struct AI::OpenAI::OpenAILanguageModelCapabilities

Overview

Capabilities of an OpenAI language model.

Different models have different capabilities and parameter support. This struct captures those differences.

Defined in:

ai/openai/openai_language_model_capabilities.cr

Constructors

Instance Method Summary

Constructor Detail

def self.new(reasoning_model : Bool, system_message_mode : SystemMessageMode, supports_flex_processing : Bool, supports_priority_processing : Bool, supports_non_reasoning_parameters : Bool) #

[View source]

Instance Method Detail

def reasoning_model? : Bool #

Whether this is a reasoning model (o1, o3, gpt-5, etc.).


[View source]
def supports_flex_processing? : Bool #

Whether the model supports flex processing (50% cheaper, higher latency). Available for o3, o4-mini, and gpt-5 models.


[View source]
def supports_non_reasoning_parameters? : Bool #

Whether the model allows temperature, topP, logProbs when reasoningEffort is none. Only gpt-5.1 and gpt-5.2 models support this.


[View source]
def supports_priority_processing? : Bool #

Whether the model supports priority processing (Enterprise feature). Available for gpt-4, gpt-5, gpt-5-mini, o3, o4-mini.


[View source]
def system_message_mode : SystemMessageMode #

How system messages should be handled for this model.


[View source]