Cost(mapping=None, *, ignore_unknown_fields=False, **kwargs)Cost for running a model deployment on a given instance type. Currently, only USD currency code is supported.
.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields
Attributes |
|
|---|---|
| Name | Description |
cost_per_million_output_tokens |
google.cloud.gkerecommender_v1.types.Amount
Optional. The cost per million output tokens, calculated as: $/output token = GPU $/s / (1/output-to-input-cost-ratio \* input tokens/s + output tokens/s) |
cost_per_million_input_tokens |
google.cloud.gkerecommender_v1.types.Amount
Optional. The cost per million input tokens. $/input token = ($/output token) / output-to-input-cost-ratio. |
pricing_model |
str
Optional. The pricing model used to calculate the cost. Can be one of: 3-years-cud, 1-year-cud, on-demand,
spot. If not provided, spot will be used.
|
output_input_cost_ratio |
float
Optional. The output-to-input cost ratio. This determines how the total GPU cost is split between input and output tokens. If not provided, 4.0 is used, assuming a 4:1
output:input cost ratio.
This field is a member of oneof_ _output_input_cost_ratio.
|