Class ReasoningOptions

Inheritance
object
ReasoningOptions
Inherited Members
Namespace: Glitch9.AIDevKit
Assembly: Glitch9.AIDevKit.dll
Syntax
[Serializable]
[JsonConverter(typeof(ReasoningOptionsConverter))]
public sealed class ReasoningOptions

Fields

| Edit this page View Source

BudgetTokens

Anthropic-specific parameter Required. Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.

Must be 1024 and less than max_tokens.

See extended thinking for details.

Declaration
[ApiSpecificProperty(Api.Anthropic, "budget_tokens")]
[ApiSpecificProperty(Api.OpenRouter, "max_tokens")]
[SerializeField]
public int BudgetTokens
Field Value
Type Description
int
| Edit this page View Source

Effort

Optional. Defaults to medium Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Declaration
[SerializeField]
[JsonProperty("effort")]
public ReasoningEffort Effort
Field Value
Type Description
ReasoningEffort
| Edit this page View Source

Exclude

Optional. Whether to exclude reasoning from the response Defaults to false

Declaration
[SerializeField]
[ApiSpecificProperty(Api.OpenRouter, "exclude")]
public bool Exclude
Field Value
Type Description
bool
| Edit this page View Source

Format

GroqCloud-specific parameter. Specifies how to output reasoning tokens

Declaration
[SerializeField]
[ApiSpecificProperty(Api.GroqCloud, "format")]
public ReasoningFormat Format
Field Value
Type Description
ReasoningFormat
| Edit this page View Source

Summary

Optional. A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.

Declaration
[SerializeField]
[JsonProperty("summary")]
public ReasoningSummaryLevel Summary
Field Value
Type Description
ReasoningSummaryLevel

Extension Methods