class

OpenAI::RealtimeResponseUsageInputTokenDetails

Inherits JSON::Serializable < Reference < Object

Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens.

Constructors

new(pull : JSON::PullParser)

new(cached_tokens : Int64 | Nil = nil, text_tokens : Int64 | Nil = nil, image_tokens : Int64 | Nil = nil, audio_tokens : Int64 | Nil = nil, cached_tokens_details : RealtimeResponseUsageInputTokenDetailsCachedTokensDetails | Nil = nil)

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Instance methods

audio_tokens

The number of audio tokens used as input for the Response.

audio_tokens=(audio_tokens : Int64 | Nil)

The number of audio tokens used as input for the Response.

cached_tokens

The number of cached tokens used as input for the Response.

cached_tokens=(cached_tokens : Int64 | Nil)

The number of cached tokens used as input for the Response.

cached_tokens_details

Details about the cached tokens used as input for the Response.

cached_tokens_details=(cached_tokens_details : RealtimeResponseUsageInputTokenDetailsCachedTokensDetails | Nil)

Details about the cached tokens used as input for the Response.

image_tokens

The number of image tokens used as input for the Response.

image_tokens=(image_tokens : Int64 | Nil)

The number of image tokens used as input for the Response.

text_tokens

The number of text tokens used as input for the Response.

text_tokens=(text_tokens : Int64 | Nil)

The number of text tokens used as input for the Response.