public sealed class Cost : IMessage<Cost>, IEquatable<Cost>, IDeepCloneable<Cost>, IBufferMessage, IMessageReference documentation and code samples for the GKE Recommender v1 API class Cost.
Cost for running a model deployment on a given instance type. Currently, only USD currency code is supported.
Namespace
Google.Cloud.GkeRecommender.V1Assembly
Google.Cloud.GkeRecommender.V1.dll
Constructors
Cost()
public Cost()Cost(Cost)
public Cost(Cost other)| Parameter | |
|---|---|
| Name | Description |
other |
Cost |
Properties
CostPerMillionInputTokens
public Amount CostPerMillionInputTokens { get; set; }Optional. The cost per million input tokens. $/input token = ($/output token) / output-to-input-cost-ratio.
| Property Value | |
|---|---|
| Type | Description |
Amount |
|
CostPerMillionOutputTokens
public Amount CostPerMillionOutputTokens { get; set; }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)
| Property Value | |
|---|---|
| Type | Description |
Amount |
|
HasOutputInputCostRatio
public bool HasOutputInputCostRatio { get; }Gets whether the "output_input_cost_ratio" field is set
| Property Value | |
|---|---|
| Type | Description |
bool |
|
OutputInputCostRatio
public float OutputInputCostRatio { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
float |
|
PricingModel
public string PricingModel { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
string |
|