponseError' nullable: true incomplete_details: type: object properties: reason: type: string enum: - max_output_tokens - content_filter description: The reason why the response is incomplete. nullable: true description: Details about why the response is incomplete. output: type: array items: $ref: '#/components/schemas/OpenAI.ItemResource' description: |- 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: anyOf: - type: string - type: array items: $ref: '#/components/schemas/OpenAI.ItemParam' nullable: true description: >- A system (or developer) message inserted into the model's context. When using along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. output_text: type: string nullable: true description: >- SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. usage: $ref: '#/components/schemas/OpenAI.ResponseUsage' parallel_tool_calls: type: boolean description: Whether to allow the model to run tool calls in parallel. default: true model: type: string description: The model used to generate this response. OpenAI.ResponseStreamEvent: type: object required: - type - sequence_number properties: type: $ref: '#/components/schemas/OpenAI.ResponseStreamEventType' sequence_number: type: integer format: int32 description: The sequence number for this event. discriminator: propertyName: type mapping: response.completed: '#/components/schemas/OpenAI.ResponseCompletedEvent' response.content_part.added: '#/components/schemas/OpenAI.ResponseContentPartAddedEvent' response.content_part.done: '#/components/schemas/OpenAI.ResponseContentPartDoneEvent' response.created: '#/components/schemas/OpenAI.ResponseCreatedEvent' error: '#/components/schemas/OpenAI.ResponseErrorEvent' response.file_search_call.completed: '#/components/schemas/OpenAI.ResponseFileSearchCallCompletedEvent' response.file_search_call.in_progress: '#/components/schemas/OpenAI.ResponseFileSearchCallInProgressEvent' response.file_search_call.searching: '#/components/schemas/OpenAI.ResponseFileSearchCallSearchingEvent' response.function_call_arguments.delta: '#/components/schemas/OpenAI.ResponseFunctionCallArgumentsDeltaEvent' response.function_call_arguments.done: '#/components/schemas/OpenAI.ResponseFunctionCallArgumentsDoneEvent' response.in_progress: '#/components/schemas/OpenAI.ResponseInProgressEvent' response.failed: '#/components/schemas/OpenAI.ResponseFailedEvent' response.incomplete: '#/components/schemas/OpenAI.ResponseIncompleteEvent' response.output_item.added: '#/components/schemas/OpenAI.ResponseOutputItemAddedEvent' response.output_item.done: '#/components/schemas/OpenAI.ResponseOutputItemDoneEvent' response.refusal.delta: '#/components/schemas/OpenAI.ResponseRefusalDeltaEvent' response.refusal.done: '#/components/schemas/OpenAI.ResponseRefusalDoneEvent' response.output_text.delta: '#/components/schemas/OpenAI.ResponseTextDeltaEvent' response.output_text.done: '#/components/schemas/OpenAI.ResponseTextDoneEvent' response.reasoning_summary_part.added: '#/components/schemas/OpenAI.ResponseReasoningSummaryPartAddedEvent' response.reasoning_summary_part.done: '#/components/schemas/OpenAI.ResponseReasoningSummaryPartDoneEvent' response.reasoning_summary_text.delta: '#/components/schemas/OpenAI.ResponseReasoningSummaryTextDeltaEvent' response.reasoning_summary_text.done: '#/components/schemas/OpenAI.ResponseReasoningSummaryTextDoneEvent' response.web_search_call.completed: '#/components/schemas/OpenAI.ResponseWebSearchCallCompletedEvent' response.web_search_call.in_progress: '#/components/schemas/OpenAI.ResponseWebSearchCallInProgressEvent' response.web_search_call.searching: '#/components/schemas/OpenAI.ResponseWebSearchCallSearchingEvent' response.image_generation_call.completed: '#/components/schemas/OpenAI.ResponseImageGenCallCompletedEvent' response.image_generation_call.generating: '#/components/schemas/OpenAI.ResponseImageGenCallGeneratingEvent' response.image_generation_call.in_progress: '#/components/schemas/OpenAI.ResponseImageGenCallInProgressEvent' response.image_generation_call.partial_image: '#/components/schemas/OpenAI.ResponseImageGenCallPartialImageEvent' response.mcp_call.arguments_delta: '#/components/schemas/OpenAI.ResponseMCPCallArgumentsDeltaEvent' response.mcp_call.arguments_done: '#/components/schemas/OpenAI.ResponseMCPCallArgumentsDoneEvent' response.mcp_call.completed: '#/components/schemas/OpenAI.ResponseMCPCallCompletedEvent' response.mcp_call.failed: '#/components/schemas/OpenAI.ResponseMCPCallFailedEvent' response.mcp_call.in_progress: '#/components/schemas/OpenAI.ResponseMCPCallInProgressEvent' response.mcp_list_tools.completed: '#/components/schemas/OpenAI.ResponseMCPListToolsCompletedEvent' response.mcp_list_tools.failed: '#/components/schemas/OpenAI.ResponseMCPListToolsFailedEvent' response.mcp_list_tools.in_progress: '#/components/schemas/OpenAI.ResponseMCPListToolsInProgressEvent' response.queued: '#/components/schemas/OpenAI.ResponseQueuedEvent' response.reasoning.delta: '#/components/schemas/OpenAI.ResponseReasoningDeltaEvent' response.reasoning.done: '#/components/schemas/OpenAI.ResponseReasoningDoneEvent' response.reasoning_summary.delta: '#/components/schemas/OpenAI.ResponseReasoningSummaryDeltaEvent' response.reasoning_summary.done: '#/components/schemas/OpenAI.ResponseReasoningSummaryDoneEvent' response.code_interpreter_call_code.delta: >- #/components/schemas/OpenAI.ResponseCodeInterpreterCallCodeDeltaEvent response.code_interpreter_call_code.done: '#/components/schemas/OpenAI.ResponseCodeInterpreterCallCodeDoneEvent' response.code_interpreter_call.completed: >- #/components/schemas/OpenAI.ResponseCodeInterpreterCallCompletedEvent response.code_interpreter_call.in_progress: >- #/components/schemas/OpenAI.ResponseCodeInterpreterCallInProgressEvent response.code_interpreter_call.interpreting: >- #/components/schemas/OpenAI.ResponseCodeInterpreterCallInterpretingEvent AzureErrorResponse: type: object properties: error: type: object properties: code: type: string description: The distinct, machine-generated identifier for the error. message: type: string description: A human-readable message associated with the error. param: type: string description: >- If applicable, the request input parameter associated with the error type: type: string enum: - error description: The object type, always 'error.' inner_error: {} description: The error details. OpenAI.Reasoning: type: object properties: effort: allOf: - $ref: '#/components/schemas/OpenAI.ReasoningEffort' nullable: true default: medium summary: type: string enum: - auto - concise - detailed nullable: true description: >- A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of `auto`, `concise`, or `detailed`. generate_summary: type: string enum: - auto - concise - detailed nullable: true description: >- **Deprecated:** use `summary` instead. A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of `auto`, `concise`, or `detailed`. deprecated: true default: null description: |- **o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). OpenAI.ResponseTextFormatConfiguration: type: object required: - type properties: type: $ref: '#/components/schemas/OpenAI.ResponseTextFormatConfigurationType' discriminator: propertyName: type mapping: text: '#/components/schemas/OpenAI.ResponseTextFormatConfigurationText' json_object: >- #/components/schemas/OpenAI.ResponseTextFormatConfigurationJsonObject json_schema: >- #/components/schemas/OpenAI.ResponseTextFormatConfigurationJsonSchema OpenAI.Tool: type: object required: - type properties: type: $ref: '#/components/schemas/OpenAI.ToolType' discriminator: propertyName: type mapping: function: '#/components/schemas/OpenAI.FunctionTool' file_search: '#/components/schemas/OpenAI.FileSearchTool' computer_use_preview: '#/components/schemas/OpenAI.ComputerUsePreviewTool' web_search_preview: '#/components/schemas/OpenAI.WebSearchPreviewTool' code_interpreter: '#/components/schemas/OpenAI.CodeInterpreterTool' image_generation: '#/components/schemas/OpenAI.ImageGenTool' local_shell: '#/components/schemas/OpenAI.LocalShellTool' mcp: '#/components/schemas/OpenAI.MCPTool' OpenAI.ToolChoiceOptions: type: string enum: - none - auto - required description: >- 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. OpenAI.ToolChoiceObject: type: object required: - type properties: type: $ref: '#/components/schemas/OpenAI.ToolChoiceObjectType' discriminator: propertyName: type mapping: file_search: '#/components/schemas/OpenAI.ToolChoiceObjectFileSearch' computer_use_preview: '#/components/schemas/OpenAI.ToolChoiceObjectComputer' web_search_preview: '#/components/schemas/OpenAI.ToolChoiceObjectWebSearch' image_generation: '#/components/schemas/OpenAI.ToolChoiceObjectImageGen' code_interpreter: '#/components/schemas/OpenAI.ToolChoiceObjectCodeInterpreter' function: '#/components/schemas/OpenAI.ToolChoiceObjectFunction' mcp: '#/components/schemas/OpenAI.ToolChoiceObjectMCP' OpenAI.Prompt: type: object required: - id properties: id: type: string description: The unique identifier of the prompt template to use. version: type: string nullable: true description: Optional version of the prompt template. variables: type: object allOf: - $ref: '#/components/schemas/OpenAI.ResponsePromptVariables' nullable: true description: |- Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). OpenAI.ImplicitUserMessage: type: object required: - content properties: content: anyOf: - type: string - type: array items: $ref: '#/components/schemas/OpenAI.ItemContent' OpenAI.ItemParam: type: object required: - type properties: type: $ref: '#/components/schemas/OpenAI.ItemType' discriminator: propertyName: type mapping: file_search_call: '#/components/schemas/OpenAI.FileSearchToolCallItemParam' computer_call: '#/components/schemas/OpenAI.ComputerToolCallItemParam' computer_call_output: '#/components/schemas/OpenAI.ComputerToolCallOutputItemParam' web_search_call: '#/components/schemas/OpenAI.WebSearchToolCallItemParam' function_call: '#/components/schemas/OpenAI.FunctionToolCallItemParam' function_call_output: '#/components/schemas/OpenAI.FunctionToolCallOutputItemParam' reasoning: '#/components/schemas/OpenAI.ReasoningItemParam' item_reference: '#/components/schemas/OpenAI.ItemReferenceItemParam' image_generation_call: '#/components/schemas/OpenAI.ImageGenToolCallItemParam' code_interpreter_call: '#/components/schemas/OpenAI.CodeInterpreterToolCallItemParam' local_shell_call: '#/components/schemas/OpenAI.LocalShellToolCallItemParam' local_shell_call_output: '#/components/schemas/OpenAI.LocalShellToolCallOutputItemParam' mcp_list_tools: '#/components/schemas/OpenAI.MCPListToolsItemParam' mcp_approval_request: '#/components/schemas/OpenAI.MCPApprovalRequestItemParam' mcp_approval_response: '#/components/schemas/OpenAI.MCPApprovalResponseItemParam' mcp_call: '#/components/schemas/OpenAI.MCPCallItemParam' message: '#/components/schemas/OpenAI.ResponsesMessageItemParam' description: Content item used to generate a response. OpenAI.Includable: type: string enum: - code_interpreter_call.outputs - computer_call_output.output.image_url - file_search_call.results - message.input_image.image_url - message.output_text.logprobs - reasoning.encrypted_content description: >- Specify additional output data to include in the model response. Currently supported values are: - `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items. - `computer_call_output.output.image_url`: Include image urls from the computer call output. - `file_search_call.results`: Include the search results of the file search tool call. - `message.input_image.image_url`: Include image urls from the input message. - `message.output_text.logprobs`: Include logprobs with assistant messages. - `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program). OpenAI.ResponseError: type: object required: - code - message properties: code: $ref: '#/components/schemas/OpenAI.ResponseErrorCode' message: type: string description: A human-readable description of the error. description: An error object returned when the model fails to generate a Response. OpenAI.ItemResource: type: object required: - type - id properties: type: $ref: '#/components/schemas/OpenAI.ItemType' id: type: string discriminator: propertyName: type mapping: file_search_call: '#/components/schemas/OpenAI.FileSearchToolCallItemResource' computer_call: '#/components/schemas/OpenAI.ComputerToolCallItemResource' computer_call_output: '#/components/schemas/OpenAI.ComputerToolCallOutputItemResource' web_search_call: '#/components/schemas/OpenAI.WebSearchToolCallItemResource' function_call: '#/components/schemas/OpenAI.FunctionToolCallItemResource' function_call_output: '#/components/schemas/OpenAI.FunctionToolCallOutputItemResource' reasoning: '#/components/schemas/OpenAI.ReasoningItemResource' image_generation_call: '#/components/schemas/OpenAI.ImageGenToolCallItemResource' code_interpreter_call: '#/components/schemas/OpenAI.CodeInterpreterToolCallItemResource' local_shell_call: '#/components/schemas/OpenAI.LocalShellToolCallItemResource' local_shell_call_output: '#/components/schemas/OpenAI.LocalShellToolCallOutputItemResource' mcp_list_tools: '#/components/schemas/OpenAI.MCPListToolsItemResource' mcp_approval_request: '#/components/schemas/OpenAI.MCPApprovalRequestItemResource' mcp_approval_response: '#/components/schemas/OpenAI.MCPApprovalResponseItemResource' mcp_call: '#/components/schemas/OpenAI.MCPCallItemResource' message: '#/components/schemas/OpenAI.ResponsesMessageItemResource' description: Content item used to generate a response. OpenAI.ResponseUsage: type: object required: - input_tokens - input_tokens_details - output_tokens - output_tokens_details - total_tokens properties: input_tokens: type: integer format: int32 description: The number of input tokens. input_tokens_details: type: object properties: cached_tokens: type: integer format: int32 description: |- The number of tokens that were retrieved from the cache. [More on prompt caching](/docs/guides/prompt-caching). required: - cached_tokens description: A detailed breakdown of the input tokens. output_tokens: type: integer format: int32 description: The number of output tokens. output_tokens_details: type: object properties: reasoning_tokens: type: integer format: int32 description: The number of reasoning tokens. required: - reasoning_tokens description: A detailed breakdown of the output tokens. total_tokens: type: integer format: int32 description: The total number of tokens used. description: |- Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. OpenAI.ResponseStreamEventType: anyOf: - type: string - type: string enum: - response.audio.delta - response.audio.done - response.audio_transcript.delta - response.audio_transcript.done - response.code_interpreter_call_code.delta - response.code_interpreter_call_code.done - response.code_interpreter_call.completed - response.code_interpreter_call.in_progress - response.code_interpreter_call.interpreting - response.completed - response.content_part.added - response.content_part.done - response.created - error - response.file_search_call.completed - response.file_search_call.in_progress - response.file_search_call.searching - response.function_call_arguments.delta - response.function_call_arguments.done - response.in_progress - response.failed - response.incomplete - response.output_item.added - response.output_item.done - response.refusal.delta - response.refusal.done - response.output_text.annotation.added - response.output_text.delta - response.output_text.done - response.reasoning_summary_part.added - response.reasoning_summary_part.done - response.reasoning_summary_text.delta - response.reasoning_summary_text.done - response.web_search_call.completed - response.web_search_call.in_progress - response.web_search_call.searching - response.image_generation_call.completed - response.image_generation_call.generating - response.image_generation_call.in_progress - response.image_generation_call.partial_image - response.mcp_call.arguments_delta - response.mcp_call.arguments_done - response.mcp_call.completed - response.mcp_call.failed - response.mcp_call.in_progress - response.mcp_list_tools.completed - response.mcp_list_tools.failed - response.mcp_list_tools.in_progress - response.queued - response.reasoning.delta - response.reasoning.done - response.reasoning_summary.delta - response.reasoning_summary.done OpenAI.ReasoningEffort: type: string enum: - low - medium - high description: |- **o-series models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. OpenAI.ResponseTextFormatConfigurationType: anyOf: - type: string - type: string enum: - text - json_schema - json_object description: >- 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. OpenAI.ToolType: anyOf: - type: string - type: string enum: - file_search - function - computer_use_preview - web_search_preview - mcp - code_interpreter - image_generation - local_shell description: A tool that can be used to generate a response. OpenAI.ToolChoiceObjectType: anyOf: - type: string - type: string enum: - file_search - function - computer_use_preview - web_search_preview - image_generation - code_interpreter - mcp description: >- Indicates that the model should use a built-in tool to generate a response. [Learn more about built-in tools](/docs/guides/tools). OpenAI.ResponsePromptVariables: type: object additionalProperties: $ref: '#/components/schemas/OpenAI.ItemParam' description: |- Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files. x-oaiExpandable: true x-oaiTypeLabel: map OpenAI.ItemContent: type: object required: - type properties: type: $ref: '#/components/schemas/OpenAI.ItemContentType' discriminator: propertyName: type mapping: input_audio: '#/components/schemas/OpenAI.ItemContentInputAudio' output_audio: '#/components/schemas/OpenAI.ItemContentOutputAudio' refusal: '#/components/schemas/OpenAI.ItemContentRefusal' input_text: '#/components/schemas/OpenAI.ItemContentInputText' input_image: '#/components/schemas/OpenAI.ItemContentInputImage' input_file: '#/components/schemas/OpenAI.ItemContentInputFile' output_text: '#/components/schemas/OpenAI.ItemContentOutputText' OpenAI.ItemType: type: string enum: - message - file_search_call - function_call - function_call_output - computer_call - computer_call_output - web_search_call - reasoning - item_reference - image_generation_call - code_interpreter_call - local_shell_call - local_shell_call_output - mcp_list_tools - mcp_approval_request - mcp_approval_response - mcp_call OpenAI.ResponseErrorCode: type: string 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 description: The error code for the response. OpenAI.ItemContentType: type: string enum: - input_text - input_audio - input_image - input_file - output_text - output_audio - refusal description: Multi-modal input and output contents. securitySchemes: ApiKeyAuth: type: apiKey in: header name: api-key ApiKeyAuth_: type: apiKey in: header name: authorization OAuth2Auth: type: oauth2 flows: implicit: authorizationUrl: https://login.microsoftonline.com/common/oauth2/v2.0/authorize scopes: https://cognitiveservices.azure.com/.default: '' ````