Class: OpenAI::Models::Chat::CompletionCreateParams

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::Chat::CompletionCreateParams

Extended by:

Internal::Type::RequestParameters::Converter

Includes:

Internal::Type::RequestParameters

Defined in:

lib/openai/models/chat/completion_create_params.rb,
sig/openai/models/chat/completion_create_params.rbs

Overview

See Also:

• OpenAI::Resources::Chat::Completions#create
• OpenAI::Resources::Chat::Completions#stream_raw

Defined Under Namespace

Modules: FunctionCall, Modality, Model, PromptCacheRetention, ResponseFormat, ServiceTier, Stop, Verbosity Classes: Function, Moderation, PromptCacheOptions, WebSearchOptions

Constant Summary

OpenAI =

Returns:

Instance Attribute Summary

• #audio ⇒ OpenAI::Chat::ChatCompletionAudioParam^?

  Parameters for audio output.

• #frequency_penalty ⇒ Float^?

  Number between -2.0 and 2.0.

• #function_call ⇒ OpenAI::Models::Chat::CompletionCreateParams::function_call^?

  Deprecated in favor of tool_choice.

• #functions ⇒ ::Array[OpenAI::Chat::CompletionCreateParams::Function]^?

  Deprecated in favor of tools.

• #logit_bias ⇒ ::Hash[Symbol, Integer]^?

  Modify the likelihood of specified tokens appearing in the completion.

• #logprobs ⇒ Boolean^?

  Whether to return log probabilities of the output tokens or not.

• #max_completion_tokens ⇒ Integer^?

  An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

• #max_tokens ⇒ Integer^?

  The maximum number of tokens that can be generated in the chat completion.

• #messages ⇒ ::Array[OpenAI::Models::Chat::chat_completion_message_param]

  A list of messages comprising the conversation so far.

• #metadata ⇒ OpenAI::Models::metadata^?

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

• #modalities ⇒ ::Array[OpenAI::Models::Chat::CompletionCreateParams::modality]^?

  Output types that you would like the model to generate.

• #model ⇒ OpenAI::Models::Chat::CompletionCreateParams::model

  Model ID used to generate the response, like gpt-6-astra or o3.

• #moderation ⇒ OpenAI::Chat::CompletionCreateParams::Moderation^?

  Configuration for running moderation on the request input and generated output.

• #n ⇒ Integer^?

  How many chat completion choices to generate for each input message.

• #parallel_tool_calls ⇒ Boolean^?

  Whether to enable parallel function calling during tool use.

• #prediction ⇒ OpenAI::Chat::ChatCompletionPredictionContent^?

  Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time.

• #presence_penalty ⇒ Float^?

  Number between -2.0 and 2.0.

• #prompt_cache_key ⇒ String^?

  Used by OpenAI to cache responses for similar requests to optimize your cache hit rates.

• #prompt_cache_options ⇒ OpenAI::Chat::CompletionCreateParams::PromptCacheOptions^?

  Options for prompt caching.

• #prompt_cache_retention ⇒ OpenAI::Models::Chat::CompletionCreateParams::prompt_cache_retention^?

  Deprecated.

• #reasoning_effort ⇒ OpenAI::Models::reasoning_effort^?

  Constrains effort on reasoning for reasoning models.

• #response_format ⇒ OpenAI::Models::Chat::CompletionCreateParams::response_format^?

  An object specifying the format that the model must output.

• #safety_identifier ⇒ String^?

  A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies.

• #seed ⇒ Integer^?

  This feature is in Beta.

• #service_tier ⇒ OpenAI::Models::Chat::CompletionCreateParams::service_tier^?

  Specifies the processing type used for serving the request.

• #stop ⇒ OpenAI::Models::Chat::CompletionCreateParams::stop^?

  Not supported with latest reasoning models o3 and o4-mini.

• #store ⇒ Boolean^?

  Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

• #stream_options ⇒ OpenAI::Chat::ChatCompletionStreamOptions^?

  Options for streaming response.

• #temperature ⇒ Float^?

  What sampling temperature to use, between 0 and 2.

• #tool_choice ⇒ OpenAI::Models::Chat::chat_completion_tool_choice_option^?

  Controls which (if any) tool is called by the model.

• #tools ⇒ ::Array[OpenAI::Models::Chat::chat_completion_tool]^?

  A list of tools the model may call.

• #top_logprobs ⇒ Integer^?

  An integer between 0 and 20 specifying the maximum 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.

• #user ⇒ String^?

  This field is being replaced by safety_identifier and prompt_cache_key.

• #verbosity ⇒ OpenAI::Models::Chat::CompletionCreateParams::verbosity^?

  Constrains the verbosity of the model's response.

• #web_search_options ⇒ OpenAI::Chat::CompletionCreateParams::WebSearchOptions^?

  This tool searches the web for relevant results to use in a response.

Attributes included from Internal::Type::RequestParameters

#request_options

Attributes inherited from Internal::Type::BaseModel

#last_response

Class Method Summary

• .values ⇒ Array<Symbol>
• .variants ⇒ Array(OpenAI::Models::ResponseFormatText, OpenAI::Models::ResponseFormatJSONSchema, OpenAI::Models::ResponseFormatJSONObject)

Instance Method Summary

• #initialize(name:, description: nil, parameters: nil) ⇒ Object constructor
• #to_hash ⇒ {

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

dump_request

Methods included from Internal::Type::RequestParameters

included

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, 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, coerce_with_error, dump, #dump, #inspect, inspect, meta_info, 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(name:, description: nil, parameters: nil) ⇒ Object

Parameters:

• A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

• Model ID used to generate the response, like gpt-6-astra or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

• Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

• Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

• Deprecated in favor of tool_choice.

  Controls which (if any) function is called by the model.

  none means the model will not call a function and instead generates a message.

  auto means the model can pick between generating a message or calling a function.

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

  none is the default when no functions are present. auto is the default if functions are present.

• Deprecated in favor of tools.

  A list of functions the model may generate JSON inputs for.

• Modify the likelihood of specified tokens appearing in the completion.

  Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

• Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

• An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

• The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

  This value is now deprecated in favor of max_completion_tokens, and is not compatible with o-series models.

• 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.

• Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

  ["text"]

  The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

  ["text", "audio"]

• Configuration for running moderation on the request input and generated output.

• How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

• Whether to enable parallel function calling during tool use.

• Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

• Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

• Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

• Options for prompt caching. Supported for gpt-5.6 and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with prompt_cache_breakpoint. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set mode to explicit to disable the implicit breakpoint. The ttl defaults to 30m, which is currently the only supported value. See the prompt caching guide for current details.

• Deprecated. Use prompt_cache_options.ttl instead.

  The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. This field expresses a maximum retention policy, while prompt_cache_options.ttl expresses a minimum cache lifetime. The two fields are independent and do not interact. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.

  For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:

  • Organizations without ZDR enabled default to 24h.
  • Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.

• Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

• An object specifying the format that the model must output.

  Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

  Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

• 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.

• This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

• 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', then the request will be processed with the Flex Processing service tier.
  • To opt-in to Fast mode at the request level, include the service_tier=fast or service_tier=priority parameter for Responses or Chat Completions. The response will show service_tier=priority regardless of if you specify service_tier=fast or priority in your request.
  • 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.

• Not supported with latest reasoning models o3 and o4-mini.

  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

• Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

  Supports text and image inputs. Note: image inputs over 8MB will be dropped.

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

• 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.

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

  none is the default when no tools are present. auto is the default if tools are present.

• A list of tools the model may call. You can provide either custom tools or function tools.

• An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. logprobs must be set to true if this parameter is used.

• 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.

• 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.

• 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. The default is medium.

• This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

# File 'lib/openai/models/chat/completion_create_params.rb', line 442

Instance Attribute Details

#audio ⇒ OpenAI::Chat::ChatCompletionAudioParam^?

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 43

optional :audio, -> { OpenAI::Chat::ChatCompletionAudioParam }, nil?: true

#frequency_penalty ⇒ Float^?

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 51

optional :frequency_penalty, Float, nil?: true

#function_call ⇒ OpenAI::Models::Chat::CompletionCreateParams::function_call^?

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

none means the model will not call a function and instead generates a message.

auto means the model can pick between generating a message or calling a function.

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

none is the default when no functions are present. auto is the default if functions are present.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 72

optional :function_call, union: -> { OpenAI::Chat::CompletionCreateParams::FunctionCall }

#functions ⇒ ::Array[OpenAI::Chat::CompletionCreateParams::Function]^?

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 82

optional(
  :functions,
  -> { OpenAI::Internal::Type::ArrayOf[OpenAI::Chat::CompletionCreateParams::Function] }
)

#logit_bias ⇒ ::Hash[Symbol, Integer]^?

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 98

optional :logit_bias, OpenAI::Internal::Type::HashOf[Integer], nil?: true

#logprobs ⇒ Boolean^?

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 106

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

#max_completion_tokens ⇒ Integer^?

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 114

optional :max_completion_tokens, Integer, nil?: true

#max_tokens ⇒ Integer^?

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o-series models.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 128

optional :max_tokens, Integer, nil?: true

#messages ⇒ ::Array[OpenAI::Models::Chat::chat_completion_message_param]

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 22

required(
  :messages,
  -> { OpenAI::Internal::Type::ArrayOf[union: OpenAI::Chat::ChatCompletionMessageParam] }
)

#metadata ⇒ OpenAI::Models::metadata^?

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 139

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

#modalities ⇒ ::Array[OpenAI::Models::Chat::CompletionCreateParams::modality]^?

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 154

optional(
  :modalities,
  -> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Chat::CompletionCreateParams::Modality] },
  nil?: true
)

#model ⇒ OpenAI::Models::Chat::CompletionCreateParams::model

Model ID used to generate the response, like gpt-6-astra or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 35

required :model, union: -> { OpenAI::Chat::CompletionCreateParams::Model }

#moderation ⇒ OpenAI::Chat::CompletionCreateParams::Moderation^?

Configuration for running moderation on the request input and generated output.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 164

optional :moderation, -> { OpenAI::Chat::CompletionCreateParams::Moderation }, nil?: true

#n ⇒ Integer^?

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 172

optional :n, Integer, nil?: true

#parallel_tool_calls ⇒ Boolean^?

Whether to enable parallel function calling during tool use.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 180

optional :parallel_tool_calls, OpenAI::Internal::Type::Boolean

#prediction ⇒ OpenAI::Chat::ChatCompletionPredictionContent^?

Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 190

optional :prediction, -> { OpenAI::Chat::ChatCompletionPredictionContent }, nil?: true

#presence_penalty ⇒ Float^?

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 198

optional :presence_penalty, Float, nil?: true

#prompt_cache_key ⇒ String^?

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 206

optional :prompt_cache_key, String, nil?: true

#prompt_cache_options ⇒ OpenAI::Chat::CompletionCreateParams::PromptCacheOptions^?

Options for prompt caching. Supported for gpt-5.6 and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with prompt_cache_breakpoint. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set mode to explicit to disable the implicit breakpoint. The ttl defaults to 30m, which is currently the only supported value. See the prompt caching guide for current details.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 220

optional :prompt_cache_options, -> { OpenAI::Chat::CompletionCreateParams::PromptCacheOptions }

#prompt_cache_retention ⇒ OpenAI::Models::Chat::CompletionCreateParams::prompt_cache_retention^?

Deprecated. Use prompt_cache_options.ttl instead.

The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. This field expresses a maximum retention policy, while prompt_cache_options.ttl expresses a minimum cache lifetime. The two fields are independent and do not interact. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.

For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:

• Organizations without ZDR enabled default to 24h.
• Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 244

optional(
  :prompt_cache_retention,
  enum: -> { OpenAI::Chat::CompletionCreateParams::PromptCacheRetention },
  nil?: true
)

#reasoning_effort ⇒ OpenAI::Models::reasoning_effort^?

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the reasoning guide for model-specific support.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 259

optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true

#response_format ⇒ OpenAI::Models::Chat::CompletionCreateParams::response_format^?

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 274

optional :response_format, union: -> { OpenAI::Chat::CompletionCreateParams::ResponseFormat }

#safety_identifier ⇒ String^?

A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, 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.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 285

optional :safety_identifier, String, nil?: true

#seed ⇒ Integer^?

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 297

optional :seed, Integer, nil?: true

#service_tier ⇒ OpenAI::Models::Chat::CompletionCreateParams::service_tier^?

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', then the request will be processed with the Flex Processing service tier.
• To opt-in to Fast mode at the request level, include the service_tier=fast or service_tier=priority parameter for Responses or Chat Completions. The response will show service_tier=priority regardless of if you specify service_tier=fast or priority in your request.
• 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:

# File 'lib/openai/models/chat/completion_create_params.rb', line 324

optional :service_tier, enum: -> { OpenAI::Chat::CompletionCreateParams::ServiceTier }, nil?: true

#stop ⇒ OpenAI::Models::Chat::CompletionCreateParams::stop^?

Not supported with latest reasoning models o3 and o4-mini.

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 333

optional :stop, union: -> { OpenAI::Chat::CompletionCreateParams::Stop }, nil?: true

#store ⇒ Boolean^?

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 344

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

#stream_options ⇒ OpenAI::Chat::ChatCompletionStreamOptions^?

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

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 350

optional :stream_options, -> { OpenAI::Chat::ChatCompletionStreamOptions }, 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:

# File 'lib/openai/models/chat/completion_create_params.rb', line 359

optional :temperature, Float, nil?: true

#tool_choice ⇒ OpenAI::Models::Chat::chat_completion_tool_choice_option^?

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

none is the default when no tools are present. auto is the default if tools are present.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 373

optional :tool_choice, union: -> { OpenAI::Chat::ChatCompletionToolChoiceOption }

#tools ⇒ ::Array[OpenAI::Models::Chat::chat_completion_tool]^?

A list of tools the model may call. You can provide either custom tools or function tools.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 382

optional(
  :tools,
  -> {
    OpenAI::Internal::Type::ArrayOf[
      union: OpenAI::UnionOf[
        OpenAI::Chat::ChatCompletionTool,
        OpenAI::StructuredOutput::JsonSchemaConverter
      ]
    ]
  }
)

#top_logprobs ⇒ Integer^?

An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. logprobs must be set to true if this parameter is used.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 401

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:

# File 'lib/openai/models/chat/completion_create_params.rb', line 411

optional :top_p, Float, nil?: true

#user ⇒ String^?

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.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 423

optional :user, String

#verbosity ⇒ OpenAI::Models::Chat::CompletionCreateParams::verbosity^?

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high. The default is medium.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 432

optional :verbosity, enum: -> { OpenAI::Chat::CompletionCreateParams::Verbosity }, nil?: true

#web_search_options ⇒ OpenAI::Chat::CompletionCreateParams::WebSearchOptions^?

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 440

optional :web_search_options, -> { OpenAI::Chat::CompletionCreateParams::WebSearchOptions }

Class Method Details

.values ⇒ Array<Symbol>

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 784

.variants ⇒ Array(OpenAI::Models::ResponseFormatText, OpenAI::Models::ResponseFormatJSONSchema, OpenAI::Models::ResponseFormatJSONObject)

Returns:

# File 'lib/openai/models/chat/completion_create_params.rb', line 746

Instance Method Details

#to_hash ⇒ {

Returns:

# File 'sig/openai/models/chat/completion_create_params.rbs', line 715

def to_hash: -> {