struct AI::OpenAI::OpenAIChatProviderOptions

• AI::OpenAI::OpenAIChatProviderOptions
• Struct
• Value
• Object

Overview

Provider-specific options for OpenAI chat language models.

These options can be passed via provider_options["openai"] in the language model call options.

Included Modules

• JSON::Serializable

Defined in:

Constructors

• .new(pull : JSON::PullParser)
• .new(logit_bias : Hash(String, Int32) | Nil = nil, logprobs : Bool | Int32 | Nil = nil, parallel_tool_calls : Bool | Nil = nil, user : String | Nil = nil, reasoning_effort : String | Nil = nil, max_completion_tokens : Int32 | Nil = nil, store : Bool | Nil = nil, metadata : Hash(String, String) | Nil = nil, prediction : Hash(String, JSON::Any) | Nil = nil, service_tier : String | Nil = nil, strict_json_schema : Bool | Nil = nil, text_verbosity : String | Nil = nil, prompt_cache_key : String | Nil = nil, prompt_cache_retention : String | Nil = nil, safety_identifier : String | Nil = nil, system_message_mode : String | Nil = nil, force_reasoning : Bool | Nil = nil)
• .new(*, __pull_for_json_serializable pull : JSON::PullParser)

Instance Method Summary

• #force_reasoning : Bool | Nil

  Force treating this model as a reasoning model.

• #logit_bias : Hash(String, Int32) | Nil

  Modify the likelihood of specified tokens appearing in the completion.

• #logprobs : Bool | Int32 | Nil

  Return the log probabilities of the tokens.

• #max_completion_tokens : Int32 | Nil

  Maximum number of completion tokens to generate.

• #metadata : Hash(String, String) | Nil

  Metadata to associate with the request.

• #parallel_tool_calls : Bool | Nil

  Whether to enable parallel function calling during tool use.

• #prediction : Hash(String, JSON::Any) | Nil

  Parameters for prediction mode.

• #prompt_cache_key : String | Nil

  A cache key for prompt caching.

• #prompt_cache_retention : String | Nil

  The retention policy for the prompt cache.

• #reasoning_effort : String | Nil

  Reasoning effort for reasoning models.

• #safety_identifier : String | Nil

  A stable identifier used to help detect users violating usage policies.

• #service_tier : String | Nil

  Service tier for the request.

• #store : Bool | Nil

  Whether to enable persistence in responses API.

• #strict_json_schema : Bool | Nil

  Whether to use strict JSON schema validation.

• #system_message_mode : String | Nil

  Override the system message mode for this model.

• #text_verbosity : String | Nil

  Controls the verbosity of the model's responses.

• #user : String | Nil

  A unique identifier representing your end-user.

Constructor Detail

Instance Method Detail