Class: OpenAI::Models::Responses::ResponseCreateParams

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::Responses::ResponseCreateParams

Extended by:

Internal::Type::RequestParameters::Converter

Includes:

Internal::Type::RequestParameters

Defined in:

lib/openai/models/responses/response_create_params.rb

Overview

See Also:

• Resources::Responses#create
• Resources::Responses#stream_raw

Defined Under Namespace

Modules: Input, ServiceTier, ToolChoice, Truncation

Instance Attribute Summary

• #background ⇒ Boolean^?

  Whether to run the model response in the background.

• #include ⇒ Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>^?

  Specify additional output data to include in the model response.

• #input ⇒ String, ...

  Text, image, or file inputs to the model, used to generate a response.

• #instructions ⇒ String^?

  A system (or developer) message inserted into the model’s context.

• #max_output_tokens ⇒ Integer^?

  An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](platform.openai.com/docs/guides/reasoning).

• #max_tool_calls ⇒ Integer^?

  The maximum number of total calls to built-in tools that can be processed in a response.

• #metadata ⇒ Hash{Symbol=>String}^?

  Set of 16 key-value pairs that can be attached to an object.

• #model ⇒ String, ...

  Model ID used to generate the response, like ‘gpt-4o` or `o3`.

• #parallel_tool_calls ⇒ Boolean^?

  Whether to allow the model to run tool calls in parallel.

• #previous_response_id ⇒ String^?

  The unique ID of the previous response to the model.

• #prompt ⇒ OpenAI::Models::Responses::ResponsePrompt^?

  Reference to a prompt template and its variables.

• #reasoning ⇒ OpenAI::Models::Reasoning^?

  **o-series models only**.

• #service_tier ⇒ Symbol, ...

  Specifies the processing type used for serving the request.

• #store ⇒ Boolean^?

  Whether to store the generated model response for later retrieval via API.

• #temperature ⇒ Float^?

  What sampling temperature to use, between 0 and 2.

• #text ⇒ OpenAI::Models::Responses::ResponseTextConfig^?

  Configuration options for a text response from the model.

• #tool_choice ⇒ Symbol, ...

  How the model should select which tool (or tools) to use when generating a response.

• #tools ⇒ Array<OpenAI::Models::Responses::FunctionTool, OpenAI::StructuredOutput::JsonSchemaConverter, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::WebSearchTool>^?

  An array of tools the model may call while generating a response.

• #top_logprobs ⇒ Integer^?

  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.

• #top_p ⇒ Float^?

  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

• #truncation ⇒ Symbol, ...

  The truncation strategy to use for the model response.

• #user ⇒ String^?

  A stable identifier for your end-users.

Attributes included from Internal::Type::RequestParameters

#request_options

Class Method Summary

• .values ⇒ Array<Symbol>
• .variants ⇒ Array(Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp)

Instance Method Summary

• #initialize(background: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, reasoning: nil, service_tier: nil, store: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, request_options: {}) ⇒ Object constructor

  Some parameter documentations has been truncated, see ResponseCreateParams for more details.

Methods included from Internal::Type::RequestParameters::Converter

dump_request

Methods included from Internal::Type::RequestParameters

included

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(background: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, reasoning: nil, service_tier: nil, store: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, request_options: {}) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Responses::ResponseCreateParams for more details.

Parameters:

• background (Boolean, nil) (defaults to: nil) —

  Whether to run the model response in the background.

• include (Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>, nil) (defaults to: nil) —

  Specify additional output data to include in the model response. Currently

• input (String, Array<OpenAI::Models::Responses::EasyInputMessage, OpenAI::Models::Responses::ResponseInputItem::Message, OpenAI::Models::Responses::ResponseOutputMessage, OpenAI::Models::Responses::ResponseFileSearchToolCall, OpenAI::Models::Responses::ResponseComputerToolCall, OpenAI::Models::Responses::ResponseInputItem::ComputerCallOutput, OpenAI::Models::Responses::ResponseFunctionWebSearch, OpenAI::Models::Responses::ResponseFunctionToolCall, OpenAI::Models::Responses::ResponseInputItem::FunctionCallOutput, OpenAI::Models::Responses::ResponseReasoningItem, OpenAI::Models::Responses::ResponseInputItem::ImageGenerationCall, OpenAI::Models::Responses::ResponseCodeInterpreterToolCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCallOutput, OpenAI::Models::Responses::ResponseInputItem::McpListTools, OpenAI::Models::Responses::ResponseInputItem::McpApprovalRequest, OpenAI::Models::Responses::ResponseInputItem::McpApprovalResponse, OpenAI::Models::Responses::ResponseInputItem::McpCall, OpenAI::Models::Responses::ResponseInputItem::ItemReference>) (defaults to: nil) —

  Text, image, or file inputs to the model, used to generate a response.

• instructions (String, nil) (defaults to: nil) —

  A system (or developer) message inserted into the model’s context.

• max_output_tokens (Integer, nil) (defaults to: nil) —

  An upper bound for the number of tokens that can be generated for a response, in

• max_tool_calls (Integer, nil) (defaults to: nil) —

  The maximum number of total calls to built-in tools that can be processed in a r

• metadata (Hash{Symbol=>String}, nil) (defaults to: nil) —

  Set of 16 key-value pairs that can be attached to an object. This can be

• model (String, Symbol, OpenAI::Models::ChatModel, OpenAI::Models::ResponsesModel::ResponsesOnlyModel) (defaults to: nil) —

  Model ID used to generate the response, like ‘gpt-4o` or `o3`. OpenAI

• parallel_tool_calls (Boolean, nil) (defaults to: nil) —

  Whether to allow the model to run tool calls in parallel.

• previous_response_id (String, nil) (defaults to: nil) —

  The unique ID of the previous response to the model. Use this to

• prompt (OpenAI::Models::Responses::ResponsePrompt, nil) (defaults to: nil) —

  Reference to a prompt template and its variables.

• reasoning (OpenAI::Models::Reasoning, nil) (defaults to: nil) —

  **o-series models only**

• service_tier (Symbol, OpenAI::Models::Responses::ResponseCreateParams::ServiceTier, nil) (defaults to: nil) —

  Specifies the processing type used for serving the request.

• store (Boolean, nil) (defaults to: nil) —

  Whether to store the generated model response for later retrieval via

• temperature (Float, nil) (defaults to: nil) —

  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will m

• text (OpenAI::Models::Responses::ResponseTextConfig) (defaults to: nil) —

  Configuration options for a text response from the model. Can be plain

• tool_choice (Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp) (defaults to: nil) —

  How the model should select which tool (or tools) to use when generating

• tools (Array<OpenAI::Models::Responses::FunctionTool, OpenAI::StructuredOutput::JsonSchemaConverter, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::WebSearchTool>) (defaults to: nil) —

  An array of tools the model may call while generating a response. You

• top_logprobs (Integer, nil) (defaults to: nil) —

  An integer between 0 and 20 specifying the number of most likely tokens to

• top_p (Float, nil) (defaults to: nil) —

  An alternative to sampling with temperature, called nucleus sampling,

• truncation (Symbol, OpenAI::Models::Responses::ResponseCreateParams::Truncation, nil) (defaults to: nil) —

  The truncation strategy to use for the model response.

• user (String) (defaults to: nil) —

  A stable identifier for your end-users.

• request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}) (defaults to: {})

# File 'lib/openai/models/responses/response_create_params.rb', line 252

Instance Attribute Details

#background ⇒ Boolean^?

Whether to run the model response in the background. [Learn more](platform.openai.com/docs/guides/background).

Returns:

• (Boolean, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 18

optional :background, OpenAI::Internal::Type::Boolean, nil?: true

#include ⇒ Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>^?

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).

Returns:

• (Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 39

optional :include,
-> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Responses::ResponseIncludable] },
nil?: true

#input ⇒ String, ...

Text, image, or file inputs to the model, used to generate a response.

Learn more:

• [Text inputs and outputs](platform.openai.com/docs/guides/text)

• [Image inputs](platform.openai.com/docs/guides/images)

• [File inputs](platform.openai.com/docs/guides/pdf-files)

• [Conversation state](platform.openai.com/docs/guides/conversation-state)

• [Function calling](platform.openai.com/docs/guides/function-calling)

Returns:

• (String, Array<OpenAI::Models::Responses::EasyInputMessage, OpenAI::Models::Responses::ResponseInputItem::Message, OpenAI::Models::Responses::ResponseOutputMessage, OpenAI::Models::Responses::ResponseFileSearchToolCall, OpenAI::Models::Responses::ResponseComputerToolCall, OpenAI::Models::Responses::ResponseInputItem::ComputerCallOutput, OpenAI::Models::Responses::ResponseFunctionWebSearch, OpenAI::Models::Responses::ResponseFunctionToolCall, OpenAI::Models::Responses::ResponseInputItem::FunctionCallOutput, OpenAI::Models::Responses::ResponseReasoningItem, OpenAI::Models::Responses::ResponseInputItem::ImageGenerationCall, OpenAI::Models::Responses::ResponseCodeInterpreterToolCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCall, OpenAI::Models::Responses::ResponseInputItem::LocalShellCallOutput, OpenAI::Models::Responses::ResponseInputItem::McpListTools, OpenAI::Models::Responses::ResponseInputItem::McpApprovalRequest, OpenAI::Models::Responses::ResponseInputItem::McpApprovalResponse, OpenAI::Models::Responses::ResponseInputItem::McpCall, OpenAI::Models::Responses::ResponseInputItem::ItemReference>, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 55

optional :input, union: -> { OpenAI::Responses::ResponseCreateParams::Input }

#instructions ⇒ String^?

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.

Returns:

• (String, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 65

optional :instructions, String, nil?: true

#max_output_tokens ⇒ Integer^?

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](platform.openai.com/docs/guides/reasoning).

Returns:

• (Integer, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 73

optional :max_output_tokens, Integer, nil?: true

#max_tool_calls ⇒ Integer^?

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.

Returns:

• (Integer, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 82

optional :max_tool_calls, Integer, nil?: true

#metadata ⇒ Hash{Symbol=>String}^?

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.

Returns:

• (Hash{Symbol=>String}, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 93

optional :metadata, OpenAI::Internal::Type::HashOf[String], nil?: true

#model ⇒ String, ...

Model ID used to generate the response, like ‘gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](platform.openai.com/docs/models) to browse and compare available models.

Returns:

• (String, Symbol, OpenAI::Models::ChatModel, OpenAI::Models::ResponsesModel::ResponsesOnlyModel, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 103

optional :model, union: -> { OpenAI::ResponsesModel }

#parallel_tool_calls ⇒ Boolean^?

Whether to allow the model to run tool calls in parallel.

Returns:

• (Boolean, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 109

optional :parallel_tool_calls, OpenAI::Internal::Type::Boolean, nil?: true

#previous_response_id ⇒ String^?

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](platform.openai.com/docs/guides/conversation-state).

Returns:

• (String, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 117

optional :previous_response_id, String, nil?: true

#prompt ⇒ OpenAI::Models::Responses::ResponsePrompt^?

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

Returns:

• (OpenAI::Models::Responses::ResponsePrompt, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 124

optional :prompt, -> { OpenAI::Responses::ResponsePrompt }, nil?: true

#reasoning ⇒ OpenAI::Models::Reasoning^?

**o-series models only**

Configuration options for [reasoning models](platform.openai.com/docs/guides/reasoning).

Returns:

• (OpenAI::Models::Reasoning, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 133

optional :reasoning, -> { OpenAI::Reasoning }, nil?: true

#service_tier ⇒ Symbol, ...

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 requset will be processed with the standard pricing and performance for the selected model.

• If set to ‘[flex](platform.openai.com/docs/guides/flex-processing)’ or ‘priority’, then the request will be processed with the corresponding service tier. [Contact sales](openai.com/contact-sales) to learn more about Priority processing.

• 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.

Returns:

• (Symbol, OpenAI::Models::Responses::ResponseCreateParams::ServiceTier, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 155

optional :service_tier, enum: -> { OpenAI::Responses::ResponseCreateParams::ServiceTier }, nil?: true

#store ⇒ Boolean^?

Whether to store the generated model response for later retrieval via API.

Returns:

• (Boolean, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 161

optional :store, OpenAI::Internal::Type::Boolean, nil?: true

#temperature ⇒ Float^?

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.

Returns:

• (Float, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 170

optional :temperature, Float, nil?: true

#text ⇒ OpenAI::Models::Responses::ResponseTextConfig^?

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

• [Text inputs and outputs](platform.openai.com/docs/guides/text)

• [Structured Outputs](platform.openai.com/docs/guides/structured-outputs)

Returns:

• (OpenAI::Models::Responses::ResponseTextConfig, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 180

optional :text,
union: -> {
  OpenAI::UnionOf[
    OpenAI::Responses::ResponseTextConfig,
    OpenAI::StructuredOutput::JsonSchemaConverter
  ]
}

#tool_choice ⇒ Symbol, ...

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.

Returns:

• (Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 194

optional :tool_choice, union: -> { OpenAI::Responses::ResponseCreateParams::ToolChoice }

#tools ⇒ Array<OpenAI::Models::Responses::FunctionTool, OpenAI::StructuredOutput::JsonSchemaConverter, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::WebSearchTool>^?

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](platform.openai.com/docs/guides/tools-web-search) or [file search](platform.openai.com/docs/guides/tools-file-search). Learn more about [built-in tools](platform.openai.com/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](platform.openai.com/docs/guides/function-calling).

Returns:

• (Array<OpenAI::Models::Responses::FunctionTool, OpenAI::StructuredOutput::JsonSchemaConverter, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::WebSearchTool>, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 213

optional :tools, -> { OpenAI::Internal::Type::ArrayOf[union: OpenAI::Responses::Tool] }

#top_logprobs ⇒ Integer^?

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.

Returns:

• (Integer, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 220

optional :top_logprobs, Integer, nil?: true

#top_p ⇒ Float^?

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.

Returns:

• (Float, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 230

optional :top_p, Float, nil?: true

#truncation ⇒ Symbol, ...

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.

Returns:

• (Symbol, OpenAI::Models::Responses::ResponseCreateParams::Truncation, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 242

optional :truncation, enum: -> { OpenAI::Responses::ResponseCreateParams::Truncation }, nil?: true

#user ⇒ String^?

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](platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

Returns:

• (String, nil)

# File 'lib/openai/models/responses/response_create_params.rb', line 250

optional :user, String

Class Method Details

.values ⇒ Array<Symbol>

Returns:

• (Array<Symbol>)

# File 'lib/openai/models/responses/response_create_params.rb', line 352

.variants ⇒ Array(Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp)

Returns:

• (Array(Symbol, OpenAI::Models::Responses::ToolChoiceOptions, OpenAI::Models::Responses::ToolChoiceTypes, OpenAI::Models::Responses::ToolChoiceFunction, OpenAI::Models::Responses::ToolChoiceMcp))

# File 'lib/openai/models/responses/response_create_params.rb', line 322