ReasoningEffort
Constrains the amount of effort a reasoning-capable model spends on internal reasoning.
Lower settings can yield faster responses and fewer reasoning tokens; higher settings may improve performance on multistep or complex tasks at the cost of additional latency and token usage. Exact effects are model-dependent. If not set, the model/provider default applies.
Serialized as "minimal" | "low" | "medium" | "high".
Entries
Strongly limits internal reasoning to minimize latency and cost. Best for simple, well-specified tasks where extra deliberation is unnecessary. Serialized as "minimal".
Allows a small amount of reasoning while prioritizing speed and efficiency. Suitable for straightforward prompts with occasional light chaining. Serialized as "low".
Balanced allowance for reasoning to handle typical multi-step tasks without excessive overhead. Serialized as "medium".
Maximizes the model’s reasoning depth for complex or ambiguous problems. Expect higher latency and token usage. Serialized as "high".
Properties
Functions
Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)
Returns an array containing the constants of this enum type, in the order they're declared.