AgentOptimizationJobTokenUsage Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Aggregated token usage for one optimization stage and model.
public class AgentOptimizationJobTokenUsage : System.ClientModel.Primitives.IJsonModel<Azure.AI.Projects.Agents.AgentOptimizationJobTokenUsage>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.Projects.Agents.AgentOptimizationJobTokenUsage>
type AgentOptimizationJobTokenUsage = class
interface IJsonModel<AgentOptimizationJobTokenUsage>
interface IPersistableModel<AgentOptimizationJobTokenUsage>
Public Class AgentOptimizationJobTokenUsage
Implements IJsonModel(Of AgentOptimizationJobTokenUsage), IPersistableModel(Of AgentOptimizationJobTokenUsage)
- Inheritance
-
AgentOptimizationJobTokenUsage
- Implements
Properties
| Name | Description |
|---|---|
| CachedTokens |
Input tokens served from the model's cache. Included in input_tokens and not additive. If omitted, the service defaults to 0. |
| InputTokens |
Total input tokens. Omitted when unmeasured. |
| Model |
Model name or deployment name that served the calls. |
| OutputTokens |
Total output tokens. Omitted when unmeasured. |
| ReasoningTokens |
Reasoning tokens counted separately by reasoning models. Included in output_tokens and not additive. If omitted, the service defaults to 0. |
| Stage |
Optimization stage that generated these calls. |
| TotalTokens |
Sum of input_tokens + output_tokens. Omitted when unmeasured. |