Enum InferenceSpeed

Namespace

Mythosia.AI.Models

Assembly

Mythosia.AI.Abstractions.dll

Selects a provider processing mode without changing the model or reasoning effort.

public enum InferenceSpeed

Fields

Fast = 2

Opt into the provider's premium low-latency processing. Neither latency nor availability is guaranteed.

ProviderDefault = 0

Omit the override and retain the provider's account/project default.

Standard = 1

Explicitly request standard processing.