Reference documentation and code samples for the GKE Recommender V1 API class Google::Cloud::GkeRecommender::V1::Cost.
Cost for running a model deployment on a given instance type. Currently, only USD currency code is supported.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#cost_per_million_input_tokens
def cost_per_million_input_tokens() -> ::Google::Cloud::GkeRecommender::V1::Amount
Returns
- (::Google::Cloud::GkeRecommender::V1::Amount) — Optional. The cost per million input tokens. $/input token = ($/output token) / output-to-input-cost-ratio.
#cost_per_million_input_tokens=
def cost_per_million_input_tokens=(value) -> ::Google::Cloud::GkeRecommender::V1::Amount
Parameter
- value (::Google::Cloud::GkeRecommender::V1::Amount) — Optional. The cost per million input tokens. $/input token = ($/output token) / output-to-input-cost-ratio.
Returns
- (::Google::Cloud::GkeRecommender::V1::Amount) — Optional. The cost per million input tokens. $/input token = ($/output token) / output-to-input-cost-ratio.
#cost_per_million_output_tokens
def cost_per_million_output_tokens() -> ::Google::Cloud::GkeRecommender::V1::Amount
Returns
- (::Google::Cloud::GkeRecommender::V1::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_output_tokens=
def cost_per_million_output_tokens=(value) -> ::Google::Cloud::GkeRecommender::V1::Amount
Parameter
- value (::Google::Cloud::GkeRecommender::V1::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)
Returns
- (::Google::Cloud::GkeRecommender::V1::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)
#output_input_cost_ratio
def output_input_cost_ratio() -> ::Float
Returns
-
(::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.
#output_input_cost_ratio=
def output_input_cost_ratio=(value) -> ::Float
Parameter
-
value (::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.
Returns
-
(::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.
#pricing_model
def pricing_model() -> ::String
Returns
-
(::String) — 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.
#pricing_model=
def pricing_model=(value) -> ::String
Parameter
-
value (::String) — 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.
Returns
-
(::String) — 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.