IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python class

Usage

Usage​

class max.pipelines.request.Usage(*, input_tokens, output_tokens, total_tokens, input_tokens_details=None, output_tokens_details=None, image_generation_details=None, audio_generation_details=None)

source

Bases: BaseModel

Token usage statistics.

Image and audio generation responses keep input_tokens, output_tokens, and total_tokens at 0 and report billing-relevant metadata in image_generation_details and audio_generation_details. Neither task consumes or produces tokens that mean anything to a caller: the prompt tokens are an implementation detail of the model’s conditioning, and the output is samples or pixels.

Parameters:

audio_generation_details​

audio_generation_details: AudioGenerationDetails | None

source

image_generation_details​

image_generation_details: ImageGenerationDetails | None

source

input_tokens​

input_tokens: int

source

input_tokens_details​

input_tokens_details: InputTokensDetails | None

source

model_config​

model_config: ClassVar[ConfigDict] = {'frozen': True}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

output_tokens​

output_tokens: int

source

output_tokens_details​

output_tokens_details: OutputTokensDetails | None

source

total_tokens​

total_tokens: int

source