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

Inherits:
Internal::Type::BaseModel show all
Extended by:
Internal::Type::RequestParameters::Converter
Includes:
Internal::Type::RequestParameters
Defined in:
lib/openai/models/chat/completion_create_params.rb

Overview

See Also:

Defined Under Namespace

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

Instance Attribute Summary collapse

Attributes included from Internal::Type::RequestParameters

#request_options

Class Method Summary collapse

Instance Method Summary collapse

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, 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

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

Parameters:

  • name (String) —

    The name of the function to be called. Must be a-z, A-Z, 0-9, or contain undersc

  • description (String) (defaults to: nil) —

    A description of what the function does, used by the model to choose when and ho

  • parameters (Hash{Symbol=>Object}) (defaults to: nil) —

    The parameters the functions accepts, described as a JSON Schema object. See the




# File 'lib/openai/models/chat/completion_create_params.rb', line 387

Instance Attribute Details

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

Parameters for audio output. Required when audio output is requested with ‘modalities: [“audio”]`. [Learn more](platform.openai.com/docs/guides/audio).

Returns:



41
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 41

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:

  • (Float, nil) 


49
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 49

optional :frequency_penalty, Float, nil?: true

#function_call ⇒ Symbol, ...

Deprecated.

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 ‘“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:



70
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 70

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

#functions ⇒ Array<OpenAI::Models::Chat::CompletionCreateParams::Function>?

Deprecated.

Deprecated in favor of ‘tools`.

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

Returns:



80
81
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 80

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:

  • (Hash{Symbol=>Integer}, nil) 


94
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 94

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:



102
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 102

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](platform.openai.com/docs/guides/reasoning).

Returns:

  • (Integer, nil) 


110
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 110

optional :max_completion_tokens, Integer, nil?: true

#max_tokens ⇒ Integer?

Deprecated.

The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](openai.com/api/pricing/) for text generated via API.

This value is now deprecated in favor of ‘max_completion_tokens`, and is not compatible with [o-series models](platform.openai.com/docs/guides/reasoning).

Returns:

  • (Integer, nil) 


124
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 124

optional :max_tokens, Integer, nil?: true

#messages ⇒ Array<OpenAI::Models::Chat::ChatCompletionDeveloperMessageParam, OpenAI::Models::Chat::ChatCompletionSystemMessageParam, OpenAI::Models::Chat::ChatCompletionUserMessageParam, OpenAI::Models::Chat::ChatCompletionAssistantMessageParam, OpenAI::Models::Chat::ChatCompletionToolMessageParam, OpenAI::Models::Chat::ChatCompletionFunctionMessageParam>

A list of messages comprising the conversation so far. Depending on the [model](platform.openai.com/docs/models) you use, different message types (modalities) are supported, like [text](platform.openai.com/docs/guides/text-generation), [images](platform.openai.com/docs/guides/vision), and [audio](platform.openai.com/docs/guides/audio).

Returns:



22
23
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 22

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

#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) 


135
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 135

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

#modalities ⇒ Array<Symbol, 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](platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use:

‘[“text”, “audio”]`

Returns:



150
151
152
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 150

optional :modalities,
-> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Chat::CompletionCreateParams::Modality] },
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:



33
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 33

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

#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:

  • (Integer, nil) 


160
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 160

optional :n, Integer, nil?: true

#parallel_tool_calls ⇒ Boolean?

Whether to enable [parallel function calling](platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use.

Returns:



168
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 168

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

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

Static predicted output content, such as the content of a text file that is being regenerated.

Returns:



175
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 175

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:

  • (Float, nil) 


183
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 183

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](platform.openai.com/docs/guides/prompt-caching).

Returns:

  • (String, nil) 


191
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 191

optional :prompt_cache_key, String

#prompt_cache_retention ⇒ Symbol, ...

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](platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).

Returns:



200
201
202
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 200

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

#reasoning_effort ⇒ Symbol, ...

Constrains effort on reasoning for [reasoning models](platform.openai.com/docs/guides/reasoning). Currently supported values are ‘none`, `minimal`, `low`, `medium`, `high`, and `xhigh`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

  • ‘gpt-5.1` defaults to `none`, which does not perform reasoning. The supported reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool calls are supported for all reasoning values in gpt-5.1.

  • All models before ‘gpt-5.1` default to `medium` reasoning effort, and do not support `none`.

  • The ‘gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.

  • ‘xhigh` is supported for all models after `gpt-5.1-codex-max`.

Returns:



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

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

#response_format ⇒ OpenAI::Models::ResponseFormatText, ...

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](platform.openai.com/docs/guides/structured-outputs).

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:



235
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 235

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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).

Returns:

  • (String, nil) 


245
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 245

optional :safety_identifier, String

#seed ⇒ Integer?

Deprecated.

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:

  • (Integer, nil) 


257
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 257

optional :seed, Integer, 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 request 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](openai.com/api-priority-processing/)’, then the request will be processed with the corresponding service tier.

  • When not set, the default behavior is ‘auto’.

When the ‘service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

Returns:



278
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 278

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

#stop ⇒ String, ...

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:

  • (String, Array<String>, nil) 


287
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 287

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](platform.openai.com/docs/guides/distillation) or [evals](platform.openai.com/docs/guides/evals) products.

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

Returns:



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

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

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

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

Returns:



303
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 303

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:

  • (Float, nil) 


312
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 312

optional :temperature, Float, nil?: true

#tool_choice ⇒ Symbol, ...

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 `“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:



326
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 326

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

#tools ⇒ Array<OpenAI::Models::Chat::ChatCompletionTool, OpenAI::StructuredOutput::JsonSchemaConverter>?

A list of tools the model may call. You can provide either [custom tools](platform.openai.com/docs/guides/function-calling#custom-tools) or [function tools](platform.openai.com/docs/guides/function-calling).

Returns:



334
335
336
337
338
339
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 334

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 number of most likely tokens to return at each token position, each with an associated log probability. ‘logprobs` must be set to `true` if this parameter is used.

Returns:

  • (Integer, nil) 


347
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 347

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) 


357
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 357

optional :top_p, Float, nil?: true

#user ⇒ String?

Deprecated.

This field is being replaced by ‘safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).

Returns:

  • (String, nil) 


369
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 369

optional :user, String

#verbosity ⇒ Symbol, ...

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`.

Returns:



377
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 377

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

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

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

Returns:



385
 
# File 'lib/openai/models/chat/completion_create_params.rb', line 385

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

Class Method Details

.values ⇒ Array<Symbol>

Returns:

  • (Array<Symbol>) 



# File 'lib/openai/models/chat/completion_create_params.rb', line 515

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

Returns:




# File 'lib/openai/models/chat/completion_create_params.rb', line 477